Release of version 1.1

Closes #12.

.gitignore

@@ -0,0 +1,4 @@
+__pycache__/
+build/
+dist/
+instaloader.egg-info/

.travis.yml

@@ -8,4 +8,4 @@ python:
 install:
  - pip install pylint requests
 script:
- - python3 -m pylint -r n -d bad-whitespace,bad-continuation,missing-docstring,anomalous-backslash-in-string,multiple-imports,dangerous-default-value,locally-disabled instaloader
+ - python3 -m pylint -r n -d bad-whitespace,bad-continuation,missing-docstring,multiple-imports,too-many-arguments,locally-disabled instaloader

README.md

@@ -1,32 +1,43 @@
 # instaloader
 
-Simple downloader to fetch all Instagram pictures and captions from a given profile.
+Tool to download pictures (or videos) and captions from Instagram, from a given set
+of profiles, from your feed or from all followees of a given profile.
 
 ## Usage
 
-Ensure having [Python](https://www.python.org/) (at least version 3.3) and
-[python3-requests](https://pypi.python.org/pypi/requests/) installed.
+instaloader is written in Python, thus ensure having
+[Python](https://www.python.org/) (at least version 3.3) installed.
 
 If you intend to use this tool under Windows, it is highly recommended to first install
-[win-unicode-console](https://github.com/Drekin/win-unicode-console).
+[win-unicode-console](https://pypi.python.org/pypi/win_unicode_console).
 
-After having [downloaded instaloader.py](https://github.com/Thammus/instaloader/releases), you invoke it with
+After having [downloaded instaloader](https://github.com/Thammus/instaloader/releases), unzip it and
+invoke bundled `setup.py` (requiring [setuptools](https://pypi.python.org/pypi/setuptools)) to
+install it:
 ```
-./instaloader.py profile [profile ...]
+./setup.py install [--user]
+```
+(pass `--user` to install it for your user only instead of globally)
+instaloader requires [python3-requests](https://pypi.python.org/pypi/requests/), which will be
+installed automatically by setup.py, if not already installed.
+
+Now, to download a set of profiles, do
+```
+instaloader profile [profile ...]
 ```
 where `profile` is the name of a profile you want to download. Instead of only one profile, you may
 also specify a list of profiles.
 
 To later update your local copy of that profile, you may run
 ```
-./instaloader.py --fast-update profile [profile ...]
+instaloader --fast-update profile [profile ...]
 ```
 When `--fast-update` is given, instaloder terminates when arriving at the first already-downloaded
 picture.
 
 Instaloader can also be used to **download private profiles**. To do so, invoke it with
 ```
-./instaloader.py --login=your_username profile [profile ...]
+instaloader --login=your_username profile [profile ...]
 ```
 When invoked like this, it also **stores the session cookies** in a file in `/tmp`, which will be
 reused later when `--login` is given. So you can download private profiles **non-interactively**
@@ -34,12 +45,17 @@ when you already have a valid session cookies file.
 
 If you want to **download all followees of a given profile**, call
 ```
-./instaloader.py --login=your_username @profile
+instaloader --login=your_username @profile
+```
+
+To **download all the pictures which you have liked**, call
+```
+instaloader --login=your_username :feed-liked
 ```
 
 The `--quiet` option makes it also **suitable as a cron job**.
 
-To get a list of other helpful flags, run `./instaloader.py --help`.
+To get a list of other helpful flags, run `instaloader --help`.
 
 ## Usage as library
 
@@ -67,8 +83,20 @@ for f in followees:
         pass
 ```
 
-`get_followees()` also returns unique IDs for all loaded followees. These IDs stay unchanged even
-if a user changes his/her username. To get the current username of a profile, given this unique ID
+You could also download your last 20 liked pics with
+```python
+instaloader.download_feed_pics(session, max_count=20, fast_update=True,
+                               filter_func=lambda node: not node["likes"]["viewer_has_liked"])
+```
+
+Each Instagram profile has its own unique ID which stays unmodified even if a user changes his/her
+username. To get said ID, given the profile's name, you may call
+```python
+instaloader.get_id_by_username(PROFILE_NAME)
+```
+
+`get_followees()` also returns unique IDs for all loaded followees. To get the current username of a
+profile, given this unique ID
 `get_username_by_id()` can be used. For example:
 ```python
 instaloader.get_username_by_id(session, followees[0]['id'])

instaloader.py

@@ -1,11 +1,23 @@
 #!/usr/bin/env python3
 
+"""Tool to download pictures (or videos) and captions from Instagram, from a given set
+of profiles, from your feed or from all followees of a given profile."""
+
 import re, json, datetime, shutil, os, time, random, sys, pickle, getpass, tempfile
 from argparse import ArgumentParser
-import requests, requests.utils
 from io import BytesIO
+import requests, requests.utils
+
+# To get version from setup.py for instaloader --version
+import pkg_resources
+try:
+    # pylint:disable=no-member
+    __version__ = pkg_resources.get_distribution('instaloader').version
+except pkg_resources.DistributionNotFound:
+    __version__ = 'Run ./setup.py --version'
 
 try:
+    # pylint:disable=wrong-import-position
     import win_unicode_console
 except ImportError:
     WINUNICODE = False
@@ -13,6 +25,7 @@ else:
     win_unicode_console.enable()
     WINUNICODE = True
 
+
 class InstaloaderException(Exception):
     """Base exception for this script"""
     pass
@@ -40,29 +53,27 @@ class ConnectionException(InstaloaderException):
     pass
 
 
-def log(*msg, sep='', end='\n', flush=False, quiet=False):
+def _log(*msg, sep='', end='\n', flush=False, quiet=False):
     if not quiet:
         print(*msg, sep=sep, end=end, flush=flush)
 
-def get_json(name, session, max_id=0, sleep_min_max=[1,5]):
+
+def get_json(name, session, max_id=0, sleep=True):
+    """Return JSON of a profile"""
     resp = session.get('http://www.instagram.com/'+name, \
         params={'max_id': max_id})
-    time.sleep(abs(sleep_min_max[1]-sleep_min_max[0])*random.random()+abs(sleep_min_max[0]))
-    match = re.search('window\._sharedData = .*<', resp.text)
+    if sleep:
+        time.sleep(4 * random.random() + 1)
+    match = re.search('window\\._sharedData = .*<', resp.text)
     if match is None:
         return None
     else:
         return json.loads(match.group(0)[21:-2])
 
-def get_last_id(data):
-    if len(data["entry_data"]) == 0 or \
-        len(data["entry_data"]["ProfilePage"][0]["user"]["media"]["nodes"]) == 0:
-        return None
-    else:
-        data = data["entry_data"]["ProfilePage"][0]["user"]["media"]["nodes"]
-        return int(data[len(data)-1]["id"])
 
 def get_username_by_id(session, profile_id):
+    """To get the current username of a profile, given its unique ID, this function can be used.
+    session is required to be a logged-in (i.e. non-anonymous) session."""
     tempsession = copy_session(session)
     tempsession.headers.update({'Content-Type' : 'application/json'})
     resp = tempsession.post('https://www.instagram.com/query/', data='q=ig_user(' +
@@ -80,17 +91,28 @@ def get_username_by_id(session, profile_id):
         raise LoginRequiredException("Login required to determine username (id: " +
                                         str(profile_id) + ").")
 
-def epoch_to_string(epoch):
+
+def get_id_by_username(profile):
+    """Each Instagram profile has its own unique ID which stays unmodified even if a user changes
+    his/her username. To get said ID, given the profile's name, you may call this function."""
+    data = get_json(profile, get_anonymous_session())
+    if len(data["entry_data"]) == 0 or "ProfilePage" not in data("entry_data"):
+        raise ProfileNotExistsException("Profile {0} does not exist.".format(profile))
+    return int(data['entry_data']['ProfilePage'][0]['user']['id'])
+
+
+def _epoch_to_string(epoch):
     return datetime.datetime.fromtimestamp(epoch).strftime('%Y-%m-%d_%H-%M-%S')
 
-def get_file_extension(url):
-    match = re.search('\.[a-z]*\?', url)
-    if match is None:
-        return url[-3:]
-    else:
-        return match.group(0)[1:-1]
 
 def get_followees(profile, session):
+    """
+    Retrieve list of followees of given profile
+
+    :param profile: Name of profile to lookup followees
+    :param session: Session belonging to a user, i.e. not an anonymous session
+    :return: List of followees (list of dictionaries), as returned by instagram server
+    """
     tmpsession = copy_session(session)
     data = get_json(profile, tmpsession)
     profile_id = data['entry_data']['ProfilePage'][0]['user']['id']
@@ -139,17 +161,21 @@ def get_followees(profile, session):
                                   "unable to gather followees.")
     raise LoginRequiredException("Login required to gather followees.")
 
+
 def download_pic(name, url, date_epoch, outputlabel=None, quiet=False):
-    # Returns true, if file was actually downloaded, i.e. updated
+    """Downloads and saves picture with given url under given directory with given timestamp.
+    Returns true, if file was actually downloaded, i.e. updated."""
     if outputlabel is None:
-        outputlabel = epoch_to_string(date_epoch)
-    filename = name.lower() + '/' + epoch_to_string(date_epoch) + '.' + get_file_extension(url)
+        outputlabel = _epoch_to_string(date_epoch)
+    urlmatch = re.search('\\.[a-z]*\\?', url)
+    file_extension = url[-3:] if urlmatch is None else urlmatch.group(0)[1:-1]
+    filename = name.lower() + '/' + _epoch_to_string(date_epoch) + '.' + file_extension
     if os.path.isfile(filename):
-        log(outputlabel + ' exists', end=' ', flush=True, quiet=quiet)
+        _log(outputlabel + ' exists', end=' ', flush=True, quiet=quiet)
         return False
     resp = get_anonymous_session().get(url, stream=True)
     if resp.status_code == 200:
-        log(outputlabel, end=' ', flush=True, quiet=quiet)
+        _log(outputlabel, end=' ', flush=True, quiet=quiet)
         os.makedirs(name.lower(), exist_ok=True)
         with open(filename, 'wb') as file:
             resp.raw.decode_content = True
@@ -159,20 +185,24 @@ def download_pic(name, url, date_epoch, outputlabel=None, quiet=False):
     else:
         raise ConnectionException("File \'" + url + "\' could not be downloaded.")
 
-def save_caption(name, date_epoch, caption, quiet=False):
-    filename = name.lower() + '/' + epoch_to_string(date_epoch) + '.txt'
+
+def save_caption(name, date_epoch, caption, shorter_output=False, quiet=False):
+    """Updates picture caption"""
+    filename = name.lower() + '/' + _epoch_to_string(date_epoch) + '.txt'
     pcaption = caption.replace('\n', ' ').strip()
     caption = caption.encode("UTF-8")
-    if os.name in ['nt', 'ce'] and not WINUNICODE:
-        output = str()
+    if shorter_output:
+        pcaption = "txt"
     else:
-        output = '[' + ((pcaption[:26]+"…") if len(pcaption)>28 else pcaption) + ']'
-    if os.path.isfile(filename):
+        pcaption = '[' + ((pcaption[:29]+u"\u2026") if len(pcaption)>31 else pcaption) + ']'
+    try:
         with open(filename, 'rb') as file:
             file_caption = file.read()
         if file_caption.replace(b'\r\n', b'\n') == caption.replace(b'\r\n', b'\n'):
-            output = output + ' unchanged'
-            log(output, end=' ', flush=True, quiet=quiet)
+            try:
+                _log(pcaption + ' unchanged', end=' ', flush=True, quiet=quiet)
+            except UnicodeEncodeError:
+                _log('txt unchanged', end=' ', flush=True, quiet=quiet)
             return None
         else:
             def get_filename(index):
@@ -183,22 +213,32 @@ def save_caption(name, date_epoch, caption, quiet=False):
                 i = i + 1
             for index in range(i, 0, -1):
                 os.rename(get_filename(index-1), get_filename(index))
-            output = output + ' updated'
-    log(output, end=' ', flush=True, quiet=quiet)
+            try:
+                _log(pcaption + ' updated', end=' ', flush=True, quiet=quiet)
+            except UnicodeEncodeError:
+                _log('txt updated', end=' ', flush=True, quiet=quiet)
+    except FileNotFoundError:
+        pass
+    try:
+        _log(pcaption, end=' ', flush=True, quiet=quiet)
+    except UnicodeEncodeError:
+        _log('txt', end=' ', flush=True, quiet=quiet)
     os.makedirs(name.lower(), exist_ok=True)
     with open(filename, 'wb') as text_file:
         shutil.copyfileobj(BytesIO(caption), text_file)
     os.utime(filename, (datetime.datetime.now().timestamp(), date_epoch))
 
+
 def download_profilepic(name, url, quiet=False):
+    """Downloads and saves profile pic with given url."""
     date_object = datetime.datetime.strptime(requests.head(url).headers["Last-Modified"], \
         '%a, %d %b %Y %H:%M:%S GMT')
-    filename = name.lower() + '/' + epoch_to_string(date_object.timestamp()) + \
+    filename = name.lower() + '/' + _epoch_to_string(date_object.timestamp()) + \
         '_UTC_profile_pic.' + url[-3:]
     if os.path.isfile(filename):
-        log(filename + ' already exists', quiet=quiet)
+        _log(filename + ' already exists', quiet=quiet)
         return None
-    match = re.search('http.*://.*instagram.*[^/]*\.(com|net)/[^/]+/.', url)
+    match = re.search('http.*://.*instagram.*[^/]*\\.(com|net)/[^/]+/.', url)
     if match is None:
         raise ConnectionException("URL \'" + url + "\' could not be processed.")
     index = len(match.group(0))-1
@@ -206,7 +246,7 @@ def download_profilepic(name, url, quiet=False):
     url = url[:index] + 's2048x2048' + ('/' if offset == 0 else str()) + url[index+offset:]
     resp = get_anonymous_session().get(url, stream=True)
     if resp.status_code == 200:
-        log(filename, quiet=quiet)
+        _log(filename, quiet=quiet)
         os.makedirs(name.lower(), exist_ok=True)
         with open(filename, 'wb') as file:
             resp.raw.decode_content = True
@@ -215,12 +255,16 @@ def download_profilepic(name, url, quiet=False):
     else:
         raise ConnectionException("File \'" + url + "\' could not be downloaded.")
 
+
 def get_default_session_filename(username):
+    """Returns default session filename for given username."""
     dirname = tempfile.gettempdir() + "/" + ".instaloader-" + getpass.getuser()
     filename = dirname + "/" + "session-" + username
     return filename
 
+
 def save_session(session, username, filename=None, quiet=False):
+    """Saves requests.Session object."""
     if filename is None:
         filename = get_default_session_filename(username)
     dirname = os.path.dirname(filename)
@@ -230,9 +274,11 @@ def save_session(session, username, filename=None, quiet=False):
     with open(filename, 'wb') as sessionfile:
         os.chmod(filename, 0o600)
         pickle.dump(requests.utils.dict_from_cookiejar(session.cookies), sessionfile)
-        log("Saved session to %s." % filename, quiet=quiet)
+        _log("Saved session to %s." % filename, quiet=quiet)
+
 
 def load_session(username, filename=None, quiet=False):
+    """Returns loaded requests.Session object, or None if not found."""
     if filename is None:
         filename = get_default_session_filename(username)
     try:
@@ -241,19 +287,23 @@ def load_session(username, filename=None, quiet=False):
             session.cookies = requests.utils.cookiejar_from_dict(pickle.load(sessionfile))
             session.headers.update(default_http_header())
             session.headers.update({'X-CSRFToken':session.cookies.get_dict()['csrftoken']})
-            log("Loaded session from %s." % filename, quiet=quiet)
+            _log("Loaded session from %s." % filename, quiet=quiet)
             return session
     except FileNotFoundError:
         pass
 
+
 def copy_session(session):
+    """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
     return new
 
+
 def test_login(session):
+    """Returns the Instagram username to which given requests.Session object belongs, or None."""
     if session is None:
         return
     data = get_json(str(), session)
@@ -262,7 +312,9 @@ def test_login(session):
     time.sleep(4 * random.random() + 1)
     return data['config']['viewer']['username']
 
+
 def default_http_header(empty_session_only=False):
+    """Returns default HTTP header we use for requests."""
     user_agent = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 ' \
                 '(KHTML, like Gecko) Chrome/51.0.2704.79 Safari/537.36'
     header = {  'Accept-Encoding' : 'gzip, deflate', \
@@ -283,7 +335,9 @@ def default_http_header(empty_session_only=False):
         del header['X-Requested-With']
     return header
 
+
 def get_anonymous_session():
+    """Returns our default anonymous requests.Session object."""
     session = requests.Session()
     session.cookies.update({'sessionid' : '', 'mid' : '', 'ig_pr' : '1', \
                                  'ig_vw' : '1920', 'csrftoken' : '', \
@@ -291,6 +345,7 @@ def get_anonymous_session():
     session.headers.update(default_http_header(empty_session_only=True))
     return session
 
+
 def get_session(user, passwd):
     """Log in to instagram with given username and password and return session object"""
     session = requests.Session()
@@ -313,18 +368,175 @@ def get_session(user, passwd):
     else:
         raise ConnectionException('Login error! Connection error!')
 
+
+def get_feed_json(session, end_cursor=None, sleep=True):
+    """
+    Get JSON of the user's feed.
+
+    :param session: Session belonging to a user, i.e. not an anonymous session
+    :param end_cursor: The end cursor, as from json["feed"]["media"]["page_info"]["end_cursor"]
+    :param sleep: Sleep between requests to instagram server
+    :return: JSON
+    """
+    if end_cursor is None:
+        return get_json(str(), session, sleep=sleep)["entry_data"]["FeedPage"][0]
+    tmpsession = copy_session(session)
+    query = "q=ig_me()+%7B%0A++feed+%7B%0A++++media.after(" + end_cursor + "%2C+12)+%7B%0A"+\
+            "++++++nodes+%7B%0A++++++++id%2C%0A++++++++caption%2C%0A++++++++code%2C%0A++++++++"+\
+            "comments.last(4)+%7B%0A++++++++++count%2C%0A++++++++++nodes+%7B%0A++++++++++++"+\
+            "id%2C%0A++++++++++++created_at%2C%0A++++++++++++text%2C%0A++++++++++++"+\
+            "user+%7B%0A++++++++++++++id%2C%0A++++++++++++++profile_pic_url%2C%0A++++++++++++++"+\
+            "username%0A++++++++++++%7D%0A++++++++++%7D%2C%0A++++++++++"+\
+            "page_info%0A++++++++%7D%2C%0A++++++++comments_disabled%2C%0A++++++++"+\
+            "date%2C%0A++++++++dimensions+%7B%0A++++++++++height%2C%0A++++++++++"+\
+            "width%0A++++++++%7D%2C%0A++++++++display_src%2C%0A++++++++is_video%2C%0A++++++++"+\
+            "likes+%7B%0A++++++++++count%2C%0A++++++++++nodes+%7B%0A++++++++++++"+\
+            "user+%7B%0A++++++++++++++id%2C%0A++++++++++++++profile_pic_url%2C%0A++++++++++++++"+\
+            "username%0A++++++++++++%7D%0A++++++++++%7D%2C%0A++++++++++"+\
+            "viewer_has_liked%0A++++++++%7D%2C%0A++++++++location+%7B%0A++++++++++"+\
+            "id%2C%0A++++++++++has_public_page%2C%0A++++++++++name%0A++++++++%7D%2C%0A++++++++"+\
+            "owner+%7B%0A++++++++++id%2C%0A++++++++++blocked_by_viewer%2C%0A++++++++++"+\
+            "followed_by_viewer%2C%0A++++++++++full_name%2C%0A++++++++++"+\
+            "has_blocked_viewer%2C%0A++++++++++is_private%2C%0A++++++++++"+\
+            "profile_pic_url%2C%0A++++++++++requested_by_viewer%2C%0A++++++++++"+\
+            "username%0A++++++++%7D%2C%0A++++++++usertags+%7B%0A++++++++++"+\
+            "nodes+%7B%0A++++++++++++user+%7B%0A++++++++++++++"+\
+            "username%0A++++++++++++%7D%2C%0A++++++++++++x%2C%0A++++++++++++y%0A++++++++++"+\
+            "%7D%0A++++++++%7D%2C%0A++++++++video_url%2C%0A++++++++"+\
+            "video_views%0A++++++%7D%2C%0A++++++page_info%0A++++%7D%0A++%7D%2C%0A++id%2C%0A++"+\
+            "profile_pic_url%2C%0A++username%0A%7D%0A&ref=feed::show"
+    tmpsession.headers.update(default_http_header())
+    tmpsession.headers.update({'Referer' : 'https://www.instagram.com/'})
+    tmpsession.headers.update({'Content-Type' : 'application/json'})
+    resp = tmpsession.post('https://www.instagram.com/query/', data=query)
+    if sleep:
+        time.sleep(4 * random.random() + 1)
+    return json.loads(resp.text)
+
+
+def download_node(node, session, name,
+                  download_videos=True, sleep=True, shorter_output=False, quiet=False):
+    """
+    Download everything associated with one instagram node, i.e. picture, caption and video.
+
+    :param node: Node, as from media->nodes list in instagram's JSONs
+    :param session: Session
+    :param name: Name of profile to which this node belongs
+    :param download_videos: True, if videos should be downloaded
+    :param sleep: Sleep between requests to instagram server
+    :param shorter_output: Shorten log output by not printing captions
+    :param quiet: Suppress output
+    :return: True if something was downloaded, False otherwise, i.e. file was already there
+    """
+    downloaded = download_pic(name, node["display_src"], node["date"], quiet=quiet)
+    if sleep:
+        time.sleep(1.75 * random.random() + 0.25)
+    if "caption" in node:
+        save_caption(name, node["date"], node["caption"], shorter_output, quiet)
+    else:
+        _log("<no caption>", end=' ', flush=True, quiet=quiet)
+    if node["is_video"] and download_videos:
+        video_data = get_json('p/' + node["code"], session, sleep=sleep)
+        download_pic(name,
+                     video_data['entry_data']['PostPage'][0]['media']['video_url'],
+                     node["date"], 'mp4', quiet=quiet)
+    _log(quiet=quiet)
+    return downloaded
+
+
+def download_feed_pics(session, max_count=None, fast_update=False, filter_func=None,
+                       download_videos=True, shorter_output=False, sleep=True, quiet=False):
+    """
+    Download pictures from the user's feed.
+
+    Example to download up to the 20 pics the user last liked:
+    >>> download_feed_pics(load_session('USER'), max_count=20, fast_update=True,
+    >>>                    filter_func=lambda node: not node["likes"]["viewer_has_liked"])
+
+    :param session: Session belonging to a user, i.e. not an anonymous session
+    :param max_count: Maximum count of pictures to download
+    :param fast_update: If true, abort when first already-downloaded picture is encountered
+    :param filter_func: function(node), which returns True if given picture should not be downloaded
+    :param download_videos: True, if videos should be downloaded
+    :param shorter_output: Shorten log output by not printing captions
+    :param sleep: Sleep between requests to instagram server
+    :param quiet: Suppress output
+    """
+    data = get_feed_json(session, sleep=sleep)
+    count = 1
+    while data["feed"]["media"]["page_info"]["has_next_page"]:
+        for node in data["feed"]["media"]["nodes"]:
+            if max_count is not None and count > max_count:
+                return
+            name = node["owner"]["username"]
+            if filter_func is not None and filter_func(node):
+                _log("<pic by %s skipped>" % name, flush=True, quiet=quiet)
+                continue
+            _log("[%3i] %s " % (count, name), end="", flush=True, quiet=quiet)
+            count += 1
+            downloaded = download_node(node, session, name,
+                                       download_videos=download_videos, sleep=sleep,
+                                       shorter_output=shorter_output, quiet=quiet)
+            if fast_update and not downloaded:
+                return
+        data = get_feed_json(session, end_cursor=data["feed"]["media"]["page_info"]["end_cursor"],
+                             sleep=sleep)
+
+
+def check_id(profile, session, json_data, quiet=False):
+    """
+    Consult locally stored ID of profile with given name, check whether ID matches and whether name
+    has changed and return current name of the profile, and store ID of profile.
+    """
+    profile_exists = len(json_data["entry_data"]) > 0 and "ProfilePage" in json_data["entry_data"]
+    is_logged_in = json_data["config"]["viewer"] is not None
+    try:
+        with open(profile + "/id", 'rb') as id_file:
+            profile_id = int(id_file.read())
+        if (not profile_exists) or \
+            (profile_id != int(json_data['entry_data']['ProfilePage'][0]['user']['id'])):
+            if is_logged_in:
+                newname = get_username_by_id(session, profile_id)
+                _log("Profile {0} has changed its name to {1}.".format(profile, newname),
+                     quiet=quiet)
+                os.rename(profile, newname)
+                return newname
+            if profile_exists:
+                raise ProfileNotExistsException("Profile {0} does not match the stored "
+                                                "unique ID {1}.".format(profile, profile_id))
+            raise ProfileNotExistsException("Profile {0} does not exist. Please login to "
+                                            "update profile name. Unique ID: {1}."
+                                            .format(profile, profile_id))
+        return profile
+    except FileNotFoundError:
+        pass
+    if profile_exists:
+        os.makedirs(profile.lower(), exist_ok=True)
+        with open(profile + "/id", 'w') as text_file:
+            profile_id = json_data['entry_data']['ProfilePage'][0]['user']['id']
+            text_file.write(profile_id+"\n")
+            _log("Stored ID {0} for profile {1}.".format(profile_id, profile), quiet=quiet)
+        return profile
+    raise ProfileNotExistsException("Profile {0} does not exist.".format(profile))
+
+
 def download(name, session, profile_pic_only=False, download_videos=True,
-        fast_update=False, sleep_min_max=[0.25,2], quiet=False):
+        fast_update=False, shorter_output=False, sleep=True, quiet=False):
     """Download one profile"""
-    # pylint:disable=too-many-arguments,too-many-branches
+    # pylint:disable=too-many-branches
     # Get profile main page json
-    data = get_json(name, session)
-    if len(data["entry_data"]) == 0 or "ProfilePage" not in data["entry_data"]:
-        raise ProfileNotExistsException("Profile %s does not exist." % name)
+    data = get_json(name, session, sleep=sleep)
+    # check if profile does exist or name has changed since last download
+    # and update name and json data if necessary
+    name_updated = check_id(name, session, data, quiet=quiet)
+    if name_updated != name:
+        name = name_updated
+        data = get_json(name, session, sleep=sleep)
     # Download profile picture
     download_profilepic(name, data["entry_data"]["ProfilePage"][0]["user"]["profile_pic_url"],
             quiet=quiet)
-    time.sleep(abs(sleep_min_max[1]-sleep_min_max[0])*random.random()+abs(sleep_min_max[0]))
+    if sleep:
+        time.sleep(1.75 * random.random() + 0.25)
     if profile_pic_only:
         return
     # Catch some errors
@@ -335,35 +547,31 @@ def download(name, session, profile_pic_only=False, download_videos=True,
             raise PrivateProfileNotFollowedException("Profile %s: private but not followed." % name)
     else:
         if data["config"]["viewer"] is not None:
-            log("profile %s could also be downloaded anonymously." % name, quiet=quiet)
+            _log("profile %s could also be downloaded anonymously." % name, quiet=quiet)
     if ("nodes" not in data["entry_data"]["ProfilePage"][0]["user"]["media"] or
             len(data["entry_data"]["ProfilePage"][0]["user"]["media"]["nodes"]) == 0) \
                     and not profile_pic_only:
         raise ProfileHasNoPicsException("Profile %s: no pics found." % name)
     # Iterate over pictures and download them
+    def get_last_id(data):
+        if len(data["entry_data"]) == 0 or \
+                        len(data["entry_data"]["ProfilePage"][0]["user"]["media"]["nodes"]) == 0:
+            return None
+        else:
+            data = data["entry_data"]["ProfilePage"][0]["user"]["media"]["nodes"]
+            return int(data[len(data) - 1]["id"])
     totalcount = data["entry_data"]["ProfilePage"][0]["user"]["media"]["count"]
     count = 1
     while get_last_id(data) is not None:
         for node in data["entry_data"]["ProfilePage"][0]["user"]["media"]["nodes"]:
-            log("[%3i/%3i] " % (count, totalcount), end="", flush=True, quiet=quiet)
-            count = count + 1
-            downloaded = download_pic(name, node["display_src"], node["date"], quiet=quiet)
-            time.sleep(abs(sleep_min_max[1]-sleep_min_max[0])*random.random() + \
-                       abs(sleep_min_max[0]))
-            if "caption" in node:
-                save_caption(name, node["date"], node["caption"], quiet=quiet)
-            else:
-                log("<no caption>", end=' ', flush=True, quiet=quiet)
-            if node["is_video"] and download_videos:
-                video_data = get_json('p/' + node["code"], session)
-                download_pic(name, \
-                        video_data['entry_data']['PostPage'][0]['media']['video_url'], \
-                        node["date"], 'mp4', quiet=quiet)
-            log(quiet=quiet)
+            _log("[%3i/%3i] " % (count, totalcount), end="", flush=True, quiet=quiet)
+            count += 1
+            downloaded = download_node(node, session, name,
+                                       download_videos=download_videos, sleep=sleep,
+                                       shorter_output=shorter_output, quiet=quiet)
             if fast_update and not downloaded:
                 return
-        data = get_json(name, session, max_id=get_last_id(data))
-        time.sleep(abs(sleep_min_max[1]-sleep_min_max[0])*random.random()+abs(sleep_min_max[0]))
+        data = get_json(name, session, max_id=get_last_id(data), sleep=sleep)
 
 def get_logged_in_session(username, password=None, quiet=False):
     """Logs in and returns session, asking user for password if needed"""
@@ -382,15 +590,15 @@ def get_logged_in_session(username, password=None, quiet=False):
 
 def download_profiles(profilelist, username=None, password=None, sessionfile=None,
         profile_pic_only=False, download_videos=True, fast_update=False,
-        sleep_min_max=[0.25,2], quiet=False):
+        sleep=True, shorter_output=False, quiet=False):
     """Download set of profiles and handle sessions"""
-    # pylint:disable=too-many-arguments,too-many-branches,too-many-locals
+    # pylint:disable=too-many-branches,too-many-locals
     # Login, if desired
     if username is not None:
         session = load_session(username, sessionfile, quiet=quiet)
         if username != test_login(session):
             session = get_logged_in_session(username, password, quiet)
-        log("Logged in as %s." % username, quiet=quiet)
+        _log("Logged in as %s." % username, quiet=quiet)
     else:
         session = get_anonymous_session()
     # Try block for KeyboardInterrupt (save session on ^C)
@@ -400,20 +608,31 @@ def download_profiles(profilelist, username=None, password=None, sessionfile=Non
         # Generate set of targets
         for pentry in profilelist:
             if pentry[0] == '@':
-                log("Retrieving followees of %s..." % pentry[1:], quiet=quiet)
+                _log("Retrieving followees of %s..." % pentry[1:], quiet=quiet)
                 followees = get_followees(pentry[1:], session)
                 targets.update([followee['username'] for followee in followees])
+            elif pentry == ":feed-all" and username is not None:
+                _log("Retrieving pictures from your feed...", quiet=quiet)
+                download_feed_pics(session, fast_update=fast_update,
+                                   download_videos=download_videos, shorter_output=shorter_output,
+                                   sleep=sleep, quiet=quiet)
+            elif pentry == ":feed-liked" and username is not None:
+                _log("Retrieving pictures you liked from your feed...", quiet=quiet)
+                download_feed_pics(session, fast_update=fast_update,
+                                   filter_func=lambda node: not node["likes"]["viewer_has_liked"],
+                                   download_videos=download_videos, shorter_output=shorter_output,
+                                   sleep=sleep, quiet=quiet)
             else:
                 targets.add(pentry)
         if len(targets) == 0:
-            log("No profiles to download given.", quiet=quiet)
+            _log("No profiles to download given.", quiet=quiet)
         elif len(targets) > 1:
-            log("Downloading %i profiles..." % len(targets), quiet=quiet)
+            _log("Downloading %i profiles..." % len(targets), quiet=quiet)
         # Iterate through targets list and download them
         for target in targets:
             try:
                 download(target, session, profile_pic_only, download_videos,
-                        fast_update, sleep_min_max, quiet)
+                        fast_update, shorter_output, sleep, quiet)
             except NonfatalException as err:
                 failedtargets.append(target)
                 print(err, file=sys.stderr)
@@ -427,13 +646,14 @@ def download_profiles(profilelist, username=None, password=None, sessionfile=Non
         save_session(session, username, sessionfile, quiet=quiet)
 
 def main():
-    parser = ArgumentParser(description='Simple downloader to fetch all Instagram pics and '\
-                                        'captions from a given profile')
+    parser = ArgumentParser(description=__doc__)
     parser.add_argument('profile', nargs='*',
-            help='Name of profile to download, or @<profile> to download all followees of '\
-                    '<profile>')
+                        help='Name of profile to download; @<profile> to download all followees of '
+                             '<profile>; or the special targets :feed-all or :feed-liked to '
+                             'download pictures from your feed if --login is given (using '
+                             '--fast-update is recommended).')
     parser.add_argument('--version', action='version',
-                        version='1.0.1')
+                        version=__version__)
     parser.add_argument('-l', '--login', metavar='YOUR-USERNAME',
             help='Login name for your Instagram account. Not needed to download public '\
                     'profiles, but if you want to download private profiles or all followees of '\
@@ -454,6 +674,8 @@ def main():
             help='Abort at encounter of first already-downloaded picture')
     parser.add_argument('-S', '--no-sleep', action='store_true',
             help='Do not sleep between actual downloads of pictures')
+    parser.add_argument('-O', '--shorter-output', action='store_true',
+            help='Do not display captions while downloading')
     parser.add_argument('-q', '--quiet', action='store_true',
             help='Disable user interaction, i.e. do not print messages (except errors) and fail ' \
                     'if login credentials are needed but not given.')
@@ -461,7 +683,7 @@ def main():
     try:
         download_profiles(args.profile, args.login, args.password, args.sessionfile,
                 args.profile_pic_only, not args.skip_videos, args.fast_update,
-                [0,0] if args.no_sleep else [0.25,2], args.quiet)
+                not args.no_sleep, args.shorter_output, args.quiet)
     except InstaloaderException as err:
         raise SystemExit("Fatal error: %s" % err)
 

setup.py

@@ -0,0 +1,31 @@
+#!/usr/bin/env python3
+
+from setuptools import setup
+
+setup(
+    name='instaloader',
+    version='1.1',
+    py_modules=['instaloader'],
+    url='https://github.com/Thammus/instaloader',
+    license='MIT',
+    author='Alexander Graf, André Koch-Kramer',
+    author_email='mail@agraf.me, koch-kramer@web.de',
+    description='Tool to download pictures (or videos) and captions from Instagram, from a given '
+                'set of profiles, from your feed or from all followees of a given profile.',
+    install_requires=['requests>=2.4'],
+    python_requires='>=3.3',
+    entry_points={'console_scripts': ['instaloader=instaloader:main']},
+    zip_safe=True,
+    keywords='instagram downloader',
+    classifiers=[
+        'Development Status :: 5 - Production/Stable',
+        'Environment :: Console',
+        'License :: OSI Approved :: MIT License',
+        'Operating System :: OS Independent',
+        'Programming Language :: Python :: 3.3',
+        'Programming Language :: Python :: 3.4',
+        'Programming Language :: Python :: 3.5',
+        'Programming Language :: Python :: 3.6'
+        'Topic :: Internet'
+    ]
+)