From ab2ffab22d02d530e0b46f9e361ff53a2139898b Mon Sep 17 00:00:00 2001 From: u-spec-png <54671367+u-spec-png@users.noreply.github.com> Date: Fri, 22 Oct 2021 00:53:45 +0000 Subject: [PATCH] [Instagram] Add login (#1288) Authored by: u-spec-png --- yt_dlp/extractor/instagram.py | 44 ++++++++++++++++++++++++++++++++++- 1 file changed, 43 insertions(+), 1 deletion(-) diff --git a/yt_dlp/extractor/instagram.py b/yt_dlp/extractor/instagram.py index 3801c7af9..24f47f3a8 100644 --- a/yt_dlp/extractor/instagram.py +++ b/yt_dlp/extractor/instagram.py @@ -4,6 +4,7 @@ import hashlib import json import re +import time from .common import InfoExtractor from ..compat import ( @@ -20,11 +21,13 @@ try_get, url_or_none, variadic, + urlencode_postdata, ) class InstagramIE(InfoExtractor): _VALID_URL = r'(?Phttps?://(?:www\.)?instagram\.com/(?:p|tv|reel)/(?P[^/?#&]+))' + _NETRC_MACHINE = 'instagram' _TESTS = [{ 'url': 'https://instagram.com/p/aye83DjauH/?foo=bar#abc', 'md5': '0d2da106a9d2631273e192b372806516', @@ -140,6 +143,45 @@ def _extract_embed_url(webpage): if mobj: return mobj.group('link') + def _login(self): + username, password = self._get_login_info() + + login_webpage = self._download_webpage( + 'https://www.instagram.com/accounts/login/', None, + note='Downloading login webpage', errnote='Failed to download login webpage') + + shared_data = self._parse_json( + self._search_regex( + r'window\._sharedData\s*=\s*({.+?});', + login_webpage, 'shared data', default='{}'), + None) + + login = self._download_json('https://www.instagram.com/accounts/login/ajax/', None, note='Logging in', headers={ + 'Accept': '*/*', + 'X-IG-App-ID': '936619743392459', + 'X-ASBD-ID': '198387', + 'X-IG-WWW-Claim': '0', + 'X-Requested-With': 'XMLHttpRequest', + 'X-CSRFToken': shared_data['config']['csrf_token'], + 'X-Instagram-AJAX': shared_data['rollout_hash'], + 'Referer': 'https://www.instagram.com/', + }, data=urlencode_postdata({ + 'enc_password': f'#PWD_INSTAGRAM_BROWSER:0:{int(time.time())}:{password}', + 'username': username, + 'queryParams': '{}', + 'optIntoOneTap': 'false', + 'stopDeletionNonce': '', + 'trustedDeviceRecords': '{}', + })) + + if not login.get('authenticated'): + if login.get('message'): + raise ExtractorError(f'Unable to login: {login["message"]}') + raise ExtractorError('Unable to login') + + def _real_initialize(self): + self._login() + def _real_extract(self, url): mobj = self._match_valid_url(url) video_id = mobj.group('id') @@ -147,7 +189,7 @@ def _real_extract(self, url): webpage, urlh = self._download_webpage_handle(url, video_id) if 'www.instagram.com/accounts/login' in urlh.geturl().rstrip('/'): - self.raise_login_required('You need to log in to access this content', method='cookies') + self.raise_login_required('You need to log in to access this content') (media, video_url, description, thumbnail, timestamp, uploader, uploader_id, like_count, comment_count, comments, height,