etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 03:03:01 +00:00
Code Issues Projects Releases Wiki Activity

[crunchyroll] Fix description extraction

Browse source
This commit is contained in:
Sergey M․ 2015-11-07 20:02:39 +06:00
parent 2c740cf28d
commit 6d02b9a392
1 changed files with 6 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
youtube_dl/extractor/crunchyroll.py
View file

@ -21,6 +21,7 @@
bytes_to_intlist, bytes_to_intlist,
intlist_to_bytes, intlist_to_bytes,
int_or_none, int_or_none,
lowercase_escape,
remove_end, remove_end,
unified_strdate, unified_strdate,
urlencode_postdata, urlencode_postdata,
@ -104,7 +105,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
'id': '589804', 'id': '589804',
'ext': 'flv', 'ext': 'flv',
'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11', 'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
'description': 'md5:fe2743efedb49d279552926d0bd0cd9e', 'description': 'md5:2fbc01f90b87e8e9137296f37b461c12',
'thumbnail': 're:^https?://.*\.jpg$', 'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'Danny Choo Network', 'uploader': 'Danny Choo Network',
'upload_date': '20120213', 'upload_date': '20120213',
@ -292,7 +293,10 @@ def _real_extract(self, url):
webpage, 'video_title') webpage, 'video_title')
video_title = re.sub(r' {2,}', ' ', video_title) video_title = re.sub(r' {2,}', ' ', video_title)
video_description = self._html_search_regex( video_description = self._html_search_regex(
r'"description":"([^"]+)', webpage, 'video_description', default=None) r'<script[^>]*>\s*.+?\[media_id=%s\].+?"description"\s*:\s*"([^"]+)' % video_id,
webpage, 'description', default=None)
if video_description:
video_description = lowercase_escape(video_description.replace(r'\r\n', '\n'))
video_upload_date = self._html_search_regex( video_upload_date = self._html_search_regex(
[r'<div>Availability for free users:(.+?)</div>', r'<div>[^<>]+<span>\s*(.+?\d{4})\s*</span></div>'], [r'<div>Availability for free users:(.+?)</div>', r'<div>[^<>]+<span>\s*(.+?\d{4})\s*</span></div>'],
webpage, 'video_upload_date', fatal=False, flags=re.DOTALL) webpage, 'video_upload_date', fatal=False, flags=re.DOTALL)