github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 20:30:41 -05:00
Code Issues Projects Releases Packages Wiki Activity

[facebook] Fix invalid video being extracted (Closes #9851)

Browse source
This commit is contained in:
Sergey M․ 2016-07-09 00:28:07 +07:00
parent 07d7689f2e
commit cedc70b292
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 15 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
youtube_dl/extractor/facebook.py
View file

@ -219,12 +219,23 @@ def _extract_from_url(self, url, video_id, fatal_if_no_video=True):
BEFORE = '{swf.addParam(param[0], param[1]);});' BEFORE = '{swf.addParam(param[0], param[1]);});'
AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});' AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});'
m = re.search(re.escape(BEFORE) + '(?:\n|\\\\n)(.*?)' + re.escape(AFTER), webpage) PATTERN = re.escape(BEFORE) + '(?:\n|\\\\n)(.*?)' + re.escape(AFTER)
if m:
swf_params = m.group(1).replace('\\\\', '\\').replace('\\"', '"') for m in re.findall(PATTERN, webpage):
swf_params = m.replace('\\\\', '\\').replace('\\"', '"')
data = dict(json.loads(swf_params)) data = dict(json.loads(swf_params))
params_raw = compat_urllib_parse_unquote(data['params']) params_raw = compat_urllib_parse_unquote(data['params'])
video_data = json.loads(params_raw)['video_data'] video_data_candidate = json.loads(params_raw)['video_data']
for _, f in video_data_candidate.items():
if not f:
continue
if isinstance(f, dict):
f = [f]
if isinstance(f, list):
continue
if f[0].get('video_id') == video_id:
video_data = video_data_candidate
break
def video_data_list2dict(video_data): def video_data_list2dict(video_data):
ret = {} ret = {}