Compare commits

...
17 Commits
Author SHA1 Message Date
Alexander Graf 6c779e8d4b First Beta Release for Version 4.5 2020-07-30 17:17:55 +02:00
Alexander Graf c24015a93d Merge branch 'master' into upcoming/v4.5 2020-07-30 17:16:00 +02:00
Alexander Graf 2c56e6994a Enhance Documentation Theme
Improvements on our bootstrap 4 theme for sphinx.
2020-07-30 17:02:43 +02:00
Alexander Graf 6791e9a2f8 Textual Improvements on Documentation
- Fix spelling errors / typos,

- Remove deprecated command line options from doc.
2020-07-30 16:41:45 +02:00
Alexander Graf 64652f3994 Feature Request template: PR -> pull request 2020-07-30 13:20:02 +02:00
Alexander Graf 4f5b223b60 Minor docs fixes 2020-07-26 19:00:01 +02:00
Alexander Graf 2a3711687f Update deps used in CI (esp. MyPy and PyLint) 2020-07-26 18:54:23 +02:00
Alexander Graf 612842f255 Minor nodeiterator-related docs improvements 2020-07-26 18:05:46 +02:00
Alexander Graf fe9cd653e7 docs: Improvements to branded syntax highlighting 2020-07-26 18:01:33 +02:00
Alexander Graf 82e7b19d6d docs: Split as-module into smaller documents 2020-07-26 18:00:37 +02:00
Alexander Graf 5d7c36399f Windows: Sanitize Path of Resume Files 2020-07-24 18:35:10 +02:00
Alexander Graf f0e66ef465 Windows EXE: Fix CommandNotFoundException
Fixes CommandNotFoundException that occured when started from within a
directory whose name contains a space.
2020-07-24 17:19:48 +02:00
Alexander Graf f71ea562af First Alpha Release for Version 4.5 2020-07-21 17:37:45 +02:00
Alexander Graf bc40b82f94 Resume a previously-aborted post download loop (#732)
With this change, Instaloader is capable of resuming a previously-aborted download loop. To do so, it creates a JSON file within the target directory when interrupted, that contains all the necessary information to later resume that operation.

Resuming an interrupted download is supported for most, but not all targets. It is supported for:

- Regular profile posts,
- IGTV posts
- Saved posts,
- Tagged posts,
- Explore posts.
2020-07-21 17:28:55 +02:00
Alexander Graf c817d1901a Merge branch 'master' into upcoming/v4.5 2020-07-18 15:32:05 +02:00
Alexander Graf fbe05a1add More flexible Rate Controller (#716)
Move InstaloaderContext's rate controlling logic into a class
RateController with fine-grained methods to enable easily changing
Instaloader's behavior regarding rate limits.
2020-07-11 13:54:31 +02:00
Lars Lindqvist fa62025ea3 Deprecate commit-mode (#697)
Rather than checking the json file to make sure posts have been
successfully downloaded, data is stored in a temporary file which
is renamed when downloading has finished, as suggested in #257.
2020-06-20 16:23:31 +02:00
33 changed files with 1088 additions and 876 deletions
+1 -1
View File
@@ -14,7 +14,7 @@ A clear and concise description of what you want to happen.
**Describe alternatives you've considered**
A clear and concise description of any alternative solutions or features you've considered.
**If the feature request is accepted, would you be willing to submit a PR?**
**If the feature request is accepted, would you be willing to submit a pull request?**
Yes / No
<!-- Help can be provided if you need assistance submitting a PR -->
+1 -1
View File
@@ -6,7 +6,7 @@ verify_ssl = true
[dev-packages]
pylint = "*"
mypy = "*"
sphinx = "*"
sphinx = "~=2.3"
pyinstaller = "*"
pefile = "*"
pywin32-ctypes = "*"
Generated
+108 -100
View File
@@ -1,7 +1,7 @@
{
"_meta": {
"hash": {
"sha256": "33408a60fda1a56bf680462fad21643ae0159bc13f3b85d8f10ebf3eef7d8725"
"sha256": "58caf1be034bed9aa7ebb8c78e75ffa7d7abe820d014b6398c444a5db566b306"
},
"pipfile-spec": 6,
"requires": {},
@@ -16,10 +16,10 @@
"default": {
"certifi": {
"hashes": [
"sha256:017c25db2a153ce562900032d5bc68e9f191e44e9a0f762f373977de9df1fbb3",
"sha256:25b64c7da4cd7479594d035c08c2d809eb4aab3a26e5a990ea98cc450c320f1f"
"sha256:5930595817496dd21bb8dc35dad090f1c2cd0adfaf21204bf6732ca5d8ee34d3",
"sha256:8fc0819f1f30ba15bdb34cceffb9ef04d99f420f68eb75d901e9560b8749fc41"
],
"version": "==2019.11.28"
"version": "==2020.6.20"
},
"chardet": {
"hashes": [
@@ -30,25 +30,25 @@
},
"idna": {
"hashes": [
"sha256:c357b3f628cf53ae2c4c05627ecc484553142ca23264e593d327bcde5e9c3407",
"sha256:ea8b7f6188e6fa117537c3df7da9fc686d485087abf6ac197f9c46432f7e4a3c"
"sha256:b307872f855b18632ce0c21c5e45be78c0ea7ae4c15c828c20788b26921eb3f6",
"sha256:b97d804b1e9b523befed77c48dacec60e6dcb0b5391d57af6a65a312a90648c0"
],
"version": "==2.8"
"version": "==2.10"
},
"requests": {
"hashes": [
"sha256:11e007a8a2aa0323f5a921e9e6a2d7e4e67d9877e85773fba9ba6419025cbeb4",
"sha256:9cf5292fcd0f598c671cfc1e0d7d1a7f13bb8085e9a590f48c010551dc6c4b31"
"sha256:b3559a131db72c33ee969480840fff4bb6dd111de7dd27c8ee1f820f4f00231b",
"sha256:fe75cc94a9443b9246fc7049224f75604b113c36acb93f87b80ed42c44cbb898"
],
"index": "pypi",
"version": "==2.22.0"
"version": "==2.24.0"
},
"urllib3": {
"hashes": [
"sha256:2f3db8b19923a873b3e5256dc9c2dedfa883e33d87c690d9c7913e1f40673cdc",
"sha256:87716c2d2a7121198ebcb7ce7cccf6ce5e9ba539041cfbaeecfb641dc0bf6acc"
"sha256:91056c15fa70756691db97756772bb1eb9678fa585d9184f24534b100dc60f4a",
"sha256:e7983572181f5e1522d9c98453462384ee92a0be7fac5f1413a1e35c56cc0461"
],
"version": "==1.25.8"
"version": "==1.25.10"
}
},
"develop": {
@@ -68,10 +68,10 @@
},
"astroid": {
"hashes": [
"sha256:71ea07f44df9568a75d0f354c49143a4575d90645e9fead6dfb52c26a85ed13a",
"sha256:840947ebfa8b58f318d42301cf8c0a20fd794a33b61cc4638e28e9e61ba32f42"
"sha256:2f4078c2a41bf377eea06d71c9d2ba4eb8f6b1af2135bec27bbbb7d8f12bb703",
"sha256:bc58d83eb610252fd8de6363e39d4f1d0619c894b0ed24603b881c02e64c7386"
],
"version": "==2.3.3"
"version": "==2.4.2"
},
"babel": {
"hashes": [
@@ -82,10 +82,10 @@
},
"certifi": {
"hashes": [
"sha256:017c25db2a153ce562900032d5bc68e9f191e44e9a0f762f373977de9df1fbb3",
"sha256:25b64c7da4cd7479594d035c08c2d809eb4aab3a26e5a990ea98cc450c320f1f"
"sha256:5930595817496dd21bb8dc35dad090f1c2cd0adfaf21204bf6732ca5d8ee34d3",
"sha256:8fc0819f1f30ba15bdb34cceffb9ef04d99f420f68eb75d901e9560b8749fc41"
],
"version": "==2019.11.28"
"version": "==2020.6.20"
},
"chardet": {
"hashes": [
@@ -109,10 +109,10 @@
},
"idna": {
"hashes": [
"sha256:c357b3f628cf53ae2c4c05627ecc484553142ca23264e593d327bcde5e9c3407",
"sha256:ea8b7f6188e6fa117537c3df7da9fc686d485087abf6ac197f9c46432f7e4a3c"
"sha256:b307872f855b18632ce0c21c5e45be78c0ea7ae4c15c828c20788b26921eb3f6",
"sha256:b97d804b1e9b523befed77c48dacec60e6dcb0b5391d57af6a65a312a90648c0"
],
"version": "==2.8"
"version": "==2.10"
},
"imagesize": {
"hashes": [
@@ -130,10 +130,10 @@
},
"jinja2": {
"hashes": [
"sha256:93187ffbc7808079673ef52771baa950426fd664d3aad1d0fa3e95644360e250",
"sha256:b0eaf100007721b5c16c1fc1eecb87409464edc10469ddc9a22a27a99123be49"
"sha256:89aab215427ef59c34ad58735269eb58b1a5808103067f7bb9d5836c651b3bb0",
"sha256:f0a4641d3cf955324a89c04f3d94663aa4d638abe8f733ecd3582848e1c37035"
],
"version": "==2.11.1"
"version": "==2.11.2"
},
"lazy-object-proxy": {
"hashes": [
@@ -208,23 +208,23 @@
},
"mypy": {
"hashes": [
"sha256:0a9a45157e532da06fe56adcfef8a74629566b607fa2c1ac0122d1ff995c748a",
"sha256:2c35cae79ceb20d47facfad51f952df16c2ae9f45db6cb38405a3da1cf8fc0a7",
"sha256:4b9365ade157794cef9685791032521233729cb00ce76b0ddc78749abea463d2",
"sha256:53ea810ae3f83f9c9b452582261ea859828a9ed666f2e1ca840300b69322c474",
"sha256:634aef60b4ff0f650d3e59d4374626ca6153fcaff96ec075b215b568e6ee3cb0",
"sha256:7e396ce53cacd5596ff6d191b47ab0ea18f8e0ec04e15d69728d530e86d4c217",
"sha256:7eadc91af8270455e0d73565b8964da1642fe226665dd5c9560067cd64d56749",
"sha256:7f672d02fffcbace4db2b05369142e0506cdcde20cea0e07c7c2171c4fd11dd6",
"sha256:85baab8d74ec601e86134afe2bcccd87820f79d2f8d5798c889507d1088287bf",
"sha256:87c556fb85d709dacd4b4cb6167eecc5bbb4f0a9864b69136a0d4640fdc76a36",
"sha256:a6bd44efee4dc8c3324c13785a9dc3519b3ee3a92cada42d2b57762b7053b49b",
"sha256:c6d27bd20c3ba60d5b02f20bd28e20091d6286a699174dfad515636cb09b5a72",
"sha256:e2bb577d10d09a2d8822a042a23b8d62bc3b269667c9eb8e60a6edfa000211b1",
"sha256:f97a605d7c8bc2c6d1172c2f0d5a65b24142e11a58de689046e62c2d632ca8c1"
"sha256:2c6cde8aa3426c1682d35190b59b71f661237d74b053822ea3d748e2c9578a7c",
"sha256:3fdda71c067d3ddfb21da4b80e2686b71e9e5c72cca65fa216d207a358827f86",
"sha256:5dd13ff1f2a97f94540fd37a49e5d255950ebcdf446fb597463a40d0df3fac8b",
"sha256:6731603dfe0ce4352c555c6284c6db0dc935b685e9ce2e4cf220abe1e14386fd",
"sha256:6bb93479caa6619d21d6e7160c552c1193f6952f0668cdda2f851156e85186fc",
"sha256:81c7908b94239c4010e16642c9102bfc958ab14e36048fa77d0be3289dda76ea",
"sha256:9c7a9a7ceb2871ba4bac1cf7217a7dd9ccd44c27c2950edbc6dc08530f32ad4e",
"sha256:a4a2cbcfc4cbf45cd126f531dedda8485671545b43107ded25ce952aac6fb308",
"sha256:b7fbfabdbcc78c4f6fc4712544b9b0d6bf171069c6e0e3cb82440dd10ced3406",
"sha256:c05b9e4fb1d8a41d41dec8786c94f3b95d3c5f528298d769eb8e73d293abc48d",
"sha256:d7df6eddb6054d21ca4d3c6249cae5578cb4602951fd2b6ee2f5510ffb098707",
"sha256:e0b61738ab504e656d1fe4ff0c0601387a5489ca122d55390ade31f9ca0e252d",
"sha256:eff7d4a85e9eea55afa34888dfeaccde99e7520b51f867ac28a48492c0b1130c",
"sha256:f05644db6779387ccdb468cc47a44b4356fc2ffa9287135d05b70a98dc83b89a"
],
"index": "pypi",
"version": "==0.761"
"version": "==0.782"
},
"mypy-extensions": {
"hashes": [
@@ -235,10 +235,10 @@
},
"packaging": {
"hashes": [
"sha256:170748228214b70b672c581a3dd610ee51f733018650740e98c7df862a583f73",
"sha256:e665345f9eef0c621aa0bf2f8d78cf6d21904eef16a93f020240b704a57f1334"
"sha256:4357f74f47b9c12db93624a82154e9b120fa8293699949152b22065d556079f8",
"sha256:998416ba6962ae7fbd6596850b80e17859a5753ba17c32284f67bfff33784181"
],
"version": "==20.1"
"version": "==20.4"
},
"pefile": {
"hashes": [
@@ -249,27 +249,27 @@
},
"psutil": {
"hashes": [
"sha256:094f899ac3ef72422b7e00411b4ed174e3c5a2e04c267db6643937ddba67a05b",
"sha256:10b7f75cc8bd676cfc6fa40cd7d5c25b3f45a0e06d43becd7c2d2871cbb5e806",
"sha256:1b1575240ca9a90b437e5a40db662acd87bbf181f6aa02f0204978737b913c6b",
"sha256:21231ef1c1a89728e29b98a885b8e0a8e00d09018f6da5cdc1f43f988471a995",
"sha256:28f771129bfee9fc6b63d83a15d857663bbdcae3828e1cb926e91320a9b5b5cd",
"sha256:70387772f84fa5c3bb6a106915a2445e20ac8f9821c5914d7cbde148f4d7ff73",
"sha256:b560f5cd86cf8df7bcd258a851ca1ad98f0d5b8b98748e877a0aec4e9032b465",
"sha256:b74b43fecce384a57094a83d2778cdfc2e2d9a6afaadd1ebecb2e75e0d34e10d",
"sha256:e85f727ffb21539849e6012f47b12f6dd4c44965e56591d8dec6e8bc9ab96f4a",
"sha256:fd2e09bb593ad9bdd7429e779699d2d47c1268cbde4dda95fcd1bd17544a0217",
"sha256:ffad8eb2ac614518bbe3c0b8eb9dffdb3a8d2e3a7d5da51c5b974fb723a5c5aa"
"sha256:0ee3c36428f160d2d8fce3c583a0353e848abb7de9732c50cf3356dd49ad63f8",
"sha256:10512b46c95b02842c225f58fa00385c08fa00c68bac7da2d9a58ebe2c517498",
"sha256:4080869ed93cce662905b029a1770fe89c98787e543fa7347f075ade761b19d6",
"sha256:5e9d0f26d4194479a13d5f4b3798260c20cecf9ac9a461e718eb59ea520a360c",
"sha256:66c18ca7680a31bf16ee22b1d21b6397869dda8059dbdb57d9f27efa6615f195",
"sha256:68d36986ded5dac7c2dcd42f2682af1db80d4bce3faa126a6145c1637e1b559f",
"sha256:90990af1c3c67195c44c9a889184f84f5b2320dce3ee3acbd054e3ba0b4a7beb",
"sha256:a5b120bb3c0c71dfe27551f9da2f3209a8257a178ed6c628a819037a8df487f1",
"sha256:d8a82162f23c53b8525cf5f14a355f5d1eea86fa8edde27287dd3a98399e4fdf",
"sha256:f2018461733b23f308c298653c8903d32aaad7873d25e1d228765e91ae42c3f2",
"sha256:ff1977ba1a5f71f89166d5145c3da1cea89a0fdb044075a12c720ee9123ec818"
],
"index": "pypi",
"version": "==5.6.7"
"version": "==5.7.2"
},
"pygments": {
"hashes": [
"sha256:2a3fe295e54a20164a9df49c75fa58526d3be48e14aceba6d6b1e8ac0bfd6f1b",
"sha256:98c8aa5a9f778fcd1026a17361ddaf7330d1b7c62ae97c3bb0ae73e0b9b6b0fe"
"sha256:647344a061c249a3b74e230c739f434d7ea4d8b1d5f3721bc0f3558049b38f44",
"sha256:ff7a40b4860b727ab48fad6360eb351cc1b33cbf9b15a0f689ca5353e9463324"
],
"version": "==2.5.2"
"version": "==2.6.1"
},
"pyinstaller": {
"hashes": [
@@ -280,25 +280,25 @@
},
"pylint": {
"hashes": [
"sha256:3db5468ad013380e987410a8d6956226963aed94ecb5f9d3a28acca6d9ac36cd",
"sha256:886e6afc935ea2590b462664b161ca9a5e40168ea99e5300935f6591ad467df4"
"sha256:7dd78437f2d8d019717dbf287772d0b2dbdfd13fc016aa7faa08d67bccc46adc",
"sha256:d0ece7d223fe422088b0e8f13fa0a1e8eb745ebffcb8ed53d3e95394b6101a1c"
],
"index": "pypi",
"version": "==2.4.4"
"version": "==2.5.3"
},
"pyparsing": {
"hashes": [
"sha256:4c830582a84fb022400b85429791bc551f1f4871c33f23e44f353119e92f969f",
"sha256:c342dccb5250c08d45fd6f8b4a559613ca603b57498511740e65cd11a2e7dcec"
"sha256:c203ec8783bf771a155b207279b9bccb8dea02d8f0c9e5f8ead507bc3246ecc1",
"sha256:ef9d7589ef3c200abe66653d3f1ab1033c3c419ae9b9bdb1240a85b024efc88b"
],
"version": "==2.4.6"
"version": "==2.4.7"
},
"pytz": {
"hashes": [
"sha256:1c557d7d0e871de1f5ccd5833f60fb2550652da6be2693c1e02300743d21500d",
"sha256:b02c06db6cf09c12dd25137e563b31700d3b80fcc4ad23abb7a315f2789819be"
"sha256:a494d53b6d39c3c6e44c3bec237336e14305e4f29bbf800b599253057fbb79ed",
"sha256:c35965d010ce31b23eeb663ed3cc8c906275d6be1a34393a1d73a41febf4a048"
],
"version": "==2019.3"
"version": "==2020.1"
},
"pywin32-ctypes": {
"hashes": [
@@ -310,18 +310,18 @@
},
"requests": {
"hashes": [
"sha256:11e007a8a2aa0323f5a921e9e6a2d7e4e67d9877e85773fba9ba6419025cbeb4",
"sha256:9cf5292fcd0f598c671cfc1e0d7d1a7f13bb8085e9a590f48c010551dc6c4b31"
"sha256:b3559a131db72c33ee969480840fff4bb6dd111de7dd27c8ee1f820f4f00231b",
"sha256:fe75cc94a9443b9246fc7049224f75604b113c36acb93f87b80ed42c44cbb898"
],
"index": "pypi",
"version": "==2.22.0"
"version": "==2.24.0"
},
"six": {
"hashes": [
"sha256:236bdbdce46e6e6a3d61a337c0f8b763ca1e8717c03b369e87a7ec7ce1319c0a",
"sha256:8f3cd2e254d8f793e7f3d6d9df77b92252b52637291d0f0da013c76ea2724b6c"
"sha256:30639c035cdb23534cd4aa2dd52c3bf48f06e5f4a941509c8bafd8ce11080259",
"sha256:8b74bedcbbbaca38ff6d7491d76f2b06b3592611af620f8426e82dddb04a5ced"
],
"version": "==1.14.0"
"version": "==1.15.0"
},
"snowballstemmer": {
"hashes": [
@@ -332,32 +332,32 @@
},
"sphinx": {
"hashes": [
"sha256:298537cb3234578b2d954ff18c5608468229e116a9757af3b831c2b2b4819159",
"sha256:e6e766b74f85f37a5f3e0773a1e1be8db3fcb799deb58ca6d18b70b0b44542a5"
"sha256:b4c750d546ab6d7e05bdff6ac24db8ae3e8b8253a3569b754e445110a0a12b66",
"sha256:fc312670b56cb54920d6cc2ced455a22a547910de10b3142276495ced49231cb"
],
"index": "pypi",
"version": "==2.3.1"
"version": "==2.4.4"
},
"sphinxcontrib-applehelp": {
"hashes": [
"sha256:edaa0ab2b2bc74403149cb0209d6775c96de797dfd5b5e2a71981309efab3897",
"sha256:fb8dee85af95e5c30c91f10e7eb3c8967308518e0f7488a2828ef7bc191d0d5d"
"sha256:806111e5e962be97c29ec4c1e7fe277bfd19e9652fb1a4392105b43e01af885a",
"sha256:a072735ec80e7675e3f432fcae8610ecf509c5f1869d17e2eecff44389cdbc58"
],
"version": "==1.0.1"
"version": "==1.0.2"
},
"sphinxcontrib-devhelp": {
"hashes": [
"sha256:6c64b077937330a9128a4da74586e8c2130262f014689b4b89e2d08ee7294a34",
"sha256:9512ecb00a2b0821a146736b39f7aeb90759834b07e81e8cc23a9c70bacb9981"
"sha256:8165223f9a335cc1af7ffe1ed31d2871f325254c0423bc0c4c7cd1c1e4734a2e",
"sha256:ff7f1afa7b9642e7060379360a67e9c41e8f3121f2ce9164266f61b9f4b338e4"
],
"version": "==1.0.1"
"version": "==1.0.2"
},
"sphinxcontrib-htmlhelp": {
"hashes": [
"sha256:4670f99f8951bd78cd4ad2ab962f798f5618b17675c35c5ac3b2132a14ea8422",
"sha256:d4fd39a65a625c9df86d7fa8a2d9f3cd8299a3a4b15db63b50aac9e161d8eff7"
"sha256:3c0bc24a2c41e340ac37c85ced6dafc879ab485c095b1d65d2461ac2f7cca86f",
"sha256:e8f5bb7e31b2dbb25b9cc435c8ab7a79787ebf7f906155729338f3156d93659b"
],
"version": "==1.0.2"
"version": "==1.0.3"
},
"sphinxcontrib-jsmath": {
"hashes": [
@@ -368,17 +368,24 @@
},
"sphinxcontrib-qthelp": {
"hashes": [
"sha256:513049b93031beb1f57d4daea74068a4feb77aa5630f856fcff2e50de14e9a20",
"sha256:79465ce11ae5694ff165becda529a600c754f4bc459778778c7017374d4d406f"
"sha256:4c33767ee058b70dba89a6fc5c1892c0d57a54be67ddd3e7875a18d14cba5a72",
"sha256:bd9fc24bcb748a8d51fd4ecaade681350aa63009a347a8c14e637895444dfab6"
],
"version": "==1.0.2"
"version": "==1.0.3"
},
"sphinxcontrib-serializinghtml": {
"hashes": [
"sha256:c0efb33f8052c04fd7a26c0a07f1678e8512e0faec19f4aa8f2473a8b81d5227",
"sha256:db6615af393650bf1151a6cd39120c29abaf93cc60db8c48eb2dddbfdc3a9768"
"sha256:eaa0eccc86e982a9b939b2b82d12cc5d013385ba5eadcc7e4fed23f4405f77bc",
"sha256:f242a81d423f59617a8e5cf16f5d4d74e28ee9a66f9e5b637a18082991db5a9a"
],
"version": "==1.1.3"
"version": "==1.1.4"
},
"toml": {
"hashes": [
"sha256:926b612be1e5ce0634a2ca03470f95169cf16f939018233a670519cb4ac58b0f",
"sha256:bda89d5935c2eac546d648028b9901107a595863cb36bae0c73ac804a9b4ce88"
],
"version": "==0.10.1"
},
"typed-ast": {
"hashes": [
@@ -404,28 +411,29 @@
"sha256:fc0fea399acb12edbf8a628ba8d2312f583bdbdb3335635db062fa98cf71fca4",
"sha256:fe460b922ec15dd205595c9b5b99e2f056fd98ae8f9f56b888e7a17dc2b757e7"
],
"markers": "implementation_name == 'cpython' and python_version < '3.8'",
"version": "==1.4.1"
},
"typing-extensions": {
"hashes": [
"sha256:091ecc894d5e908ac75209f10d5b4f118fbdb2eb1ede6a63544054bb1edb41f2",
"sha256:910f4656f54de5993ad9304959ce9bb903f90aadc7c67a0bef07e678014e892d",
"sha256:cf8b63fedea4d89bab840ecbb93e75578af28f76f66c35889bd7065f5af88575"
"sha256:6e95524d8a547a91e08f404ae485bbb71962de46967e1b71a0cb89af24e761c5",
"sha256:79ee589a3caca649a9bfd2a8de4709837400dfa00b6cc81962a1e6a1815969ae",
"sha256:f8d2bd89d25bc39dabe7d23df520442fa1d8969b82544370e03d88b5a591c392"
],
"version": "==3.7.4.1"
"version": "==3.7.4.2"
},
"urllib3": {
"hashes": [
"sha256:2f3db8b19923a873b3e5256dc9c2dedfa883e33d87c690d9c7913e1f40673cdc",
"sha256:87716c2d2a7121198ebcb7ce7cccf6ce5e9ba539041cfbaeecfb641dc0bf6acc"
"sha256:91056c15fa70756691db97756772bb1eb9678fa585d9184f24534b100dc60f4a",
"sha256:e7983572181f5e1522d9c98453462384ee92a0be7fac5f1413a1e35c56cc0461"
],
"version": "==1.25.8"
"version": "==1.25.10"
},
"wrapt": {
"hashes": [
"sha256:565a021fd19419476b9362b05eeaa094178de64f8361e44468f9e9d7843901e1"
"sha256:b62ffa81fb85f4332a4f609cab4ac40709470da05643a082ec1eb88e6d9b97d7"
],
"version": "==1.11.2"
"version": "==1.12.1"
}
}
}
+3 -1
View File
@@ -49,7 +49,9 @@
directory accordingly,
- allows **fine-grained customization** of filters and where to store
downloaded media.
downloaded media,
- automatically **resumes previously-interrupted** download iterations.
::
+2 -2
View File
@@ -17,7 +17,7 @@ import subprocess
def __main():
with contextlib.suppress(AttributeError, psutil.Error):
if psutil.Process().parent().parent().name() == "explorer.exe":
subprocess.Popen("powershell -NoExit -Command \\\"& {0}\\\"".format(sys.argv[0]))
subprocess.Popen("powershell -NoExit -Command \\\"& '{0}'\\\"".format(sys.argv[0]))
return
main()
@@ -44,7 +44,7 @@ with open('__main__.py', 'w+') as f:
f.writelines(lines)
# install dependencies and invoke PyInstaller
commands = ["pip install pipenv==2018.11.26",
commands = ["pip install pipenv==2020.6.2",
"pipenv sync --dev",
"pipenv run pyinstaller --log-level=DEBUG instaloader.spec"]
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
-78
View File
@@ -1,78 +0,0 @@
@import url(bootstrap-4.1.3.min.css);
a {
color: #008d06; }
a:hover, a.current, a.active {
color: #f48400; }
a.current, a.active {
font-weight: 500; }
.doc-sidebar a:hover, .modal-body a:hover {
text-decoration: none; }
code {
color: #212529; }
.highlight {
border-radius: 0.3em; }
.highlight pre {
padding: 0.7em;
color: #fff; }
.highlight .c1 {
color: #666; }
.highlight .k, .highlight .kn, .highlight .ow {
color: #008d06; }
.highlight .nb, .highlight .ne, .highlight .nf, .highlight .vm {
color: #f48400; }
.highlight .s1, .highlight .s2, .highlight .sa, .highlight .se, .highlight .si, .highlight .mi {
color: #ff7efd; }
.highlight .c1, .highlight .nf, .highlight .sa, .highlight .se, .highlight .si {
font-style: italic; }
.highlight .k, .highlight .kn, .highlight .ow {
font-weight: bold; }
.doc-content {
padding-top: 0.5em;
top: 3.5625em;
position: fixed;
bottom: 0;
overflow-y: auto; }
.doc-sidebar {
position: fixed;
padding-top: 0.5em;
top: 3.5625em;
bottom: 0;
right: 0;
overflow-y: auto; }
.doc-sidebar ul {
list-style-type: none;
padding-left: 1em; }
.doc-sidebar ul.current {
padding-left: 0; }
.doc-sidebar li {
padding-top: 0.2em;
padding-bottom: 0.2em; }
.admonition {
border-radius: 0.3em;
border: 1px solid #ccc;
background-color: #f8f9fa; }
.admonition .admonition-title {
color: #ff7efd; }
.topic {
border-radius: 0.3em;
background-color: #f8f9fa; }
.nav-link {
padding-top: 0;
padding-bottom: 0; }
.btn-success {
background-color: #008d06;
border-color: #008d06; }
.btn-success:hover {
background-color: #f48400;
border-color: #f48400; }
/*# sourceMappingURL=instaloader.css.map */
-22
View File
@@ -1,22 +0,0 @@
$(function () {
$('[data-toggle="tooltip"]').tooltip();
$('.doc-sidebar > ul > li.current').attr("id", "localtoc");
$('#localtoc ul').addClass("nav flex-column");
$('#localtoc ul li').addClass("nav-item");
$('#localtoc ul li a').addClass("nav-link");
$('.doc-content').scrollspy({target: '#localtoc'});
const top_href = '#' + $('.section:first').attr("id");
$('#localtoc > a.current').attr("href", top_href);
$('#navbarToc a').on("click", function () {
const href = $(this).attr("href");
if (href === '#') {
window.location.href = top_href;
} else {
window.location.href = href;
}
$('#navbarToc').modal('hide');
});
});
-124
View File
@@ -1,124 +0,0 @@
@import 'bootstrap-4.1.3.min.css';
$color_instaloader_main: #008d06;
$color_instaloader_accent: #f48400;
$color_instaloader_hyper: #ff7efd;
$color_normal_text: #212529;
$color_light_bg: #f8f9fa;
a {
color: $color_instaloader_main;
&:hover, &.current, &.active {
color: $color_instaloader_accent;
}
&.current, &.active {
font-weight: 500;
}
}
.doc-sidebar, .modal-body {
a:hover {
text-decoration: none
}
}
code {
color: $color_normal_text;
}
.highlight {
border-radius: 0.3em;
pre {
padding: 0.7em;
color: #fff;
}
.c1 {
color: #666;
}
.k, .kn, .ow {
color: $color_instaloader_main
}
.nb, .ne, .nf, .vm {
color: $color_instaloader_accent
}
.s1, .s2, .sa, .se, .si, .mi {
color: $color_instaloader_hyper
}
.c1, .nf, .sa, .se, .si {
font-style: italic;
}
.k, .kn, .ow {
font-weight: bold
}
}
.doc-content {
padding-top: 0.5em;
top: 3.5625em;
position: fixed;
bottom: 0;
overflow-y: auto;
}
.doc-sidebar {
position: fixed;
padding-top: 0.5em;
top: 3.5625em;
bottom: 0;
right: 0;
overflow-y: auto;
ul {
list-style-type: none;
padding-left: 1em;
&.current {
padding-left: 0;
}
}
li {
padding-top: 0.2em;
padding-bottom: 0.2em;
}
}
.admonition {
border-radius: 0.3em;
border: 1px solid #ccc;
background-color: $color_light_bg;
.admonition-title {
color: $color_instaloader_hyper;
}
}
.topic {
border-radius: 0.3em;
background-color: $color_light_bg;
}
.nav-link {
padding-top: 0;
padding-bottom: 0;
}
.btn-success {
background-color: $color_instaloader_main;
border-color: $color_instaloader_main;
&:hover {
background-color: $color_instaloader_accent;
border-color: $color_instaloader_accent;
}
}
File diff suppressed because one or more lines are too long
+50
View File
File diff suppressed because one or more lines are too long
+46 -78
View File
@@ -1,9 +1,6 @@
{% extends "!layout.html" %}
{% set html5_doctype = True %}
{% set script_files = script_files + ['_static/bootstrap-4.1.3.bundle.min.js', '_static/instaloader.js'] %}
{% set script_files = script_files + ['_static/instaloaderdoc.js'] %}
{% block htmltitle %}
{% if pagename == "index" %}
<title>{{ title|striptags|e }}</title>
@@ -11,7 +8,6 @@
<title>{{ title|striptags|e }}{{ titlesuffix }}</title>
{% endif %}
{% endblock %}
{% block extrahead %}
{{ super() }}
<meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
@@ -22,94 +18,66 @@
<link rel="canonical" href="https://instaloader.github.io/{{ pagename }}.html"/>
{% endif %}
{% endblock %}
{% block header %}
<nav class="navbar navbar-expand-sm navbar-light bg-light fixed-top border-bottom">
<nav class="navbar navbar-light navbar-expand bg-light border-bottom">
<a class="navbar-brand" href="{{ pathto(master_doc) }}">
<img src="{{ pathto('_static/' + logo, 1) }}" width="30" height="30" class="d-inline-block align-top" alt="logo">
Instaloader
<span class="ml-3">Instaloader</span>
</a>
<ul class="navbar-nav mr-auto">
<li class="nav-item ml-0 ml-sm-2 ml-md-0">
<a target="_blank" class="nav-link"
<li class="nav-item ml-0 ml-sm-2">
<a target="_blank" class="nav-link" rel="noopener"
href="https://github.com/instaloader/instaloader/releases/tag/v{{ current_release }}"
title="Released on {{ current_release_date }}" data-toggle="tooltip">v<b>{{ current_release }}</b></a>
title="Released on {{ current_release_date }}" data-toggle="tooltip">
v<b>{{ current_release }}</b>
</a>
</li>
</ul>
<button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbarLinks"
aria-controls="navbarLinks" aria-expanded="false" aria-label="Toggle navigation">
<ul class="navbar-nav ml-auto d-none d-sm-flex">
<li class="nav-item">
<a target="_blank" class="nav-link" rel="noopener" href="https://github.com/instaloader/instaloader/issues">
Issues
</a>
</li>
<li class="nav-item">
<a target="_blank" class="nav-link" rel="noopener" href="https://github.com/instaloader/instaloader/releases">
Releases
</a>
</li>
<li class="nav-item">
<a target="_blank" class="nav-link" rel="noopener" href="https://github.com/instaloader/instaloader">
GitHub
</a>
</li>
</ul>
<button class="d-inline-block d-md-none btn btn-outline-primary btn-sm" type="button"
data-toggle="collapse" data-target="#instaloaderdocSidebar" aria-controls="instaloaderdocSidebar"
aria-expanded="false" aria-label="Toggle navigation">
<span class="navbar-toggler-icon"></span>
</button>
<div class="collapse navbar-collapse" id="navbarLinks">
<ul class="navbar-nav ml-auto">
<li class="nav-item">
<a target="_blank" class="nav-link" href="https://github.com/instaloader/instaloader/issues">Issues</a>
</li>
<li class="nav-item">
<a target="_blank" class="nav-link" href="https://github.com/instaloader/instaloader/releases">Releases</a>
</li>
<li class="nav-item">
<a target="_blank" class="nav-link" href="https://github.com/instaloader/instaloader">GitHub</a>
</li>
</ul>
<form class="form-inline" action="search.html" method="get">
<div class="input-group my-2 my-sm-0 ml-2">
<input class="form-control" type="search" placeholder="Search" aria-label="Search" name="q">
<div class="input-group-append">
<button class="btn btn-success btn-small" type="submit">Go</button>
</div>
</div>
</form>
</div>
{% if pagename != "index" %}
<button type="button" class="btn btn-success d-md-none btn-small ml-2" data-toggle="modal"
data-target="#navbarToc">
TOC
</button>
{% endif %}
</nav>
{% if pagename != "index" %}
<div class="modal fade" id="navbarToc" tabindex="-1" role="dialog"
aria-hidden="true" aria-labelledby="navbarTocTitle">
<div class="modal-dialog modal-dialog-centered" role="document">
<div class="modal-content">
<div class="modal-header">
<h5 class="modal-title" id="navbarTocTitle">Contents</h5>
<button type="button" class="close" data-dismiss="modal" aria-label="Close">
<span aria-hidden="true">&times;</span>
</button>
</div>
<div class="modal-body">
{{ toctree(maxdepth=-1) }}
</div>
</div>
</div>
</div>
{% endif %}
{% endblock %}
{% block relbar1 %}{% endblock %}
{% block relbar2 %}{% endblock %}
{% block footer %}{% endblock %}
{% block content %}
<div class="container-fluid row">
<div class="col-12 {% if pagename != "index" %}col-md-9 col-xl-10{% endif %} doc-content">
{% block body %}{% endblock %}
<div class="container-fluid">
<div class="row">
<aside class="instaloaderdoc-sidebar collapse d-md-block col-md-3 col-xl-2 bg-light"
id="instaloaderdocSidebar">
<nav>
<form action="{{ pathto('search') }}" method="get" role="search" class="border-bottom mr-2 pb-2 mb-2 px-1">
<label class="sr-only" for="searchQueryInput">Search</label>
<input type="search" name="q" id="searchQueryInput" class="form-control my-2"
placeholder="Search..." aria-label="Search">
</form>
<h4>Contents</h4>
{{ toctree(maxdepth=-1) }}
</nav>
</aside>
<main class="col-12 col-md-9 col-xl-10 pt-2">
{% block body %}{% endblock %}
</main>
</div>
{% if pagename != "index" %}
<div class="d-none col-md-3 col-xl-2 bg-light doc-sidebar d-md-flex flex-column border-left">
<h3>{{ _('Table of Contents') }}</h3>
{{ toctree(maxdepth=-1) }}
<div class="d-flex justify-content-between small mt-auto mb-2">
<a class="reference internal{% if pagename == "genindex" %} current{% endif %}" href="genindex.html">Index</a>
{% if pagename != "genindex" and pagename != "search" %}
<a class="reference external"
href="https://github.com/instaloader/instaloader/edit/master/docs/{{ pagename }}.rst">Edit this page</a>
{% endif %}
</div>
</div>
{% endif %}
</div>
{% endblock %}
{% endblock %}
+9 -135
View File
@@ -12,9 +12,6 @@ Python Module :mod:`instaloader`
.. highlight:: python
.. contents::
:backlinks: none
Instaloader exposes its internally used methods and structures as a Python
module, making it a **powerful and intuitive Python API for Instagram**,
allowing to further customize obtaining media and metadata.
@@ -94,140 +91,17 @@ metadata of a Profile. :class:`Profile` instances can be created with:
- :attr:`PostComment.owner` attribute for comment in :meth:`Post.get_comments`
Profile of a Post comment.
A reference of the many methods provided by the :mod:`instaloader` module is
provided in the remainder of this document.
For a list of real code examples using the Instaloader module for advanced
tasks, see :ref:`codesnippets`.
``Instaloader`` (Main Class)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
The reference of the many classes provided by the :mod:`instaloader` module is
divided into the following subsections.
.. autoclass:: Instaloader
:no-show-inheritance:
.. toctree::
:maxdepth: 2
Instagram Structures
^^^^^^^^^^^^^^^^^^^^
Posts
"""""
.. autoclass:: Post
:no-show-inheritance:
Additionally, the following trivial structures are defined:
.. autoclass:: PostSidecarNode
:no-show-inheritance:
.. autoclass:: PostComment
:no-show-inheritance:
.. autoclass:: PostCommentAnswer
:no-show-inheritance:
.. autoclass:: PostLocation
:no-show-inheritance:
User Stories
""""""""""""
.. autoclass:: Story
:no-show-inheritance:
.. autoclass:: StoryItem
:no-show-inheritance:
Highlights
""""""""""
.. autoclass:: Highlight
:no-show-inheritance:
:inherited-members:
Bases: :class:`Story`
.. versionadded:: 4.1
Profiles
""""""""
.. autoclass:: Profile
:no-show-inheritance:
Hashtags
""""""""
.. autoclass:: Hashtag
:no-show-inheritance:
.. versionadded:: 4.4
TopSearchResults
""""""""""""""""
.. autoclass:: TopSearchResults
:no-show-inheritance:
.. versionadded:: 4.3
Loading and Saving
""""""""""""""""""
:class:`Post`, :class:`StoryItem`, :class:`Profile` and :class:`Hashtag` can be saved and loaded
to/from JSON files.
.. autofunction:: load_structure_from_file
.. autofunction:: save_structure_to_file
Exceptions
^^^^^^^^^^
.. currentmodule:: instaloader.exceptions
.. autoexception:: InstaloaderException
:no-show-inheritance:
.. autoexception:: ConnectionException
.. currentmodule:: instaloader
.. autoexception:: QueryReturnedBadRequestException
.. autoexception:: QueryReturnedForbiddenException
.. autoexception:: ProfileNotExistsException
.. autoexception:: ProfileHasNoPicsException
.. autoexception:: PrivateProfileNotFollowedException
.. autoexception:: LoginRequiredException
.. autoexception:: TwoFactorAuthRequiredException
.. versionadded:: 4.2
.. autoexception:: InvalidArgumentException
.. autoexception:: BadResponseException
.. autoexception:: BadCredentialsException
.. autoexception:: PostChangedException
.. autoexception:: QueryReturnedNotFoundException
.. versionchanged:: 4.3
QueryReturnedNotFoundException now inherits ConnectionException
to retry on 404 errors.
.. autoexception:: TooManyRequestsException
``InstaloaderContext`` (Low-level functions)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. autoclass:: InstaloaderContext
:no-show-inheritance:
module/instaloader
module/structures
module/nodeiterator
module/instaloadercontext
module/exceptions
+1 -1
View File
@@ -111,7 +111,7 @@ Instaloader supports the following targets:
``profile`` (requires :option:`--login`).
- ``-post``
Replace **post** with the post's shortcode to download single post. Must be preceeded by ``--`` in
Replace **post** with the post's shortcode to download single post. Must be preceded by ``--`` in
the argument list to not be mistaken as an option flag::
instaloader -- -B_K4CykAOtf
+25 -36
View File
@@ -36,7 +36,7 @@ stores all posts along with the pictures's captions there.
Re-Download the given object
- ``+args.txt``
Read targets (and options) from given textfile. See :option:`+args.txt`.
Read targets (and options) from given text file. See :option:`+args.txt`.
What to Download of each Post
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -94,13 +94,6 @@ What to Download of each Post
What to Download of each Profile
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. option:: --profile-pic-only, -P
.. deprecated:: 4.1
Use :option:`--no-posts`.
Only download profile picture.
.. option:: --no-posts
Do not download regular posts.
@@ -135,20 +128,6 @@ What to Download of each Profile
.. versionadded:: 4.3
.. option:: --stories-only
.. deprecated:: 4.1
Use :option:`--stories` :option:`--no-posts`.
Rather than downloading regular posts of each specified profile, only
download stories. Requires :option:`--login`. Does not imply
:option:`--no-profile-pic`.
.. note::
If possible, use ``:stories`` target rather than :option:`--stories-only`
with all your followees. ``:stories`` uses fewer API requests.
Which Posts to Download
^^^^^^^^^^^^^^^^^^^^^^^
@@ -223,6 +202,29 @@ How to Download
``#hashtag`` or the profile name. Defaults to ``{date_utc}_UTC``.
See :ref:`filename-specification` for a list of supported tokens.
.. option:: --resume-prefix prefix
For many targets, Instaloader is capable of resuming a previously-aborted
download loop. To do so, it creates a JSON file within the target directory
when interrupted. This option controls the prefix for filenames that are
used to save the information to resume an interrupted download. The default
prefix is ``iterator``.
Resuming an interrupted download is supported for most, but not all targets.
JSON files with resume information are always compressed, regardless of
:option:`--no-compress-json`.
This feature is turned off entirely with :option:`--no-resume`.
.. versionadded:: 4.5
.. option:: --no-resume
Do not resume a previously-aborted download iteration, and do not save such
information when interrupted.
.. versionadded:: 4.5
.. option:: --user-agent USER_AGENT
User Agent to use for HTTP requests. Per default, Instaloader pretends being
@@ -234,19 +236,6 @@ How to Download
to ``3``. If a connection fails, it can be manually skipped by hitting
:kbd:`Control-c`. Set this to ``0`` to retry infinitely.
.. option:: --commit-mode
Tries to ensure downloaded images avoid corruption in case of unexpected
interruption. If the last picture is corrupted, Instaloader will fix the
picture the next time it is run.
.. versionadded:: 4.2
.. warning::
We discourage from using the "commit mode" due to its bugs when being used
with other command line options (e.g. :issue:`257` with
:option:`--fast-update` and :issue:`483` with :option:`--tagged`).
.. option:: --request-timeout N
Seconds to wait before timing out a connection request.
@@ -266,7 +255,7 @@ Miscellaneous Options
Read arguments from file `args.txt`, a shortcut to provide arguments from
file rather than command-line. This provides a convenient way to hide login
info from CLI, and can also be used to simplify managment of long arguments.
info from CLI, and can also be used to simplify management of long arguments.
.. note::
+1 -1
View File
@@ -94,7 +94,7 @@ Discussed in :issue:`113`.
Top X Posts of User
-------------------
With Instaloader, it is easy to download the few most-liked pictres of a user.
With Instaloader, it is easy to download the few most-liked pictures of a user.
.. literalinclude:: codesnippets/194_top_x_of_user.py
+3 -1
View File
@@ -50,6 +50,8 @@ autodoc_member_order = 'bysource'
intersphinx_mapping = {'python': ('https://docs.python.org/3', None),
'requests': ('https://requests.kennethreitz.org/en/master/', None)}
nitpick_ignore = [('py:class', 'typing.Tuple')]
current_release = subprocess.check_output(["git", "describe", "--abbrev=0"]).decode("ascii")[1:-1]
date_format = "%e %b %Y" if platform.system() != "Windows" else "%d %b %Y"
current_release_date = subprocess.check_output(
@@ -372,6 +374,6 @@ texinfo_documents = [
def setup(app):
typing.TYPE_CHECKING = True
app.add_stylesheet("instaloader.css")
app.add_stylesheet("instaloaderdoc.css")
app.connect('autodoc-process-signature', sphinx_autodoc_typehints.process_signature)
app.connect('autodoc-process-docstring', sphinx_autodoc_typehints.process_docstring)
+2
View File
@@ -40,6 +40,8 @@ See :ref:`install` for more options on how to install Instaloader.
- allows **fine-grained customization** of filters and where to store
downloaded media,
- automatically **resumes previously-interrupted** download iterations,
- is free `open source <https://github.com/instaloader/instaloader>`__
software written in Python.
+49
View File
@@ -0,0 +1,49 @@
Exceptions
^^^^^^^^^^
.. module:: instaloader
:noindex:
.. highlight:: python
.. currentmodule:: instaloader.exceptions
.. autoexception:: InstaloaderException
:no-show-inheritance:
.. autoexception:: ConnectionException
.. currentmodule:: instaloader
.. autoexception:: QueryReturnedBadRequestException
.. autoexception:: QueryReturnedForbiddenException
.. autoexception:: ProfileNotExistsException
.. autoexception:: ProfileHasNoPicsException
.. autoexception:: PrivateProfileNotFollowedException
.. autoexception:: LoginRequiredException
.. autoexception:: TwoFactorAuthRequiredException
.. versionadded:: 4.2
.. autoexception:: InvalidArgumentException
.. autoexception:: BadResponseException
.. autoexception:: BadCredentialsException
.. autoexception:: PostChangedException
.. autoexception:: QueryReturnedNotFoundException
.. versionchanged:: 4.3
QueryReturnedNotFoundException now inherits ConnectionException
to retry on 404 errors.
.. autoexception:: TooManyRequestsException
+10
View File
@@ -0,0 +1,10 @@
``Instaloader`` (Main Class)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. module:: instaloader
:noindex:
.. highlight:: python
.. autoclass:: Instaloader
:no-show-inheritance:
+24
View File
@@ -0,0 +1,24 @@
``InstaloaderContext`` (Low-level functions)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. module:: instaloader
:noindex:
.. highlight:: python
.. contents::
:backlinks: none
``InstaloaderContext``
""""""""""""""""""""""
.. autoclass:: InstaloaderContext
:no-show-inheritance:
``RateController``
""""""""""""""""""
.. autoclass:: RateController
:no-show-inheritance:
.. versionadded:: 4.5
+31
View File
@@ -0,0 +1,31 @@
Resumable Iterations
^^^^^^^^^^^^^^^^^^^^
.. module:: instaloader
:noindex:
.. highlight:: python
.. contents::
:backlinks: none
For many download targets, Instaloader is able to resume a
previously-interrupted iteration. It provides an interruptible
Iterator :class:`NodeIterator` and a context manager
:func:`resumable_iteration`, which we both present here.
.. versionadded:: 4.5
``NodeIterator``
""""""""""""""""
.. autoclass:: NodeIterator
:no-show-inheritance:
.. autoclass:: FrozenNodeIterator
:no-show-inheritance:
``resumable_iteration``
"""""""""""""""""""""""
.. autofunction:: resumable_iteration
+82
View File
@@ -0,0 +1,82 @@
Instagram Structures
^^^^^^^^^^^^^^^^^^^^
.. module:: instaloader
:noindex:
.. highlight:: python
.. contents::
:backlinks: none
Posts
"""""
.. autoclass:: Post
:no-show-inheritance:
Additionally, the following trivial structures are defined:
.. autoclass:: PostSidecarNode
:no-show-inheritance:
.. autoclass:: PostComment
:no-show-inheritance:
.. autoclass:: PostCommentAnswer
:no-show-inheritance:
.. autoclass:: PostLocation
:no-show-inheritance:
User Stories
""""""""""""
.. autoclass:: Story
:no-show-inheritance:
.. autoclass:: StoryItem
:no-show-inheritance:
Highlights
""""""""""
.. autoclass:: Highlight
:no-show-inheritance:
:inherited-members:
Bases: :class:`Story`
.. versionadded:: 4.1
Profiles
""""""""
.. autoclass:: Profile
:no-show-inheritance:
Hashtags
""""""""
.. autoclass:: Hashtag
:no-show-inheritance:
.. versionadded:: 4.4
TopSearchResults
""""""""""""""""
.. autoclass:: TopSearchResults
:no-show-inheritance:
.. versionadded:: 4.3
Loading and Saving
""""""""""""""""""
:class:`Post`, :class:`StoryItem`, :class:`Profile`, :class:`Hashtag` and
:class:`FrozenNodeIterator` can be saved and loaded to/from JSON files.
.. autofunction:: load_structure_from_file
.. autofunction:: save_structure_to_file
+1 -1
View File
@@ -1,2 +1,2 @@
requests
sphinx!=1.7.7
sphinx~=2.3
+3 -3
View File
@@ -28,7 +28,7 @@ happen in normal conditions, consider adjusting the
:option:`--max-connection-attempts` option.
There have been observations that services, that in their nature offer
promiscious IP addresses, such as cloud, VPN and public proxy services, might be
promiscuous IP addresses, such as cloud, VPN and public proxy services, might be
subject to significantly stricter limits for anonymous access. However,
logged-in accesses (see :option:`--login`) do not seem to be affected.
@@ -58,7 +58,7 @@ Nevertheless, in :issue:`92` and :issue:`615` users reported problems with
logging in. We recommend to always keep the sessionfile which Instaloader
creates when using :option:`--login`. If a sessionfile is present,
:option:`--login` does not make make use of the failure-prone login procedure.
Also, sessionfiles usually do not expire and can be copied between different
Also, session files usually do not expire and can be copied between different
computers without any problems.
If you do not have a sessionfile present, you may use the following script
@@ -78,7 +78,7 @@ To use this script,
#. Then, ``instaloader -l USERNAME`` should work fine.
This script also supports specifying a cookiefile path, which may be useful if
This script also supports specifying a cookie file path, which may be useful if
you use multiple Firefox profiles or if your operating system has the directory
structure differently set up. Also, you can specify an alternative sessionfile
path.
+3 -2
View File
@@ -1,7 +1,7 @@
"""Download pictures (or videos) along with their captions and other metadata from Instagram."""
__version__ = '4.4.5'
__version__ = '4.5b1'
try:
@@ -14,6 +14,7 @@ else:
from .exceptions import *
from .instaloader import Instaloader
from .instaloadercontext import InstaloaderContext
from .instaloadercontext import InstaloaderContext, RateController
from .nodeiterator import NodeIterator, FrozenNodeIterator, resumable_iteration
from .structures import (Hashtag, Highlight, Post, PostSidecarNode, PostComment, PostCommentAnswer, PostLocation,
Profile, Story, StoryItem, TopSearchResults, load_structure_from_file, save_structure_to_file)
+14 -8
View File
@@ -351,6 +351,13 @@ def main():
'--dirname-pattern. {profile} is replaced by the profile name,'
'{target} is replaced by the target you specified, i.e. either :feed'
'#hashtag or the profile name. Defaults to \'{date_utc}_UTC\'')
g_how.add_argument('--resume-prefix', metavar='PREFIX',
help='Prefix for filenames that are used to save the information to resume an interrupted '
'download.')
g_how.add_argument('--no-resume', action='store_true',
help='Do not resume a previously-aborted download iteration, and do not save such information '
'when interrupted.')
g_how.add_argument('--use-aged-resume-files', action='store_true', help=SUPPRESS)
g_how.add_argument('--user-agent',
help='User Agent to use for HTTP requests. Defaults to \'{}\'.'.format(default_user_agent()))
g_how.add_argument('-S', '--no-sleep', action='store_true', help=SUPPRESS)
@@ -358,10 +365,7 @@ def main():
help='Maximum number of connection attempts until a request is aborted. Defaults to 3. If a '
'connection fails, it can be manually skipped by hitting CTRL+C. Set this to 0 to retry '
'infinitely.')
g_how.add_argument('--commit-mode', action='store_true',
help='Tries to ensure downloaded images avoid corruption in case of unexpected interruption. '
'If the last picture is corrupted, Instaloader will fix the picture the next time it is run. '
'Requires the JSON metadata to be saved.')
g_how.add_argument('--commit-mode', action='store_true', help=SUPPRESS)
g_how.add_argument('--request-timeout', metavar='N', type=float,
help='seconds to wait before timing out a connection request')
@@ -397,6 +401,10 @@ def main():
raise SystemExit("--no-captions and --post-metadata-txt or --storyitem-metadata-txt given; "
"That contradicts.")
if args.no_resume and args.resume_prefix:
raise SystemExit("--no-resume and --resume-prefix given; That contradicts.")
resume_prefix = (args.resume_prefix if args.resume_prefix else 'iterator') if not args.no_resume else None
if args.no_pictures and args.fast_update:
raise SystemExit('--no-pictures and --fast-update cannot be used together.')
@@ -405,9 +413,6 @@ def main():
download_posts = not (args.no_posts or args.stories_only or args.profile_pic_only)
download_stories = args.stories or args.stories_only
if args.commit_mode and args.no_metadata_json:
raise SystemExit('--commit-mode requires JSON metadata to be saved.')
loader = Instaloader(sleep=not args.no_sleep, quiet=args.quiet, user_agent=args.user_agent,
dirname_pattern=args.dirname_pattern, filename_pattern=args.filename_pattern,
download_pictures=not args.no_pictures,
@@ -419,7 +424,8 @@ def main():
storyitem_metadata_txt_pattern=storyitem_metadata_txt_pattern,
max_connection_attempts=args.max_connection_attempts,
request_timeout=args.request_timeout,
commit_mode=args.commit_mode)
resume_prefix=resume_prefix,
check_resume_bbd=not args.use_aged_resume_files)
_main(loader,
args.profile,
username=args.login.lower() if args.login is not None else None,
+123 -113
View File
@@ -1,6 +1,5 @@
import getpass
import json
import lzma
import os
import platform
import re
@@ -14,15 +13,16 @@ from functools import wraps
from hashlib import md5
from io import BytesIO
from pathlib import Path
from typing import Any, Callable, Iterator, List, Optional, Set, Union
from typing import Any, Callable, ContextManager, IO, Iterator, List, Optional, Set, Union, cast
import requests
import urllib3 # type: ignore
from .exceptions import *
from .instaloadercontext import InstaloaderContext
from .instaloadercontext import InstaloaderContext, RateController
from .nodeiterator import NodeIterator, resumable_iteration
from .structures import (Hashtag, Highlight, JsonExportable, Post, PostLocation, Profile, Story, StoryItem,
save_structure_to_file, load_structure_from_file)
load_structure_from_file, save_structure_to_file)
def get_default_session_filename(username: str) -> str:
@@ -153,8 +153,10 @@ class Instaloader:
txt file.
:param storyitem_metadata_txt_pattern: :option:`--storyitem-metadata-txt`, default is empty (=none)
:param max_connection_attempts: :option:`--max-connection-attempts`
:param commit_mode: :option:`--commit-mode`
:param request_timeout: :option:`--request-timeout`, set per-request timeout (seconds)
:param rate_controller: Generator for a :class:`RateController` to override rate controlling behavior
:param resume_prefix: :option:`--resume-prefix`, or None for :option:`--no-resume`.
:param check_resume_bbd: Whether to check the date of expiry of resume files and reject them if expired.
.. attribute:: context
@@ -178,9 +180,12 @@ class Instaloader:
storyitem_metadata_txt_pattern: str = None,
max_connection_attempts: int = 3,
request_timeout: Optional[float] = None,
commit_mode: bool = False):
rate_controller: Optional[Callable[[InstaloaderContext], RateController]] = None,
resume_prefix: Optional[str] = "iterator",
check_resume_bbd: bool = True):
self.context = InstaloaderContext(sleep, quiet, user_agent, max_connection_attempts, request_timeout)
self.context = InstaloaderContext(sleep, quiet, user_agent, max_connection_attempts,
request_timeout, rate_controller)
# configuration parameters
self.dirname_pattern = dirname_pattern or "{target}"
@@ -196,12 +201,8 @@ class Instaloader:
else post_metadata_txt_pattern
self.storyitem_metadata_txt_pattern = '' if storyitem_metadata_txt_pattern is None \
else storyitem_metadata_txt_pattern
self.commit_mode = commit_mode
if self.commit_mode and not self.save_metadata:
raise InvalidArgumentException("Commit mode requires JSON metadata to be saved.")
# Used to keep state in commit mode
self._committed = None # type: Optional[bool]
self.resume_prefix = resume_prefix
self.check_resume_bbd = check_resume_bbd
@contextmanager
def anonymous_copy(self):
@@ -223,7 +224,8 @@ class Instaloader:
storyitem_metadata_txt_pattern=self.storyitem_metadata_txt_pattern,
max_connection_attempts=self.context.max_connection_attempts,
request_timeout=self.context.request_timeout,
commit_mode=self.commit_mode)
resume_prefix=self.resume_prefix,
check_resume_bbd=self.check_resume_bbd)
yield new_loader
self.context.error_log.extend(new_loader.context.error_log)
new_loader.context.error_log = [] # avoid double-printing of errors
@@ -249,15 +251,9 @@ class Instaloader:
if filename_suffix is not None:
filename += '_' + filename_suffix
filename += '.' + file_extension
# A post is considered "commited" if the json file exists and is not malformed.
if self.commit_mode:
if self._committed and os.path.isfile(filename):
self.context.log(filename + ' exists', end=' ', flush=True)
return False
else:
if os.path.isfile(filename):
self.context.log(filename + ' exists', end=' ', flush=True)
return False
if os.path.isfile(filename):
self.context.log(filename + ' exists', end=' ', flush=True)
return False
self.context.get_and_write_raw(url, filename)
os.utime(filename, (datetime.now().timestamp(), mtime.timestamp()))
return True
@@ -355,7 +351,8 @@ class Instaloader:
except UnicodeEncodeError:
self.context.log('txt', end=' ', flush=True)
with open(filename, 'wb') as text_file:
shutil.copyfileobj(BytesIO(bcaption), text_file)
with BytesIO(bcaption) as bio:
shutil.copyfileobj(cast(IO, bio), text_file)
os.utime(filename, (datetime.now().timestamp(), mtime.timestamp()))
def save_location(self, filename: str, location: PostLocation, mtime: datetime) -> None:
@@ -365,10 +362,29 @@ class Instaloader:
"https://maps.google.com/maps?q={0},{1}&ll={0},{1}\n".format(location.lat,
location.lng))
with open(filename, 'wb') as text_file:
shutil.copyfileobj(BytesIO(location_string.encode()), text_file)
with BytesIO(location_string.encode()) as bio:
shutil.copyfileobj(cast(IO, bio), text_file)
os.utime(filename, (datetime.now().timestamp(), mtime.timestamp()))
self.context.log('geo', end=' ', flush=True)
def format_filename_within_target_path(self,
target: Union[str, Path],
owner_profile: Optional[Profile],
identifier: str,
name_suffix: str,
extension: str):
"""Returns a filename within the target path.
.. versionadded:: 4.5"""
if ((format_string_contains_key(self.dirname_pattern, 'profile') or
format_string_contains_key(self.dirname_pattern, 'target'))):
profile_str = owner_profile.username.lower() if owner_profile is not None else target
return os.path.join(self.dirname_pattern.format(profile=profile_str, target=target),
'{0}_{1}.{2}'.format(identifier, name_suffix, extension))
else:
return os.path.join(self.dirname_pattern.format(),
'{0}_{1}_{2}.{3}'.format(target, identifier, name_suffix, extension))
@_retry_on_connection_error
def download_title_pic(self, url: str, target: Union[str, Path], name_suffix: str, owner_profile: Optional[Profile],
_attempt: int = 1) -> None:
@@ -389,16 +405,7 @@ class Instaloader:
else:
pic_bytes = http_response.content
pic_identifier = md5(pic_bytes).hexdigest()[:16]
pic_extension = 'jpg'
if ((format_string_contains_key(self.dirname_pattern, 'profile') or
format_string_contains_key(self.dirname_pattern, 'target'))):
profile_str = owner_profile.username.lower() if owner_profile is not None else target
filename = os.path.join(self.dirname_pattern.format(profile=profile_str,
target=target),
'{0}_{1}.{2}'.format(pic_identifier, name_suffix, pic_extension))
else:
filename = os.path.join(self.dirname_pattern.format(),
'{0}_{1}_{2}.{3}'.format(target, pic_identifier, name_suffix, pic_extension))
filename = self.format_filename_within_target_path(target, owner_profile, pic_identifier, name_suffix, 'jpg')
content_length = http_response.headers.get('Content-Length', None)
if os.path.isfile(filename) and (not self.context.is_logged_in or
(content_length is not None and
@@ -506,7 +513,6 @@ class Instaloader:
# Download the image(s) / video thumbnail and videos within sidecars if desired
downloaded = True
self._committed = self.check_if_committed(filename)
if self.download_pictures:
if post.typename == 'GraphSidecar':
edge_number = 1
@@ -719,59 +725,78 @@ class Instaloader:
fast_update: bool = False,
post_filter: Optional[Callable[[Post], bool]] = None,
max_count: Optional[int] = None,
total_count: Optional[int] = None) -> None:
total_count: Optional[int] = None,
owner_profile: Optional[Profile] = None) -> None:
"""
Download the Posts returned by given Post Iterator.
..versionadded:: 4.4
.. versionadded:: 4.4
.. versionchanged:: 4.5
Transparently resume an aborted operation if `posts` is a :class:`NodeIterator`.
:param posts: Post Iterator to loop through.
:param target: Target name
:param fast_update: :option:`--fast-update`
:param post_filter: :option:`--post-filter`
:param max_count: Maximum count of Posts to download (:option:`--count`)
:param total_count: Total number of posts returned by given iterator
:param target: Target name.
:param fast_update: :option:`--fast-update`.
:param post_filter: :option:`--post-filter`.
:param max_count: Maximum count of Posts to download (:option:`--count`).
:param total_count: Total number of posts returned by given iterator.
:param owner_profile: Associated profile, if any.
"""
for number, post in enumerate(posts):
if max_count is not None and number >= max_count:
break
if total_count is not None:
self.context.log("[{0:{w}d}/{1:{w}d}] ".format(number + 1, total_count,
w=len(str(total_count))),
end="", flush=True)
else:
if max_count is not None:
self.context.log("[{0:{w}d}/{1:{w}d}] ".format(number + 1, max_count,
w=len(str(max_count))),
displayed_count = (max_count if total_count is None or max_count is not None and max_count < total_count
else total_count)
sanitized_target = target
if isinstance(target, str):
sanitized_target = _PostPathFormatter.sanitize_path(target)
with resumable_iteration(
context=self.context,
iterator=posts,
load=load_structure_from_file,
save=save_structure_to_file,
format_path=lambda magic: self.format_filename_within_target_path(
sanitized_target, owner_profile, self.resume_prefix or '', magic, 'json.xz'
),
check_bbd=self.check_resume_bbd,
enabled=self.resume_prefix is not None
) as resume_info:
is_resuming, start_index = resume_info
for number, post in enumerate(posts):
if max_count is not None and number + start_index >= max_count:
break
if displayed_count is not None:
self.context.log("[{0:{w}d}/{1:{w}d}] ".format(number + start_index + 1, displayed_count,
w=len(str(displayed_count))),
end="", flush=True)
else:
self.context.log("[{:3d}] ".format(number + 1), end="", flush=True)
if post_filter is not None:
try:
if not post_filter(post):
self.context.log("{} skipped".format(post))
continue
except (InstaloaderException, KeyError, TypeError) as err:
self.context.error("{} skipped. Filter evaluation failed: {}".format(post, err))
continue
with self.context.error_catcher("Download {} of {}".format(post, target)):
# The PostChangedException gets raised if the Post's id/shortcode changed while obtaining
# additional metadata. This is most likely the case if a HTTP redirect takes place while
# resolving the shortcode URL.
# The `post_changed` variable keeps the fast-update functionality alive: A Post which is
# obained after a redirect has probably already been downloaded as a previous Post of the
# same Profile.
# Observed in issue #225: https://github.com/instaloader/instaloader/issues/225
post_changed = False
while True:
self.context.log("[{:3d}] ".format(number + start_index + 1), end="", flush=True)
if post_filter is not None:
try:
downloaded = self.download_post(post, target=target)
break
except PostChangedException:
post_changed = True
if not post_filter(post):
self.context.log("{} skipped".format(post))
continue
except (InstaloaderException, KeyError, TypeError) as err:
self.context.error("{} skipped. Filter evaluation failed: {}".format(post, err))
continue
if fast_update and not downloaded and not post_changed:
break
with self.context.error_catcher("Download {} of {}".format(post, target)):
# The PostChangedException gets raised if the Post's id/shortcode changed while obtaining
# additional metadata. This is most likely the case if a HTTP redirect takes place while
# resolving the shortcode URL.
# The `post_changed` variable keeps the fast-update functionality alive: A Post which is
# obained after a redirect has probably already been downloaded as a previous Post of the
# same Profile.
# Observed in issue #225: https://github.com/instaloader/instaloader/issues/225
post_changed = False
while True:
try:
downloaded = self.download_post(post, target=target)
break
except PostChangedException:
post_changed = True
continue
if fast_update and not downloaded and not post_changed:
# disengage fast_update for first post when resuming
if not is_resuming or number > 0:
break
@_requires_login
def get_feed_posts(self) -> Iterator[Post]:
@@ -831,8 +856,10 @@ class Instaloader:
"""
self.context.log("Retrieving saved posts...")
assert self.context.username is not None # safe due to @_requires_login; required by typechecker
self.posts_download_loop(Profile.from_username(self.context, self.context.username).get_saved_posts(), ":saved",
fast_update, post_filter, max_count=max_count)
node_iterator = Profile.from_username(self.context, self.context.username).get_saved_posts()
self.posts_download_loop(node_iterator, ":saved",
fast_update, post_filter,
max_count=max_count, total_count=node_iterator.count)
@_requires_login
def get_location_posts(self, location: str) -> Iterator[Post]:
@@ -887,18 +914,20 @@ class Instaloader:
max_count=max_count)
@_requires_login
def get_explore_posts(self) -> Iterator[Post]:
def get_explore_posts(self) -> NodeIterator[Post]:
"""Get Posts which are worthy of exploring suggested by Instagram.
:return: Iterator over Posts of the user's suggested posts.
:rtype: NodeIterator[Post]
:raises LoginRequiredException: If called without being logged in.
"""
data = self.context.get_json('explore/', {})
yield from (Post(self.context, node)
for node in self.context.graphql_node_list("df0dcc250c2b18d9fd27c5581ef33c7c",
{}, 'https://www.instagram.com/explore/',
lambda d: d['data']['user']['edge_web_discover_media'],
data.get('rhx_gis')))
return NodeIterator(
self.context,
'df0dcc250c2b18d9fd27c5581ef33c7c',
lambda d: d['data']['user']['edge_web_discover_media'],
lambda n: Post(self.context, n),
query_referer='https://www.instagram.com/explore/',
)
def get_hashtag_posts(self, hashtag: str) -> Iterator[Post]:
"""Get Posts associated with a #hashtag.
@@ -969,7 +998,7 @@ class Instaloader:
.. versionadded:: 4.3"""
self.context.log("Retrieving IGTV videos for profile {}.".format(profile.username))
self.posts_download_loop(profile.get_igtv_posts(), profile.username, fast_update, post_filter,
total_count=profile.igtvcount)
total_count=profile.igtvcount, owner_profile=profile)
def _get_id_filename(self, profile_name: str) -> str:
if ((format_string_contains_key(self.dirname_pattern, 'profile') or
@@ -1079,11 +1108,11 @@ class Instaloader:
def _error_raiser(_str):
yield
# error_handler type is Callable[[Optional[str]], ContextManager[None]] (not supported with Python 3.5)
error_handler = _error_raiser if raise_errors else self.context.error_catcher
error_handler = cast(Callable[[Optional[str]], ContextManager[None]],
_error_raiser if raise_errors else self.context.error_catcher)
for profile in profiles:
with error_handler(profile.username): # type: ignore
with error_handler(profile.username):
profile_name = profile.username
# Download profile picture
@@ -1124,7 +1153,7 @@ class Instaloader:
if posts:
self.context.log("Retrieving posts from profile {}.".format(profile_name))
self.posts_download_loop(profile.get_posts(), profile_name, fast_update, post_filter,
total_count=profile.mediacount)
total_count=profile.mediacount, owner_profile=profile)
if stories and profiles:
with self.context.error_catcher("Download stories"):
@@ -1204,26 +1233,7 @@ class Instaloader:
# Iterate over pictures and download them
self.context.log("Retrieving posts from profile {}.".format(profile_name))
self.posts_download_loop(profile.get_posts(), profile_name, fast_update, post_filter,
total_count=profile.mediacount)
def check_if_committed(self, filename: str) -> bool:
"""Checks to see if the current post has been committed.
A post is considered committed if its json metadata file exists and is not malformed.
.. versionadded:: 4.2
"""
if os.path.isfile(filename + '.json.xz'):
filename += '.json.xz'
elif os.path.isfile(filename + '.json'):
filename += '.json'
else:
return False
try:
load_structure_from_file(self.context, filename)
return True
except (FileNotFoundError, lzma.LZMAError, json.decoder.JSONDecodeError):
return False
total_count=profile.mediacount, owner_profile=profile)
def interactive_login(self, username: str) -> None:
"""Logs in and internally stores session, asking user for password interactively.
+117 -87
View File
@@ -1,5 +1,6 @@
import hashlib
import json
import os
import pickle
import random
import re
@@ -23,7 +24,7 @@ def copy_session(session: requests.Session, request_timeout: Optional[float] = N
"""Duplicates a requests.Session."""
new = requests.Session()
new.cookies = requests.utils.cookiejar_from_dict(requests.utils.dict_from_cookiejar(session.cookies))
new.headers = session.headers.copy() # type: ignore
new.headers = session.headers.copy()
if request_timeout is not None:
# Override default timeout behavior.
# Need to silence mypy bug for this. See: https://github.com/python/mypy/issues/2427
@@ -52,7 +53,8 @@ class InstaloaderContext:
"""
def __init__(self, sleep: bool = True, quiet: bool = False, user_agent: Optional[str] = None,
max_connection_attempts: int = 3, request_timeout: Optional[float] = None):
max_connection_attempts: int = 3, request_timeout: Optional[float] = None,
rate_controller: Optional[Callable[["InstaloaderContext"], "RateController"]] = None):
self.user_agent = user_agent if user_agent is not None else default_user_agent()
self.request_timeout = request_timeout
@@ -68,9 +70,7 @@ class InstaloaderContext:
# error log, filled with error() and printed at the end of Instaloader.main()
self.error_log = [] # type: List[str]
# For the adaption of sleep intervals (rate control)
self._graphql_query_timestamps = dict() # type: Dict[str, List[float]]
self._graphql_earliest_next_request_time = 0.0
self._rate_controller = rate_controller(self) if rate_controller is not None else RateController(self)
# Can be set to True for testing, disables supression of InstaloaderContext._error_catcher
self.raise_all_errors = False
@@ -294,77 +294,6 @@ class InstaloaderContext:
if self.sleep:
time.sleep(min(random.expovariate(0.7), 5.0))
def _dump_query_timestamps(self, current_time: float):
"""Output the number of GraphQL queries grouped by their query_hash within the last time."""
windows = [10, 11, 15, 20, 30, 60]
print("GraphQL requests:", file=sys.stderr)
for query_hash, times in self._graphql_query_timestamps.items():
print(" {}".format(query_hash), file=sys.stderr)
for window in windows:
reqs_in_sliding_window = sum(t > current_time - window * 60 for t in times)
print(" last {} minutes: {} requests".format(window, reqs_in_sliding_window), file=sys.stderr)
def _graphql_request_count_per_sliding_window(self, query_hash: str) -> int:
"""Return how many GraphQL requests can be done within the sliding window."""
if self.is_logged_in:
max_reqs = {'1cb6ec562846122743b61e492c85999f': 20,
'33ba35852cb50da46f5b5e889df7d159': 20,
'iphone': 100,
'other': 100}
else:
max_reqs = {'1cb6ec562846122743b61e492c85999f': 200,
'33ba35852cb50da46f5b5e889df7d159': 200,
'other': 200}
return max_reqs.get(query_hash) or min(max_reqs.values())
def _graphql_query_waittime(self, query_hash: str, current_time: float, untracked_queries: bool = False) -> float:
"""Calculate time needed to wait before GraphQL query can be executed."""
sliding_window = 660
if query_hash not in self._graphql_query_timestamps:
self._graphql_query_timestamps[query_hash] = []
self._graphql_query_timestamps[query_hash] = list(filter(lambda t: t > current_time - 60 * 60,
self._graphql_query_timestamps[query_hash]))
reqs_in_sliding_window = list(filter(lambda t: t > current_time - sliding_window,
self._graphql_query_timestamps[query_hash]))
count_per_sliding_window = self._graphql_request_count_per_sliding_window(query_hash)
if len(reqs_in_sliding_window) < count_per_sliding_window and not untracked_queries:
return max(0, self._graphql_earliest_next_request_time - current_time)
next_request_time = min(reqs_in_sliding_window) + sliding_window + 6
if untracked_queries:
self._graphql_earliest_next_request_time = next_request_time
return round(max(next_request_time, self._graphql_earliest_next_request_time) - current_time)
def _ratecontrol_graphql_query(self, query_hash: str, untracked_queries: bool = False):
"""Called before a GraphQL query is made in order to stay within Instagram's rate limits.
:param query_hash: The query_hash parameter of the query.
:param untracked_queries: True, if 429 has been returned to apply 429 logic.
"""
if not untracked_queries:
waittime = self._graphql_query_waittime(query_hash, time.monotonic(), untracked_queries)
assert waittime >= 0
if waittime > 10:
self.log('\nToo many queries in the last time. Need to wait {} seconds, until {:%H:%M}.'
.format(waittime, datetime.now() + timedelta(seconds=waittime)))
time.sleep(waittime)
if query_hash not in self._graphql_query_timestamps:
self._graphql_query_timestamps[query_hash] = [time.monotonic()]
else:
self._graphql_query_timestamps[query_hash].append(time.monotonic())
else:
text_for_429 = ("HTTP error code 429 was returned because too many queries occurred in the last time. "
"Please do not use Instagram in your browser or run multiple instances of Instaloader "
"in parallel.")
print(textwrap.fill(text_for_429), file=sys.stderr)
current_time = time.monotonic()
waittime = self._graphql_query_waittime(query_hash, current_time, untracked_queries)
assert waittime >= 0
if waittime > 10:
self.log('The request will be retried in {} seconds, at {:%H:%M}.'
.format(waittime, datetime.now() + timedelta(seconds=waittime)))
self._dump_query_timestamps(current_time)
time.sleep(waittime)
def get_json(self, path: str, params: Dict[str, Any], host: str = 'www.instagram.com',
session: Optional[requests.Session] = None, _attempt=1) -> Dict[str, Any]:
"""JSON request to Instagram.
@@ -385,11 +314,11 @@ class InstaloaderContext:
try:
self.do_sleep()
if is_graphql_query:
self._ratecontrol_graphql_query(params['query_hash'])
self._rate_controller.wait_before_query(params['query_hash'])
if is_iphone_query:
self._ratecontrol_graphql_query('iphone')
self._rate_controller.wait_before_query('iphone')
if is_other_query:
self._ratecontrol_graphql_query('other')
self._rate_controller.wait_before_query('other')
resp = sess.get('https://{0}/{1}'.format(host, path), params=params, allow_redirects=False)
while resp.is_redirect:
redirect_url = resp.headers['location']
@@ -445,12 +374,13 @@ class InstaloaderContext:
raise ConnectionException(error_string) from err
self.error(error_string + " [retrying; skip with ^C]", repeat_at_end=False)
try:
if is_graphql_query and isinstance(err, TooManyRequestsException):
self._ratecontrol_graphql_query(params['query_hash'], untracked_queries=True)
if is_iphone_query and isinstance(err, TooManyRequestsException):
self._ratecontrol_graphql_query('iphone', untracked_queries=True)
if is_other_query and isinstance(err, TooManyRequestsException):
self._ratecontrol_graphql_query('other', untracked_queries=True)
if isinstance(err, TooManyRequestsException):
if is_graphql_query:
self._rate_controller.handle_429(params['query_hash'])
if is_iphone_query:
self._rate_controller.handle_429('iphone')
if is_other_query:
self._rate_controller.handle_429('other')
return self.get_json(path=path, params=params, host=host, session=sess, _attempt=_attempt + 1)
except KeyboardInterrupt:
self.error("[skipped by user]", repeat_at_end=False)
@@ -498,7 +428,12 @@ class InstaloaderContext:
edge_extractor: Callable[[Dict[str, Any]], Dict[str, Any]],
rhx_gis: Optional[str] = None,
first_data: Optional[Dict[str, Any]] = None) -> Iterator[Dict[str, Any]]:
"""Retrieve a list of GraphQL nodes."""
"""
Retrieve a list of GraphQL nodes.
.. deprecated:: 4.5
Use :class:`NodeIterator` instead, which provides more functionality.
"""
def _query():
query_variables['first'] = self._graphql_page_length
@@ -547,11 +482,12 @@ class InstaloaderContext:
.. versionadded:: 4.2.1"""
self.log(filename, end=' ', flush=True)
with open(filename, 'wb') as file:
with open(filename + '.temp', 'wb') as file:
if isinstance(resp, requests.Response):
shutil.copyfileobj(resp.raw, file)
else:
file.write(resp)
os.rename(filename + '.temp', filename)
def get_raw(self, url: str, _attempt=1) -> requests.Response:
"""Downloads a file anonymously.
@@ -593,3 +529,97 @@ class InstaloaderContext:
if self._root_rhx_gis is None:
self._root_rhx_gis = self.get_json('', {}).get('rhx_gis', '')
return self._root_rhx_gis or None
class RateController:
"""
Class providing request tracking and rate controlling to stay within rate limits.
It can be overridden to change Instaloader's behavior regarding rate limits, for example to raise a custom
exception when the rate limit is hit::
import instaloader
class MyRateController(instaloader.RateController):
def sleep(self, secs):
raise MyCustomException()
L = instaloader.Instaloader(rate_controller=lambda ctx: MyRateController(ctx))
"""
def __init__(self, context: InstaloaderContext):
self._context = context
self._graphql_query_timestamps = dict() # type: Dict[str, List[float]]
self._graphql_earliest_next_request_time = 0.0
def sleep(self, secs: float):
"""Wait given number of seconds."""
# Not static, to allow for the behavior of this method to depend on context-inherent properties, such as
# whether we are logged in.
# pylint:disable=no-self-use
time.sleep(secs)
def _dump_query_timestamps(self, current_time: float):
windows = [10, 11, 15, 20, 30, 60]
print("GraphQL requests:", file=sys.stderr)
for query_hash, times in self._graphql_query_timestamps.items():
print(" {}".format(query_hash), file=sys.stderr)
for window in windows:
reqs_in_sliding_window = sum(t > current_time - window * 60 for t in times)
print(" last {} minutes: {} requests".format(window, reqs_in_sliding_window), file=sys.stderr)
def count_per_sliding_window(self, query_type: str) -> int:
"""Return how many GraphQL requests can be done within the sliding window."""
# Not static, to allow for the count_per_sliding_window to depend on context-inherent properties, such as
# whether we are logged in.
# pylint:disable=no-self-use,unused-argument
return 200
def query_waittime(self, query_type: str, current_time: float, untracked_queries: bool = False) -> float:
"""Calculate time needed to wait before GraphQL query can be executed."""
sliding_window = 660
if query_type not in self._graphql_query_timestamps:
self._graphql_query_timestamps[query_type] = []
self._graphql_query_timestamps[query_type] = list(filter(lambda t: t > current_time - 60 * 60,
self._graphql_query_timestamps[query_type]))
reqs_in_sliding_window = list(filter(lambda t: t > current_time - sliding_window,
self._graphql_query_timestamps[query_type]))
count_per_sliding_window = self.count_per_sliding_window(query_type)
if len(reqs_in_sliding_window) < count_per_sliding_window and not untracked_queries:
return max(0.0, self._graphql_earliest_next_request_time - current_time)
next_request_time = min(reqs_in_sliding_window) + sliding_window + 6
if untracked_queries:
self._graphql_earliest_next_request_time = next_request_time
return max(next_request_time, self._graphql_earliest_next_request_time) - current_time
def wait_before_query(self, query_type: str) -> None:
"""This method is called before a query to Instagram. It calls :meth:`RateController.sleep` to wait
until the request can be made."""
waittime = self.query_waittime(query_type, time.monotonic(), False)
assert waittime >= 0
if waittime > 15:
self._context.log("\nToo many queries in the last time. Need to wait {} seconds, until {:%H:%M}."
.format(round(waittime), datetime.now() + timedelta(seconds=waittime)))
if waittime > 0:
self.sleep(waittime)
if query_type not in self._graphql_query_timestamps:
self._graphql_query_timestamps[query_type] = [time.monotonic()]
else:
self._graphql_query_timestamps[query_type].append(time.monotonic())
def handle_429(self, query_type: str) -> None:
"""This method is called to handle a 429 Too Many Requests response. It calls :meth:`RateController.sleep` to
wait until we can repeat the same request."""
text_for_429 = ("HTTP error code 429 was returned because too many queries occurred in the last time. "
"Please do not use Instagram in your browser or run multiple instances of Instaloader "
"in parallel.")
print(textwrap.fill(text_for_429), file=sys.stderr)
current_time = time.monotonic()
waittime = self.query_waittime(query_type, current_time, True)
assert waittime >= 0
if waittime > 15:
self._context.log("The request will be retried in {} seconds, at {:%H:%M}."
.format(round(waittime), datetime.now() + timedelta(seconds=waittime)))
self._dump_query_timestamps(current_time)
if waittime > 0:
self.sleep(waittime)
+269
View File
@@ -0,0 +1,269 @@
import base64
import hashlib
import json
import os
from contextlib import contextmanager
from datetime import datetime, timedelta
from lzma import LZMAError
from typing import Any, Callable, Dict, Iterator, NamedTuple, Optional, Tuple, TypeVar
from .exceptions import InvalidArgumentException, QueryReturnedBadRequestException
from .instaloadercontext import InstaloaderContext
FrozenNodeIterator = NamedTuple('FrozenNodeIterator',
[('query_hash', str),
('query_variables', Dict),
('query_referer', Optional[str]),
('context_username', Optional[str]),
('total_index', int),
('best_before', Optional[float]),
('remaining_data', Optional[Dict])])
FrozenNodeIterator.__doc__ = \
"""A serializable representation of a :class:`NodeIterator` instance, saving its iteration state."""
FrozenNodeIterator.query_hash.__doc__ = """The GraphQL ``query_hash`` parameter."""
FrozenNodeIterator.query_variables.__doc__ = """The GraphQL ``query_variables`` parameter."""
FrozenNodeIterator.query_referer.__doc__ = """The HTTP referer used for the GraphQL query."""
FrozenNodeIterator.context_username.__doc__ = """The username who created the iterator, or ``None``."""
FrozenNodeIterator.total_index.__doc__ = """Number of items that have already been returned."""
FrozenNodeIterator.best_before.__doc__ = """Date when parts of the stored nodes might have expired."""
FrozenNodeIterator.remaining_data.__doc__ = \
"""The already-retrieved, yet-unprocessed ``edges`` and the ``page_info`` at time of freezing."""
T = TypeVar('T')
class NodeIterator(Iterator[T]):
"""
Iterate the nodes within edges in a GraphQL pagination. Instances of this class are returned by many (but not all)
of Instaloader's :class:`Post`-returning functions (such as :meth:`Profile.get_posts` etc.).
What makes this iterator special is its ability to freeze/store its current state, e.g. to interrupt an iteration,
and later thaw/resume from where it left off.
You can freeze a NodeIterator with :meth:`NodeIterator.freeze`::
post_iterator = profile.get_posts()
try:
for post in post_iterator:
do_something_with(post)
except KeyboardInterrupt:
save("resume_information.json", post_iterator.freeze())
and later reuse it with :meth:`NodeIterator.thaw` on an equally-constructed NodeIterator::
post_iterator = profile.get_posts()
post_iterator.thaw(load("resume_information.json"))
A :class:`FrozenNodeIterator` can only be thawn with a matching NodeIterator, i.e. a NodeIterator instance that has
been constructed with the same parameters as the instance that is represented by the :class:`FrozenNodeIterator` in
question. This is to ensure that an iteration cannot be resumed in a wrong, unmatching loop. As a quick way to
distinguish iterators that are saved e.g. in files, there is the :attr:`NodeIterator.magic` string: Two
NodeIterators are matching if and only if they have the same magic.
See also :func:`resumable_iteration` for a high-level context manager that handles a resumable iteration.
"""
_graphql_page_length = 50
_shelf_life = timedelta(days=29)
def __init__(self,
context: InstaloaderContext,
query_hash: str,
edge_extractor: Callable[[Dict[str, Any]], Dict[str, Any]],
node_wrapper: Callable[[Dict], T],
query_variables: Optional[Dict[str, Any]] = None,
query_referer: Optional[str] = None,
first_data: Optional[Dict[str, Any]] = None):
self._context = context
self._query_hash = query_hash
self._edge_extractor = edge_extractor
self._node_wrapper = node_wrapper
self._query_variables = query_variables if query_variables is not None else {}
self._query_referer = query_referer
self._data = first_data
self._page_index = 0
self._total_index = 0
self._best_before = (None if first_data is None else
datetime.now() + NodeIterator._shelf_life)
def _query(self, after: Optional[str] = None) -> Dict:
pagination_variables = {'first': NodeIterator._graphql_page_length} # type: Dict[str, Any]
if after is not None:
pagination_variables['after'] = after
try:
data = self._edge_extractor(
self._context.graphql_query(
self._query_hash, {**self._query_variables, **pagination_variables}, self._query_referer
)
)
self._best_before = datetime.now() + NodeIterator._shelf_life
return data
except QueryReturnedBadRequestException:
new_page_length = int(NodeIterator._graphql_page_length / 2)
if new_page_length >= 12:
NodeIterator._graphql_page_length = new_page_length
self._context.error("HTTP Error 400 (Bad Request) on GraphQL Query. Retrying with shorter page length.",
repeat_at_end=False)
return self._query(after)
else:
raise
def __iter__(self):
return self
def __next__(self) -> T:
if self._data is None:
self._data = self._query()
if self._page_index < len(self._data['edges']):
node = self._data['edges'][self._page_index]['node']
page_index, total_index = self._page_index, self._total_index
try:
self._page_index += 1
self._total_index += 1
except KeyboardInterrupt:
self._page_index, self._total_index = page_index, total_index
raise
return self._node_wrapper(node)
if self._data['page_info']['has_next_page']:
query_response = self._query(self._data['page_info']['end_cursor'])
page_index, data = self._page_index, self._data
try:
self._page_index = 0
self._data = query_response
except KeyboardInterrupt:
self._page_index, self._data = page_index, data
raise
return self.__next__()
raise StopIteration()
@property
def count(self) -> Optional[int]:
"""The ``count`` as returned by Instagram. This is not always the total count this iterator will yield."""
return self._data.get('count') if self._data is not None else None
@property
def total_index(self) -> int:
"""Number of items that have already been returned."""
return self._total_index
@property
def magic(self) -> str:
"""Magic string for easily identifying a matching iterator file for resuming (hash of some parameters)."""
if 'blake2b' not in hashlib.algorithms_available:
magic_hash = hashlib.new('sha224')
else:
# Use blake2b when possible, i.e. on Python >= 3.6.
magic_hash = hashlib.blake2b(digest_size=6) # type:ignore # pylint: disable=no-member
magic_hash.update(json.dumps(
[self._query_hash, self._query_variables, self._query_referer, self._context.username]
).encode())
return base64.urlsafe_b64encode(magic_hash.digest()).decode()
def freeze(self) -> FrozenNodeIterator:
"""Freeze the iterator for later resuming."""
remaining_data = None
if self._data is not None:
remaining_data = {**self._data,
'edges': (self._data['edges'][(max(self._page_index - 1, 0)):])}
return FrozenNodeIterator(
query_hash=self._query_hash,
query_variables=self._query_variables,
query_referer=self._query_referer,
context_username=self._context.username,
total_index=max(self.total_index - 1, 0),
best_before=self._best_before.timestamp() if self._best_before else None,
remaining_data=remaining_data,
)
def thaw(self, frozen: FrozenNodeIterator) -> None:
"""
Use this iterator for resuming from earlier iteration.
:raises InvalidArgumentException:
If
- the iterator on which this method is called has already been used, or
- the given :class:`FrozenNodeIterator` does not match, i.e. belongs to a different iteration.
"""
if self._total_index or self._page_index:
raise InvalidArgumentException("thaw() called on already-used iterator.")
if (self._query_hash != frozen.query_hash or
self._query_variables != frozen.query_variables or
self._query_referer != frozen.query_referer or
self._context.username != frozen.context_username):
raise InvalidArgumentException("Mismatching resume information.")
self._total_index = frozen.total_index
self._best_before = datetime.fromtimestamp(frozen.best_before) if frozen.best_before else None
self._data = frozen.remaining_data
@contextmanager
def resumable_iteration(context: InstaloaderContext,
iterator: Iterator,
load: Callable[[InstaloaderContext, str], Any],
save: Callable[[FrozenNodeIterator, str], None],
format_path: Callable[[str], str],
check_bbd: bool = True,
enabled: bool = True) -> Iterator[Tuple[bool, int]]:
"""
High-level context manager to handle a resumable iteration that can be interrupted with a KeyboardInterrupt.
It can be used as follows to automatically load a previously-saved state into the iterator, save the iterator's
state when interrupted, and delete the resume file upon completion::
post_iterator = profile.get_posts()
with resumable_iteration(
context=L.context,
iterator=post_iterator,
load=lambda _, path: FrozenNodeIterator(**json.load(open(path))),
save=lambda fni, path: json.dump(fni._asdict(), open(path, 'w')),
format_path=lambda magic: "resume_info_{}.json".format(magic)
) as resume_info:
is_resuming, start_index = resume_info
for post in post_iterator:
do_something_with(post)
It yields a tuple (is_resuming, start_index).
When the passed iterator is not a :class:`NodeIterator`, it behaves as if ``resumable_iteration`` was not used,
just executing the inner body.
:param context: The :class:`InstaloaderContext`.
:param iterator: The fresh :class:`NodeIterator`.
:param load: Loads a FrozenNodeIterator from given path. The object is ignored if it has a different type.
:param save: Saves the given FrozenNodeIterator to the given path.
:param format_path: Returns the path to the resume file for the given magic.
:param check_bbd: Whether to check the best before date and reject an expired FrozenNodeIterator.
:param enabled: Set to False to disable all functionality and simply execute the inner body.
"""
if not enabled or not isinstance(iterator, NodeIterator):
yield False, 0
return
is_resuming = False
start_index = 0
resume_file_path = format_path(iterator.magic)
resume_file_exists = os.path.isfile(resume_file_path)
if resume_file_exists:
try:
fni = load(context, resume_file_path)
if not isinstance(fni, FrozenNodeIterator):
raise InvalidArgumentException("Invalid type.")
if check_bbd and fni.best_before and datetime.fromtimestamp(fni.best_before) < datetime.now():
raise InvalidArgumentException("\"Best before\" date exceeded.")
iterator.thaw(fni)
is_resuming = True
start_index = iterator.total_index
context.log("Resuming from {}.".format(resume_file_path))
except (InvalidArgumentException, LZMAError, json.decoder.JSONDecodeError) as exc:
context.error("Warning: Not resuming from {}: {}".format(resume_file_path, exc))
try:
yield is_resuming, start_index
except KeyboardInterrupt:
os.makedirs(os.path.dirname(resume_file_path), exist_ok=True)
save(iterator.freeze(), resume_file_path)
context.log("\nSaved resume information to {}.".format(resume_file_path))
raise
if resume_file_exists:
os.unlink(resume_file_path)
context.log("Iteration complete, deleted resume information file {}.".format(resume_file_path))
+101 -60
View File
@@ -9,7 +9,7 @@ from typing import Any, Dict, Iterator, List, Optional, Union
from . import __version__
from .exceptions import *
from .instaloadercontext import InstaloaderContext
from .nodeiterator import FrozenNodeIterator, NodeIterator
PostSidecarNode = namedtuple('PostSidecarNode', ['is_video', 'display_url', 'video_url'])
PostSidecarNode.__doc__ = "Item of a Sidecar Post."
@@ -26,7 +26,7 @@ PostCommentAnswer.likes_count.__doc__ = "Number of likes on comment."
PostComment = namedtuple('PostComment', (*PostCommentAnswer._fields, 'answers')) # type: ignore
for field in PostCommentAnswer._fields:
getattr(PostComment, field).__doc__ = getattr(PostCommentAnswer, field).__doc__
getattr(PostComment, field).__doc__ = getattr(PostCommentAnswer, field).__doc__ # pylint: disable=no-member
PostComment.answers.__doc__ = r"Iterator which yields all :class:`PostCommentAnswer`\ s for the comment." # type: ignore
PostLocation = namedtuple('PostLocation', ['id', 'name', 'slug', 'has_public_page', 'lat', 'lng'])
@@ -402,11 +402,14 @@ class Post:
# If the answer's metadata already contains all comments, don't do GraphQL requests to obtain them
yield from (_postcommentanswer(comment['node']) for comment in answer_edges)
return
yield from (_postcommentanswer(answer_node) for answer_node in
self._context.graphql_node_list("51fdd02b67508306ad4484ff574a0b62",
{'comment_id': node['id']},
'https://www.instagram.com/p/' + self.shortcode + '/',
lambda d: d['data']['comment']['edge_threaded_comments']))
yield from NodeIterator(
self._context,
'51fdd02b67508306ad4484ff574a0b62',
lambda d: d['data']['comment']['edge_threaded_comments'],
_postcommentanswer,
{'comment_id': node['id']},
'https://www.instagram.com/p/{0}/'.format(self.shortcode),
)
def _postcomment(node):
return PostComment(*_postcommentanswer(node),
@@ -422,12 +425,14 @@ class Post:
# If the Post's metadata already contains all parent comments, don't do GraphQL requests to obtain them
yield from (_postcomment(comment['node']) for comment in comment_edges)
return
yield from (_postcomment(node) for node in
self._context.graphql_node_list(
"97b41c52301f77ce508f55e66d17620e",
{'shortcode': self.shortcode},
'https://www.instagram.com/p/' + self.shortcode + '/',
lambda d: d['data']['shortcode_media']['edge_media_to_parent_comment']))
yield from NodeIterator(
self._context,
'97b41c52301f77ce508f55e66d17620e',
lambda d: d['data']['shortcode_media']['edge_media_to_parent_comment'],
_postcomment,
{'shortcode': self.shortcode},
'https://www.instagram.com/p/{0}/'.format(self.shortcode),
)
def get_likes(self) -> Iterator['Profile']:
"""Iterate over all likes of the post. A :class:`Profile` instance of each likee is yielded."""
@@ -439,10 +444,14 @@ class Post:
# If the Post's metadata already contains all likes, don't do GraphQL requests to obtain them
yield from (Profile(self._context, like['node']) for like in likes_edges)
return
yield from (Profile(self._context, node) for node in
self._context.graphql_node_list("1cb6ec562846122743b61e492c85999f", {'shortcode': self.shortcode},
'https://www.instagram.com/p/' + self.shortcode + '/',
lambda d: d['data']['shortcode_media']['edge_liked_by']))
yield from NodeIterator(
self._context,
'1cb6ec562846122743b61e492c85999f',
lambda d: d['data']['shortcode_media']['edge_liked_by'],
lambda n: Profile(self._context, n),
{'shortcode': self.shortcode},
'https://www.instagram.com/p/{0}/'.format(self.shortcode),
)
@property
def is_sponsored(self) -> bool:
@@ -770,80 +779,110 @@ class Profile:
Use :attr:`profile_pic_url`."""
return self.profile_pic_url
def get_posts(self) -> Iterator[Post]:
"""Retrieve all posts from a profile."""
self._obtain_metadata()
yield from (Post(self._context, node, self) for node in
self._context.graphql_node_list("472f257a40c653c64c666ce877d59d2b",
{'id': self.userid},
'https://www.instagram.com/{0}/'.format(self.username),
lambda d: d['data']['user']['edge_owner_to_timeline_media'],
first_data=self._metadata('edge_owner_to_timeline_media')))
def get_posts(self) -> NodeIterator[Post]:
"""Retrieve all posts from a profile.
def get_saved_posts(self) -> Iterator[Post]:
"""Get Posts that are marked as saved by the user."""
:rtype: NodeIterator[Post]"""
self._obtain_metadata()
return NodeIterator(
self._context,
'472f257a40c653c64c666ce877d59d2b',
lambda d: d['data']['user']['edge_owner_to_timeline_media'],
lambda n: Post(self._context, n, self),
{'id': self.userid},
'https://www.instagram.com/{0}/'.format(self.username),
self._metadata('edge_owner_to_timeline_media'),
)
def get_saved_posts(self) -> NodeIterator[Post]:
"""Get Posts that are marked as saved by the user.
:rtype: NodeIterator[Post]"""
if self.username != self._context.username:
raise LoginRequiredException("--login={} required to get that profile's saved posts.".format(self.username))
self._obtain_metadata()
yield from (Post(self._context, node) for node in
self._context.graphql_node_list("f883d95537fbcd400f466f63d42bd8a1",
{'id': self.userid},
'https://www.instagram.com/{0}/'.format(self.username),
lambda d: d['data']['user']['edge_saved_media'],
first_data=self._metadata('edge_saved_media')))
return NodeIterator(
self._context,
'f883d95537fbcd400f466f63d42bd8a1',
lambda d: d['data']['user']['edge_saved_media'],
lambda n: Post(self._context, n),
{'id': self.userid},
'https://www.instagram.com/{0}/'.format(self.username),
self._metadata('edge_saved_media'),
)
def get_tagged_posts(self) -> Iterator[Post]:
def get_tagged_posts(self) -> NodeIterator[Post]:
"""Retrieve all posts where a profile is tagged.
:rtype: NodeIterator[Post]
.. versionadded:: 4.0.7"""
self._obtain_metadata()
yield from (Post(self._context, node, self if int(node['owner']['id']) == self.userid else None) for node in
self._context.graphql_node_list("e31a871f7301132ceaab56507a66bbb7",
{'id': self.userid},
'https://www.instagram.com/{0}/'.format(self.username),
lambda d: d['data']['user']['edge_user_to_photos_of_you']))
return NodeIterator(
self._context,
'e31a871f7301132ceaab56507a66bbb7',
lambda d: d['data']['user']['edge_user_to_photos_of_you'],
lambda n: Post(self._context, n, self if int(n['owner']['id']) == self.userid else None),
{'id': self.userid},
'https://www.instagram.com/{0}/'.format(self.username),
)
def get_igtv_posts(self) -> Iterator[Post]:
def get_igtv_posts(self) -> NodeIterator[Post]:
"""Retrieve all IGTV posts.
:rtype: NodeIterator[Post]
.. versionadded:: 4.3"""
self._obtain_metadata()
yield from (Post(self._context, node, self) for node in
self._context.graphql_node_list('bc78b344a68ed16dd5d7f264681c4c76',
{'id': self.userid},
'https://www.instagram.com/{0}/channel/'.format(self.username),
lambda d: d['data']['user']['edge_felix_video_timeline'],
first_data=self._metadata('edge_felix_video_timeline')))
return NodeIterator(
self._context,
'bc78b344a68ed16dd5d7f264681c4c76',
lambda d: d['data']['user']['edge_felix_video_timeline'],
lambda n: Post(self._context, n, self),
{'id': self.userid},
'https://www.instagram.com/{0}/channel/'.format(self.username),
self._metadata('edge_felix_video_timeline'),
)
def get_followers(self) -> Iterator['Profile']:
def get_followers(self) -> NodeIterator['Profile']:
"""
Retrieve list of followers of given profile.
To use this, one needs to be logged in and private profiles has to be followed.
:rtype: NodeIterator[Profile]
"""
if not self._context.is_logged_in:
raise LoginRequiredException("--login required to get a profile's followers.")
self._obtain_metadata()
yield from (Profile(self._context, node) for node in
self._context.graphql_node_list("37479f2b8209594dde7facb0d904896a",
{'id': str(self.userid)},
'https://www.instagram.com/' + self.username + '/',
lambda d: d['data']['user']['edge_followed_by']))
return NodeIterator(
self._context,
'37479f2b8209594dde7facb0d904896a',
lambda d: d['data']['user']['edge_followed_by'],
lambda n: Profile(self._context, n),
{'id': str(self.userid)},
'https://www.instagram.com/{0}/'.format(self.username),
)
def get_followees(self) -> Iterator['Profile']:
def get_followees(self) -> NodeIterator['Profile']:
"""
Retrieve list of followees (followings) of given profile.
To use this, one needs to be logged in and private profiles has to be followed.
:rtype: NodeIterator[Profile]
"""
if not self._context.is_logged_in:
raise LoginRequiredException("--login required to get a profile's followees.")
self._obtain_metadata()
yield from (Profile(self._context, node) for node in
self._context.graphql_node_list("58712303d941c6855d4e888c5f0cd22f",
{'id': str(self.userid)},
'https://www.instagram.com/' + self.username + '/',
lambda d: d['data']['user']['edge_follow']))
return NodeIterator(
self._context,
'58712303d941c6855d4e888c5f0cd22f',
lambda d: d['data']['user']['edge_follow'],
lambda n: Profile(self._context, n),
{'id': str(self.userid)},
'https://www.instagram.com/{0}/'.format(self.username),
)
def get_similar_accounts(self) -> Iterator['Profile']:
"""
@@ -1398,7 +1437,7 @@ class TopSearchResults:
return self._searchstring
JsonExportable = Union[Post, Profile, StoryItem, Hashtag]
JsonExportable = Union[Post, Profile, StoryItem, Hashtag, FrozenNodeIterator]
def save_structure_to_file(structure: JsonExportable, filename: str) -> None:
@@ -1447,6 +1486,8 @@ def load_structure_from_file(context: InstaloaderContext, filename: str) -> Json
return StoryItem(context, json_structure['node'])
elif node_type == "Hashtag":
return Hashtag(context, json_structure['node'])
elif node_type == "FrozenNodeIterator":
return FrozenNodeIterator(**json_structure['node'])
else:
raise InvalidArgumentException("{}: Not an Instaloader JSON.".format(filename))
elif 'shortcode' in json_structure:
+8 -7
View File
@@ -5,7 +5,7 @@ import shutil
import tempfile
import unittest
from itertools import islice
from typing import Dict, List
from typing import Optional
import instaloader
@@ -23,8 +23,7 @@ PRIVATE_PROFILE_ID = 1706625676
EMPTY_PROFILE = "not_public"
EMPTY_PROFILE_ID = 1928659031
# Preserve query timestamps (rate control) between tests to not get rate limited
instaloadercontext_query_timestamps = dict() # type: Dict[str, List[float]]
ratecontroller = None # type: Optional[instaloader.RateController]
class TestInstaloaderAnonymously(unittest.TestCase):
@@ -37,13 +36,15 @@ class TestInstaloaderAnonymously(unittest.TestCase):
download_comments=True,
save_metadata=True)
self.L.context.raise_all_errors = True
# pylint:disable=protected-access
self.L.context._graphql_query_timestamps = instaloadercontext_query_timestamps.copy()
if ratecontroller is not None:
# pylint:disable=protected-access
ratecontroller._context = self.L.context
self.L.context._rate_controller = ratecontroller
def tearDown(self):
# pylint:disable=global-statement,protected-access
global instaloadercontext_query_timestamps
instaloadercontext_query_timestamps = self.L.context._graphql_query_timestamps.copy()
global ratecontroller
ratecontroller = self.L.context._rate_controller
self.L.close()
os.chdir('/')
print("Removing {}".format(self.dir))