Compare commits

..
17 Commits
Author SHA1 Message Date
Alexander Graf e268f9e625 Release of Version 4.3.2 2020-04-10 12:08:24 +02:00
Alexander Graf 793b7e82ba Limit feed node processing to Post nodes
Fixes #478.
2020-04-10 12:05:15 +02:00
Alexander Graf 7329ee10d8 Catch KeyError: 'authenticated' when Logging In
Fixes #472.
2020-04-10 12:05:15 +02:00
Alexander Graf 57d2ce9538 Alleviate #449 by catching bad metadata response
Instead of ungracefully failing with a TypeError, the Post is now skipped with
an error message containing the invalid JSON.
2020-04-10 11:57:36 +02:00
Alexander Graf c56657855d Release of Version 4.3.1 2020-04-04 10:54:04 +02:00
Alexander Graf 8c7561c5d7 Fix Downloading of Videos within a Sidecar Post
Fixes #558.
2020-04-04 10:51:55 +02:00
Alexander Graf 9c2e7c70ac Fix number output in download_igtv() 2020-03-16 13:38:13 +01:00
Alexander Graf ffbf5b517c Release of Version 4.3 2020-03-16 09:13:25 +01:00
Alexander Graf 0843e10187 First Release Candidate for Version 4.3 2020-03-15 14:28:16 +01:00
Alexander Graf 78a93c945e Revert "Revert "Remove nonworking saythanks.io link""
saythanks.io does not work again and the link is now removed.
This reverts commit b2acbcf0e0.
2020-03-14 17:56:44 +01:00
Alexander Graf bb3e309195 First Beta Release for Version 4.3 2020-03-14 17:21:07 +01:00
Alexander Graf 6cc2ed54ea Download IGTV Videos of a Profile (--igtv) 2020-03-14 16:56:51 +01:00
Alexander Graf 41cf260fdd Fix post filter for downloading tagged posts 2020-03-14 16:55:37 +01:00
Alexander Graf f910705c51 docs: Fix formatting of request_timeout param 2020-03-07 11:14:07 +01:00
Alexander Graf aa3f19dcbe Second Alpha Release for Version 4.3 2020-03-01 17:44:17 +01:00
Alexander Graf fe258f1abb Also Download Highlight Cover Pictures
Instaloader.download_highlights(), as well as the Instaloader CLI with
--highlight option, now also downloads the cover picture of each highlight.

This closes #323, where it was suggested.
2020-03-01 17:41:58 +01:00
Alexander Graf 534497bea5 fix misplacement of --request-timeout in docs 2020-02-28 09:49:29 +01:00
11 changed files with 164 additions and 54 deletions
+3 -6
View File
@@ -2,7 +2,7 @@
.. badges-start
|travis| |pypi| |pyversion| |license| |aur| |contributors| |downloads| |saythanks|
|travis| |pypi| |pyversion| |license| |aur| |contributors| |downloads|
.. |travis| image:: https://img.shields.io/travis/instaloader/instaloader/master.svg
:alt: Travis-CI Build Status
@@ -23,10 +23,6 @@
:alt: Contributor Count
:target: https://github.com/instaloader/instaloader/graphs/contributors
.. |saythanks| image:: https://img.shields.io/badge/Say%20Thanks-!-ff7efd.svg
:alt: Say Thanks!
:target: https://saythanks.io/to/aandergr
.. |aur| image:: https://img.shields.io/aur/version/instaloader.svg
:alt: Arch User Repository Package
:target: https://aur.archlinux.org/packages/instaloader/
@@ -57,7 +53,8 @@
::
instaloader [--comments] [--geotags] [--stories] [--highlights] [--tagged]
instaloader [--comments] [--geotags]
[--stories] [--highlights] [--tagged] [--igtv]
[--login YOUR-USERNAME] [--fast-update]
profile | "#hashtag" | :stories | :feed | :saved
-3
View File
@@ -51,9 +51,6 @@
<li class="nav-item">
<a target="_blank" class="nav-link" href="https://github.com/instaloader/instaloader">GitHub</a>
</li>
<li class="nav-item d-sm-none d-lg-block">
<a target="_blank" class="nav-link" href="https://saythanks.io/to/aandergr">Say Thanks!</a>
</li>
</ul>
<form class="form-inline" action="search.html" method="get">
<div class="input-group my-2 my-sm-0 ml-2">
+5 -2
View File
@@ -77,10 +77,13 @@ Instaloader supports the following targets:
instructs Instaloader to also **download the user's stories**,
- :option:`--highlights`
to **download highlights of each profile that is downloaded**, and
to **download highlights of each profile that is downloaded**,
- :option:`--tagged`
to **download posts where the user is tagged**.
to **download posts where the user is tagged**, and
- :option:`--igtv`
to **download IGTV videos**.
- ``"#hashtag"``
Posts with a certain **hashtag** (the quotes are usually necessary),
+12 -6
View File
@@ -129,6 +129,12 @@ What to Download of each Profile
.. versionadded:: 4.1
.. option:: --igtv
Also download IGTV videos.
.. versionadded:: 4.3
.. option:: --stories-only
.. deprecated:: 4.1
@@ -237,6 +243,12 @@ How to Download
.. versionadded:: 4.2
.. option:: --request-timeout N
Seconds to wait before timing out a connection request.
.. versionadded:: 4.3
Miscellaneous Options
^^^^^^^^^^^^^^^^^^^^^
@@ -246,12 +258,6 @@ Miscellaneous Options
if login credentials are needed but not given.
This is handy for running :ref:`instaloader-as-cronjob`.
.. option:: --request-timeout N
Seconds to wait before timing out a connection request.
.. versionadded:: 4.3
.. option:: +args.txt
Read arguments from file `args.txt`, a shortcut to provide arguments from
+2 -1
View File
@@ -45,7 +45,8 @@ See :ref:`install` for more options on how to install Instaloader.
::
instaloader [--comments] [--geotags] [--stories] [--highlights] [--tagged]
instaloader [--comments] [--geotags]
[--stories] [--highlights] [--tagged] [--igtv]
[--login YOUR-USERNAME] [--fast-update]
profile | "#hashtag" | %location_id |
:stories | :feed | :saved
+1 -1
View File
@@ -1,7 +1,7 @@
"""Download pictures (or videos) along with their captions and other metadata from Instagram."""
__version__ = '4.3a1'
__version__ = '4.3.2'
try:
+16 -7
View File
@@ -19,7 +19,8 @@ def usage_string():
argv0 = os.path.basename(sys.argv[0])
argv0 = "instaloader" if argv0 == "__main__.py" else argv0
return """
{0} [--comments] [--geotags] [--stories] [--highlights] [--tagged]
{0} [--comments] [--geotags]
{2:{1}} [--stories] [--highlights] [--tagged] [--igtv]
{2:{1}} [--login YOUR-USERNAME] [--fast-update]
{2:{1}} profile | "#hashtag" | %%location_id | :stories | :feed | :saved
{0} --help""".format(argv0, len(argv0), '')
@@ -61,7 +62,10 @@ def _main(instaloader: Instaloader, targetlist: List[str],
username: Optional[str] = None, password: Optional[str] = None,
sessionfile: Optional[str] = None,
download_profile_pic: bool = True, download_posts=True,
download_stories: bool = False, download_highlights: bool = False, download_tagged: bool = False,
download_stories: bool = False,
download_highlights: bool = False,
download_tagged: bool = False,
download_igtv: bool = False,
fast_update: bool = False,
max_count: Optional[int] = None, post_filter_str: Optional[str] = None,
storyitem_filter_str: Optional[str] = None) -> None:
@@ -158,7 +162,8 @@ def _main(instaloader: Instaloader, targetlist: List[str],
try:
profile = instaloader.check_profile_id(target)
if instaloader.context.is_logged_in and profile.has_blocked_viewer:
if download_profile_pic or ((download_posts or download_tagged) and not profile.is_private):
if download_profile_pic or ((download_posts or download_tagged or download_igtv)
and not profile.is_private):
raise ProfileNotExistsException("{} blocked you; But we download her anonymously."
.format(target))
else:
@@ -169,7 +174,7 @@ def _main(instaloader: Instaloader, targetlist: List[str],
# Not only our profile.has_blocked_viewer condition raises ProfileNotExistsException,
# check_profile_id() also does, since access to blocked profile may be responded with 404.
if instaloader.context.is_logged_in and (download_profile_pic or download_posts or
download_tagged):
download_tagged or download_igtv):
instaloader.context.log(err)
instaloader.context.log("Trying again anonymously, helps in case you are just blocked.")
with instaloader.anonymous_copy() as anonymous_loader:
@@ -185,14 +190,15 @@ def _main(instaloader: Instaloader, targetlist: List[str],
if profiles and download_profile_pic and not instaloader.context.is_logged_in:
instaloader.context.error("Warning: Use --login to download HD version of profile pictures.")
instaloader.download_profiles(profiles,
download_profile_pic, download_posts, download_tagged, download_highlights,
download_stories, fast_update, post_filter, storyitem_filter)
download_profile_pic, download_posts, download_tagged, download_igtv,
download_highlights, download_stories,
fast_update, post_filter, storyitem_filter)
if anonymous_retry_profiles:
instaloader.context.log("Downloading anonymously: {}"
.format(' '.join([p.username for p in anonymous_retry_profiles])))
with instaloader.anonymous_copy() as anonymous_loader:
anonymous_loader.download_profiles(anonymous_retry_profiles,
download_profile_pic, download_posts, download_tagged,
download_profile_pic, download_posts, download_tagged, download_igtv,
fast_update=fast_update, post_filter=post_filter)
except KeyboardInterrupt:
print("\nInterrupted by user.", file=sys.stderr)
@@ -287,6 +293,8 @@ def main():
help='Also download highlights of each profile that is downloaded. Requires --login.')
g_prof.add_argument('--tagged', action='store_true',
help='Also download posts where each profile is tagged.')
g_prof.add_argument('--igtv', action='store_true',
help='Also download IGTV videos.')
g_cond = parser.add_argument_group("Which Posts to Download")
@@ -411,6 +419,7 @@ def main():
download_stories=download_stories,
download_highlights=args.highlights,
download_tagged=args.tagged,
download_igtv=args.igtv,
fast_update=args.fast_update,
max_count=int(args.count) if args.count is not None else None,
post_filter_str=args.post_filter,
+78 -26
View File
@@ -142,7 +142,7 @@ class Instaloader:
: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 request_timeout: :option:`--request-timeout`, set per-request timeout (seconds)
.. attribute:: context
@@ -358,42 +358,56 @@ class Instaloader:
self.context.log('geo', end=' ', flush=True)
@_retry_on_connection_error
def download_profilepic(self, profile: Profile, _attempt: int = 1) -> None:
"""Downloads and saves profile pic."""
def download_title_pic(self, url: str, target: Union[str, Path], name_suffix: str, owner_profile: Profile,
_attempt: int = 1) -> None:
"""Downloads and saves a picture that does not have an association with a Post or StoryItem, such as a
Profile picture or a Highlight cover picture. Modification time is taken from the HTTP response headers.
.. versionadded:: 4.3"""
def _epoch_to_string(epoch: datetime) -> str:
return epoch.strftime('%Y-%m-%d_%H-%M-%S_UTC')
profile_pic_response = self.context.get_raw(profile.profile_pic_url)
http_response = self.context.get_raw(url)
date_object = None # type: Optional[datetime]
if 'Last-Modified' in profile_pic_response.headers:
date_object = datetime.strptime(profile_pic_response.headers["Last-Modified"], '%a, %d %b %Y %H:%M:%S GMT')
profile_pic_bytes = None
profile_pic_identifier = _epoch_to_string(date_object)
if 'Last-Modified' in http_response.headers:
date_object = datetime.strptime(http_response.headers["Last-Modified"], '%a, %d %b %Y %H:%M:%S GMT')
pic_bytes = None
pic_identifier = _epoch_to_string(date_object)
else:
profile_pic_bytes = profile_pic_response.content
profile_pic_identifier = md5(profile_pic_bytes).hexdigest()[:16]
profile_pic_extension = 'jpg'
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'))):
filename = '{0}/{1}_profile_pic.{2}'.format(self.dirname_pattern.format(profile=profile.username.lower(),
target=profile.username.lower()),
profile_pic_identifier, profile_pic_extension)
filename = '{0}/{1}_{2}.{3}'.format(self.dirname_pattern.format(profile=owner_profile.username.lower(),
target=target),
pic_identifier, name_suffix, pic_extension)
else:
filename = '{0}/{1}_{2}_profile_pic.{3}'.format(self.dirname_pattern.format(), profile.username.lower(),
profile_pic_identifier, profile_pic_extension)
content_length = profile_pic_response.headers.get('Content-Length', None)
filename = '{0}/{1}_{2}_{3}.{4}'.format(self.dirname_pattern.format(), target,
pic_identifier, name_suffix, pic_extension)
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
os.path.getsize(filename) >= int(content_length))):
self.context.log(filename + ' already exists')
return None
os.makedirs(os.path.dirname(filename), exist_ok=True)
self.context.write_raw(profile_pic_bytes if profile_pic_bytes else profile_pic_response, filename)
self.context.write_raw(pic_bytes if pic_bytes else http_response, filename)
if date_object:
os.utime(filename, (datetime.now().timestamp(), date_object.timestamp()))
self.context.log('') # log output of _get_and_write_raw() does not produce \n
def download_profilepic(self, profile: Profile) -> None:
"""Downloads and saves profile pic."""
self.download_title_pic(profile.profile_pic_url, profile.username.lower(), 'profile_pic', profile)
def download_highlight_cover(self, highlight: Highlight, target: Union[str, Path]) -> None:
"""Downloads and saves Highlight cover picture.
.. versionadded:: 4.3"""
self.download_title_pic(highlight.cover_url, target, 'cover', highlight.owner_profile)
@_requires_login
def save_session_to_file(self, filename: Optional[str] = None) -> None:
"""Saves internally stored :class:`requests.Session` object.
@@ -646,6 +660,9 @@ class Instaloader:
.. versionadded:: 4.1
.. versionchanged:: 4.3
Also downloads and saves the Highlight's cover pictures.
:param user: ID or Profile of the user whose highlights should get downloaded.
:param fast_update: If true, abort when first already-downloaded picture is encountered
:param filename_target: Replacement for {target} in dirname_pattern and filename_pattern
@@ -655,7 +672,11 @@ class Instaloader:
"""
for user_highlight in self.get_highlights(user):
name = user_highlight.owner_username
highlight_target = (filename_target
if filename_target
else Path(name) / Path(user_highlight.title)) # type: Union[str, Path]
self.context.log("Retrieving highlights \"{}\" from profile {}".format(user_highlight.title, name))
self.download_highlight_cover(user_highlight, highlight_target)
totalcount = user_highlight.itemcount
count = 1
for item in user_highlight.get_items():
@@ -666,9 +687,7 @@ class Instaloader:
count += 1
with self.context.error_catcher('Download highlights \"{}\" from user {}'.format(user_highlight.title,
name)):
downloaded = self.download_storyitem(item, filename_target
if filename_target
else Path(name) / Path(user_highlight.title))
downloaded = self.download_storyitem(item, highlight_target)
if fast_update and not downloaded:
break
@@ -684,8 +703,10 @@ class Instaloader:
while True:
feed = data["user"]["edge_web_feed_timeline"]
yield from (Post(self.context, edge["node"]) for edge in feed["edges"]
if not edge["node"]["__typename"] == "GraphSuggestedUserFeedUnit")
for edge in feed["edges"]:
node = edge["node"]
if node.get("__typename") in Post.supported_graphql_types() and node.get("shortcode") is not None:
yield Post(self.context, node)
if not feed["page_info"]["has_next_page"]:
break
data = self.context.graphql_query("d6f4427fbe92d846298cf93df0b937d3",
@@ -892,11 +913,29 @@ class Instaloader:
count += 1
if post_filter is not None and not post_filter(post):
self.context.log('<{} skipped>'.format(post))
continue
with self.context.error_catcher('Download tagged {}'.format(profile.username)):
downloaded = self.download_post(post, target if target else Path(profile.username) / Path(':tagged'))
if fast_update and not downloaded:
break
def download_igtv(self, profile: Profile, fast_update: bool = False,
post_filter: Optional[Callable[[Post], bool]] = None) -> None:
"""Download IGTV videos of a profile.
.. versionadded:: 4.3"""
self.context.log("Retrieving IGTV videos for profile {}.".format(profile.username))
for number, post in enumerate(profile.get_igtv_posts()):
self.context.log("[{0:{w}d}/{1:{w}d}] ".format(number+1, profile.igtvcount, w=len(str(profile.igtvcount))),
end="", flush=True)
if post_filter is not None and not post_filter(post):
self.context.log('<{} skipped>'.format(post))
continue
with self.context.error_catcher('Download IGTV {}'.format(post.shortcode)):
downloaded = self.download_post(post, target=profile.username)
if fast_update and not downloaded:
break
def _get_id_filename(self, profile_name: str) -> str:
if ((format_string_contains_key(self.dirname_pattern, 'profile') or
format_string_contains_key(self.dirname_pattern, 'target'))):
@@ -969,7 +1008,10 @@ class Instaloader:
def download_profiles(self, profiles: Set[Profile],
profile_pic: bool = True, posts: bool = True,
tagged: bool = False, highlights: bool = False, stories: bool = False,
tagged: bool = False,
igtv: bool = False,
highlights: bool = False,
stories: bool = False,
fast_update: bool = False,
post_filter: Optional[Callable[[Post], bool]] = None,
storyitem_filter: Optional[Callable[[Post], bool]] = None,
@@ -980,6 +1022,7 @@ class Instaloader:
:param profile_pic: not :option:`--no-profile-pic`.
:param posts: not :option:`--no-posts`.
:param tagged: :option:`--tagged`.
:param igtv: :option:`--igtv`.
:param highlights: :option:`--highlights`.
:param stories: :option:`--stories`.
:param fast_update: :option:`--fast-update`.
@@ -989,7 +1032,11 @@ class Instaloader:
Whether :exc:`LoginRequiredException` and :exc:`PrivateProfileNotFollowedException` should be raised or
catched and printed with :meth:`InstaloaderContext.error_catcher`.
.. versionadded:: 4.1"""
.. versionadded:: 4.1
.. versionchanged:: 4.3
Add `igtv` parameter.
"""
@contextmanager
def _error_raiser(_str):
@@ -1015,7 +1062,7 @@ class Instaloader:
self.save_metadata_json(json_filename, profile)
# Catch some errors
if profile.is_private and (tagged or highlights or posts):
if profile.is_private and (tagged or igtv or highlights or posts):
if not self.context.is_logged_in:
raise LoginRequiredException("--login=USERNAME required.")
if not profile.followed_by_viewer and self.context.username != profile.username:
@@ -1026,6 +1073,11 @@ class Instaloader:
with self.context.error_catcher('Download tagged of {}'.format(profile_name)):
self.download_tagged(profile, fast_update=fast_update, post_filter=post_filter)
# Download IGTV, if requested
if igtv:
with self.context.error_catcher('Download IGTV of {}'.format(profile_name)):
self.download_igtv(profile, fast_update=fast_update, post_filter=post_filter)
# Download highlights, if requested
if highlights:
with self.context.error_catcher('Download highlights of {}'.format(profile_name)):
+6
View File
@@ -239,6 +239,12 @@ class InstaloaderContext:
resp_json['message']))
else:
raise ConnectionException("Login error: \"{}\" status.".format(resp_json['status']))
if 'authenticated' not in resp_json:
# Issue #472
if 'message' in resp_json:
raise ConnectionException("Login error: Unexpected response, \"{}\".".format(resp_json['message']))
else:
raise ConnectionException("Login error: Unexpected response, this might indicate a blocked IP.")
if not resp_json['authenticated']:
if resp_json['user']:
# '{"authenticated": false, "user": true, "status": "ok"}'
+35 -2
View File
@@ -98,6 +98,11 @@ class Post:
raise InvalidArgumentException("Wrong mediaid {0}, unable to convert to shortcode".format(str(mediaid)))
return b64encode(mediaid.to_bytes(9, 'big'), b'-_').decode().replace('A', ' ').lstrip().replace(' ', 'A')
@staticmethod
def supported_graphql_types() -> List[str]:
"""The values of __typename fields that the :class:`Post` class can handle."""
return ["GraphImage", "GraphVideo", "GraphSidecar"]
def _asdict(self):
node = self._node
if self._full_metadata_dict:
@@ -134,6 +139,12 @@ class Post:
pic_json = self._context.get_json("p/{0}/".format(self.shortcode), params={})
self._full_metadata_dict = pic_json['entry_data']['PostPage'][0]['graphql']['shortcode_media']
self._rhx_gis_str = pic_json.get('rhx_gis')
if self._full_metadata_dict is None:
# issue #449
self._context.error("Fetching Post metadata failed (issue #449). "
"The following data has been returned:\n"
+ json.dumps(pic_json['entry_data'], indent=2))
raise BadResponseException("Fetching Post metadata failed.")
if self.shortcode != self._full_metadata_dict['shortcode']:
self._node.update(self._full_metadata_dict)
raise PostChangedException
@@ -224,7 +235,11 @@ class Post:
def get_sidecar_nodes(self) -> Iterator[PostSidecarNode]:
"""Sidecar nodes of a Post with typename==GraphSidecar."""
if self.typename == 'GraphSidecar':
for edge in self._field('edge_sidecar_to_children', 'edges'):
edges = self._field('edge_sidecar_to_children', 'edges')
if any(edge['node']['is_video'] for edge in edges):
# video_url is only present in full metadata, issue #558.
edges = self._full_metadata['edge_sidecar_to_children']['edges']
for edge in edges:
node = edge['node']
is_video = node['is_video']
yield PostSidecarNode(is_video=is_video, display_url=node['display_url'],
@@ -518,10 +533,11 @@ class Profile:
def _asdict(self):
json_node = self._node.copy()
# remove posts
# remove posts to avoid "Circular reference detected" exception
json_node.pop('edge_media_collections', None)
json_node.pop('edge_owner_to_timeline_media', None)
json_node.pop('edge_saved_media', None)
json_node.pop('edge_felix_video_timeline', None)
if self._iphone_struct_:
json_node['iphone_struct'] = self._iphone_struct_
return json_node
@@ -598,6 +614,10 @@ class Profile:
def mediacount(self) -> int:
return self._metadata('edge_owner_to_timeline_media', 'count')
@property
def igtvcount(self) -> int:
return self._metadata('edge_felix_video_timeline', 'count')
@property
def followers(self) -> int:
return self._metadata('edge_followed_by', 'count')
@@ -741,6 +761,19 @@ class Profile:
lambda d: d['data']['user']['edge_user_to_photos_of_you'],
self._rhx_gis))
def get_igtv_posts(self) -> Iterator[Post]:
"""Retrieve all IGTV posts.
.. 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'],
self._rhx_gis,
self._metadata('edge_felix_video_timeline')))
def get_followers(self) -> Iterator['Profile']:
"""
Retrieve list of followers of given profile.
+6
View File
@@ -12,6 +12,7 @@ import instaloader
PROFILE_WITH_HIGHLIGHTS = 325732271
PUBLIC_PROFILE = "selenagomez"
PUBLIC_PROFILE_ID = 460563723
PUBLIC_PROFILE_WITH_IGTV = "natgeo"
HASHTAG = "kitten"
LOCATION = "362629379"
OWN_USERNAME = "aandergr"
@@ -104,6 +105,11 @@ class TestInstaloaderAnonymously(unittest.TestCase):
PAGING_MAX_COUNT):
print(post)
def test_public_profile_igtv(self):
for post in islice(instaloader.Profile.from_username(self.L.context, PUBLIC_PROFILE_WITH_IGTV).get_igtv_posts(),
PAGING_MAX_COUNT):
print(post)
class TestInstaloaderLoggedIn(TestInstaloaderAnonymously):