Upstream/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-16 14:18:10 +01:00
Code Issues Projects Releases Wiki Activity

[facebook] Fix extraction (closes #11926)

Browse Source
This commit is contained in:
Sergey M․ 2017-02-01 23:15:38 +07:00
parent 000f207944
commit b83ef507b4
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 27 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
youtube_dl/extractor/facebook.py
View File

@ -12,14 +12,16 @@ from ..compat import (
compat_urllib_parse_unquote_plus, compat_urllib_parse_unquote_plus,
) )
from ..utils import ( from ..utils import (
clean_html,
error_to_compat_str, error_to_compat_str,
ExtractorError, ExtractorError,
get_element_by_id,
int_or_none, int_or_none,
js_to_json,
limit_length, limit_length,
sanitized_Request, sanitized_Request,
try_get,
urlencode_postdata, urlencode_postdata,
get_element_by_id,
clean_html,
) )
@ -243,14 +245,30 @@ class FacebookIE(InfoExtractor):
video_data = None video_data = None
server_js_data = self._parse_json(self._search_regex( def extract_video_data(instances):
r'handleServerJS\(({.+})(?:\);|,")', webpage, 'server js data', default='{}'), video_id) for item in instances:
for item in server_js_data.get('instances', []):
if item[1][0] == 'VideoConfig': if item[1][0] == 'VideoConfig':
video_item = item[2][0] video_item = item[2][0]
if video_item.get('video_id') == video_id: if video_item.get('video_id') == video_id:
video_data = video_item['videoData'] return video_item['videoData']
break
server_js_data = self._parse_json(self._search_regex(
r'handleServerJS\(({.+})(?:\);|,")', webpage,
'server js data', default='{}'), video_id, fatal=False)
if server_js_data:
video_data = extract_video_data(server_js_data.get('instances', []))
if not video_data:
server_js_data = self._parse_json(
self._search_regex(
r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+stream_pagelet',
webpage, 'js data', default='{}'),
video_id, transform_source=js_to_json, fatal=False)
if server_js_data:
video_data = extract_video_data(try_get(
server_js_data, lambda x: x['jsmods']['instances'],
list) or [])
if not video_data: if not video_data:
if not fatal_if_no_video: if not fatal_if_no_video: