diff options
author | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2013-10-27 14:18:55 +0100 |
---|---|---|
committer | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2013-10-27 14:18:55 +0100 |
commit | af4d506eb35a257e91098fa92498b24ef5de14c6 (patch) | |
tree | fe4e67797c2b77d3fc0c49358666684e09fb3f20 /youtube_dl | |
parent | 749a4fd2fd88017bafca5c298f16123fd0146b40 (diff) |
[faz] Use a regex for getting the description
The page cannot be parsed in python2.6 with the html parser.
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/extractor/faz.py | 6 |
1 files changed, 2 insertions, 4 deletions
diff --git a/youtube_dl/extractor/faz.py b/youtube_dl/extractor/faz.py index deaa4ed2d..89ed08db4 100644 --- a/youtube_dl/extractor/faz.py +++ b/youtube_dl/extractor/faz.py @@ -5,8 +5,6 @@ import xml.etree.ElementTree from .common import InfoExtractor from ..utils import ( determine_ext, - clean_html, - get_element_by_attribute, ) @@ -47,12 +45,12 @@ class FazIE(InfoExtractor): '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 = { 'id': video_id, 'title': self._og_search_title(webpage), 'formats': formats, - 'description': clean_html(descr_html), + 'description': descr, 'thumbnail': config.find('STILL/STILL_BIG').text, } # TODO: Remove when #980 has been merged |