github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[faz] Use a regex for getting the description

Browse source 
The page cannot be parsed in python2.6 with the html parser.
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-10-27 14:18:55 +01:00
parent 749a4fd2fd
commit af4d506eb3
1 changed files with 2 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
youtube_dl/extractor/faz.py
View file

@ -5,8 +5,6 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
clean_html,
get_element_by_attribute,
) )
@ -47,12 +45,12 @@ def _real_extract(self, url):
'format_id': code.lower(), 'format_id': code.lower(),
}) })
descr_html = get_element_by_attribute('class', 'Content Copy', webpage) descr = self._html_search_regex(r'<p class="Content Copy">(.*?)</p>', webpage, u'description')
info = { info = {
'id': video_id, 'id': video_id,
'title': self._og_search_title(webpage), 'title': self._og_search_title(webpage),
'formats': formats, 'formats': formats,
'description': clean_html(descr_html), 'description': descr,
'thumbnail': config.find('STILL/STILL_BIG').text, 'thumbnail': config.find('STILL/STILL_BIG').text,
} }
# TODO: Remove when #980 has been merged # TODO: Remove when #980 has been merged