nojhan/weboob-devel
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

fix parsing video IDs

Browse source
This commit is contained in:
Romain Bignon 2012-04-06 16:08:02 +02:00
commit 189896de02
1 changed files with 4 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

12
modules/dailymotion/pages.py
View file

@ -36,19 +36,15 @@ __all__ = ['IndexPage', 'VideoPage']
class IndexPage(BasePage): class IndexPage(BasePage):
def iter_videos(self): def iter_videos(self):
for div in self.parser.select(self.document.getroot(), 'div.dmpi_video_item'): for div in self.parser.select(self.document.getroot(), 'div.dmpi_video_item'):
_id = 0 _id = div.attrib.get('data-id', None)
for cls in div.attrib['class'].split():
if cls.startswith('id_'):
_id = int(cls[3:])
break
if _id == 0: if _id is None:
self.browser.logger.warning('Unable to find the ID of a video') self.browser.logger.warning('Unable to find the ID of a video')
continue continue
video = DailymotionVideo(int(_id)) video = DailymotionVideo(_id)
video.title = self.parser.select(div, 'h3 a', 1).text video.title = self.parser.select(div, 'h3 a', 1).text
video.author = self.parser.select(div, 'div.dmpi_user_login', 1).find('a').text video.author = self.parser.select(div, 'div.dmpi_user_login', 1).find('a').find('span').text.strip()
video.description = html2text(self.parser.tostring(self.parser.select(div, 'div.dmpi_video_description', 1))).strip() video.description = html2text(self.parser.tostring(self.parser.select(div, 'div.dmpi_video_description', 1))).strip()
try: try:
parts = self.parser.select(div, 'div.duration', 1).text.split(':') parts = self.parser.select(div, 'div.duration', 1).text.split(':')