support passing timeout to requests (#422)

Adds a request_timeout parameter to Instaloader instantiation.

Closes #330.

docs/cli-options.rst

@@ -246,6 +246,10 @@ 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.
+
 .. option:: +args.txt
 
    Read arguments from file `args.txt`, a shortcut to provide arguments from

instaloader/__main__.py

@@ -343,6 +343,8 @@ def main():
                        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('--request-timeout', metavar='N', type=float,
+                       help='seconds to wait before timing out a connection request')
 
     g_misc = parser.add_argument_group('Miscellaneous Options')
     g_misc.add_argument('-q', '--quiet', action='store_true',
@@ -397,6 +399,7 @@ def main():
                              post_metadata_txt_pattern=post_metadata_txt_pattern,
                              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)
         _main(loader,
               args.profile,

instaloader/instaloader.py

@@ -142,6 +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)
 
     .. attribute:: context
 
@@ -150,6 +151,7 @@ class Instaloader:
 
     def __init__(self,
                  sleep: bool = True, quiet: bool = False,
+                 request_timeout: Optional[float] = None,
                  user_agent: Optional[str] = None,
                  dirname_pattern: Optional[str] = None,
                  filename_pattern: Optional[str] = None,
@@ -165,7 +167,7 @@ class Instaloader:
                  max_connection_attempts: int = 3,
                  commit_mode: bool = False):
 
-        self.context = InstaloaderContext(sleep, quiet, user_agent, max_connection_attempts)
+        self.context = InstaloaderContext(sleep, quiet, user_agent, max_connection_attempts, request_timeout)
 
         # configuration parameters
         self.dirname_pattern = dirname_pattern or "{target}"
@@ -191,12 +193,20 @@ class Instaloader:
     @contextmanager
     def anonymous_copy(self):
         """Yield an anonymous, otherwise equally-configured copy of an Instaloader instance; Then copy its error log."""
-        new_loader = Instaloader(self.context.sleep, self.context.quiet, self.context.user_agent, self.dirname_pattern,
+        new_loader = Instaloader(
-                                 self.filename_pattern, download_pictures=self.download_pictures,
+            self.context.sleep,
+            self.context.request_timeout,
+            self.context.quiet,
+            self.context.user_agent,
+            self.dirname_pattern,
+            self.filename_pattern,
+            download_pictures=self.download_pictures,
             download_videos=self.download_videos,
             download_video_thumbnails=self.download_video_thumbnails,
-                                 download_geotags=self.download_geotags, download_comments=self.download_comments,
+            download_geotags=self.download_geotags,
-                                 save_metadata=self.save_metadata, compress_json=self.compress_json,
+            download_comments=self.download_comments,
+            save_metadata=self.save_metadata,
+            compress_json=self.compress_json,
             post_metadata_txt_pattern=self.post_metadata_txt_pattern,
             storyitem_metadata_txt_pattern=self.storyitem_metadata_txt_pattern,
             max_connection_attempts=self.context.max_connection_attempts)

instaloader/instaloadercontext.py

@@ -10,6 +10,7 @@ import time
 import urllib.parse
 from contextlib import contextmanager
 from datetime import datetime, timedelta
+from functools import partial
 from typing import Any, Callable, Dict, Iterator, List, Optional, Union
 
 import requests
@@ -18,11 +19,15 @@ import requests.utils
 from .exceptions import *
 
 
-def copy_session(session: requests.Session) -> requests.Session:
+def copy_session(session: requests.Session, request_timeout: Optional[float] = None) -> requests.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.copy() # type: ignore
+    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
+        new.request = partial(new.request, timeout=request_timeout) # type: ignore
     return new
 
 
@@ -47,9 +52,10 @@ class InstaloaderContext:
     """
 
     def __init__(self, sleep: bool = True, quiet: bool = False, user_agent: Optional[str] = None,
-                 max_connection_attempts: int = 3):
+                 max_connection_attempts: int = 3, request_timeout: Optional[float] = None):
 
         self.user_agent = user_agent if user_agent is not None else default_user_agent()
+        self.request_timeout = request_timeout
         self._session = self.get_anonymous_session()
         self.username = None
         self.sleep = sleep
@@ -155,6 +161,10 @@ class InstaloaderContext:
                                 'ig_vw': '1920', 'csrftoken': '',
                                 's_network': '', 'ds_user_id': ''})
         session.headers.update(self._default_http_header(empty_session_only=True))
+        if self.request_timeout is not None:
+            # Override default timeout behavior.
+            # Need to silence mypy bug for this. See: https://github.com/python/mypy/issues/2427
+            session.request = partial(session.request, timeout=self.request_timeout) # type: ignore
         return session
 
     def save_session_to_file(self, sessionfile):
@@ -167,6 +177,10 @@ class InstaloaderContext:
         session.cookies = requests.utils.cookiejar_from_dict(pickle.load(sessionfile))
         session.headers.update(self._default_http_header())
         session.headers.update({'X-CSRFToken': session.cookies.get_dict()['csrftoken']})
+        if self.request_timeout is not None:
+            # Override default timeout behavior.
+            # Need to silence mypy bug for this. See: https://github.com/python/mypy/issues/2427
+            session.request = partial(session.request, timeout=self.request_timeout) # type: ignore
         self._session = session
         self.username = username
 
@@ -191,6 +205,10 @@ class InstaloaderContext:
                                 'ig_vw': '1920', 'ig_cb': '1', 'csrftoken': '',
                                 's_network': '', 'ds_user_id': ''})
         session.headers.update(self._default_http_header())
+        if self.request_timeout is not None:
+            # Override default timeout behavior.
+            # Need to silence mypy bug for this. See: https://github.com/python/mypy/issues/2427
+            session.request = partial(session.request, timeout=self.request_timeout) # type: ignore
         session.get('https://www.instagram.com/web/__mid/')
         csrf_token = session.cookies.get_dict()['csrftoken']
         session.headers.update({'X-CSRFToken': csrf_token})
@@ -203,7 +221,7 @@ class InstaloaderContext:
         except json.decoder.JSONDecodeError:
             raise ConnectionException("Login error: JSON decode fail, {} - {}.".format(login.status_code, login.reason))
         if resp_json.get('two_factor_required'):
-            two_factor_session = copy_session(session)
+            two_factor_session = copy_session(session, self.request_timeout)
             two_factor_session.headers.update({'X-CSRFToken': csrf_token})
             two_factor_session.cookies.update({'csrftoken': csrf_token})
             self.two_factor_auth_pending = (two_factor_session,
@@ -426,7 +444,7 @@ class InstaloaderContext:
         :param rhx_gis: 'rhx_gis' variable as somewhere returned by Instagram, needed to 'sign' request
         :return: The server's response dictionary.
         """
-        with copy_session(self._session) as tmpsession:
+        with copy_session(self._session, self.request_timeout) as tmpsession:
             tmpsession.headers.update(self._default_http_header(empty_session_only=True))
             del tmpsession.headers['Connection']
             del tmpsession.headers['Content-Length']
@@ -494,7 +512,7 @@ class InstaloaderContext:
         :raises ConnectionException: When query repeatedly failed.
 
         .. versionadded:: 4.2.1"""
-        with copy_session(self._session) as tempsession:
+        with copy_session(self._session, self.request_timeout) as tempsession:
             tempsession.headers['User-Agent'] = 'Instagram 10.3.2 (iPhone7,2; iPhone OS 9_3_3; en_US; en-US; ' \
                                                 'scale=2.00; 750x1334) AppleWebKit/420+'
             for header in ['Host', 'Origin', 'X-Instagram-AJAX', 'X-Requested-With']: