midgard/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[youtube] Correct invalid JSON (Fixes #2353)

Browse source
This commit is contained in:
Philipp Hagemeister 2014-02-09 17:56:10 +01:00
parent 1afe753462
commit 81c2f20b53
3 changed files with 15 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
youtube_dl/extractor/common.py
View file

@ -271,8 +271,11 @@ class InfoExtractor(object):
def _download_json(self, url_or_request, video_id, def _download_json(self, url_or_request, video_id,
note=u'Downloading JSON metadata', note=u'Downloading JSON metadata',
errnote=u'Unable to download JSON metadata'): errnote=u'Unable to download JSON metadata',
transform_source=None):
json_string = self._download_webpage(url_or_request, video_id, note, errnote) json_string = self._download_webpage(url_or_request, video_id, note, errnote)
if transform_source:
json_string = transform_source(json_string)
try: try:
return json.loads(json_string) return json.loads(json_string)
except ValueError as ve: except ValueError as ve:

10
youtube_dl/extractor/youtube.py
View file

@ -34,6 +34,7 @@ from ..utils import (
unified_strdate, unified_strdate,
orderedSet, orderedSet,
write_json_file, write_json_file,
uppercase_escape,
) )
class YoutubeBaseInfoExtractor(InfoExtractor): class YoutubeBaseInfoExtractor(InfoExtractor):
@ -1590,11 +1591,10 @@ class YoutubeChannelIE(InfoExtractor):
# Download all channel pages using the json-based channel_ajax query # Download all channel pages using the json-based channel_ajax query
for pagenum in itertools.count(1): for pagenum in itertools.count(1):
url = self._MORE_PAGES_URL % (pagenum, channel_id) url = self._MORE_PAGES_URL % (pagenum, channel_id)
page = self._download_webpage(url, channel_id, page = self._download_json(
u'Downloading page #%s' % pagenum) url, channel_id, note=u'Downloading page #%s' % pagenum,
transform_source=uppercase_escape)
page = json.loads(page)
ids_in_page = self.extract_videos_from_page(page['content_html']) ids_in_page = self.extract_videos_from_page(page['content_html'])
video_ids.extend(ids_in_page) video_ids.extend(ids_in_page)

6
youtube_dl/utils.py
View file

@ -1214,3 +1214,9 @@ class PagedList(object):
if end == nextfirstid: if end == nextfirstid:
break break
return res return res
def uppercase_escape(s):
return re.sub(
r'\\U([0-9a-fA-F]{8})',
lambda m: compat_chr(int(m.group(1), base=16)), s)