From 238d42cf5d4b1a95ba42bf56dcb1bf559ac11c29 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 17 Apr 2018 22:37:50 +0700 Subject: [PATCH] [instagram:user] Fix extraction (closes #16119) --- youtube_dl/extractor/instagram.py | 49 ++++++++++++++++++++++++------- 1 file changed, 38 insertions(+), 11 deletions(-) diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index 8da1d5f2f..5cea37d92 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -6,11 +6,16 @@ import json import re from .common import InfoExtractor -from ..compat import compat_str +from ..compat import ( + compat_str, + compat_HTTPError, +) from ..utils import ( + ExtractorError, get_element_by_attribute, int_or_none, lowercase_escape, + std_headers, try_get, ) @@ -239,6 +244,8 @@ class InstagramUserIE(InfoExtractor): } } + _gis_tmpl = None + def _entries(self, data): def get_count(suffix): return int_or_none(try_get( @@ -257,16 +264,36 @@ class InstagramUserIE(InfoExtractor): 'first': 100, 'after': cursor, }) - s = '%s:%s:%s' % (rhx_gis, csrf_token, variables) - media = self._download_json( - 'https://www.instagram.com/graphql/query/', uploader_id, - 'Downloading JSON page %d' % page_num, headers={ - 'X-Requested-With': 'XMLHttpRequest', - 'X-Instagram-GIS': hashlib.md5(s.encode('utf-8')).hexdigest(), - }, query={ - 'query_hash': '472f257a40c653c64c666ce877d59d2b', - 'variables': variables, - })['data']['user']['edge_owner_to_timeline_media'] + + if self._gis_tmpl: + gis_tmpls = [self._gis_tmpl] + else: + gis_tmpls = [ + '%s' % rhx_gis, + '', + '%s:%s' % (rhx_gis, csrf_token), + '%s:%s:%s' % (rhx_gis, csrf_token, std_headers['User-Agent']), + ] + + for gis_tmpl in gis_tmpls: + try: + media = self._download_json( + 'https://www.instagram.com/graphql/query/', uploader_id, + 'Downloading JSON page %d' % page_num, headers={ + 'X-Requested-With': 'XMLHttpRequest', + 'X-Instagram-GIS': hashlib.md5( + ('%s:%s' % (gis_tmpl, variables)).encode('utf-8')).hexdigest(), + }, query={ + 'query_hash': '42323d64886122307be10013ad2dcc44', + 'variables': variables, + })['data']['user']['edge_owner_to_timeline_media'] + self._gis_tmpl = gis_tmpl + break + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + if gis_tmpl != gis_tmpls[-1]: + continue + raise edges = media.get('edges') if not edges or not isinstance(edges, list):