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

code clean

Browse source
This commit is contained in:
Christophe Benz 2010-04-20 03:05:40 +02:00
commit 8a08c79616
2 changed files with 4 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

4
weboob/backends/youtube/browser.py
View file

@ -33,10 +33,6 @@ class YoutubeBrowser(BaseBrowser):
'.*youtube\.com/results\?.*': ResultsPage,
}
def __init__(self, *args, **kwargs):
kwargs['parser'] = LxmlHtmlParser()
BaseBrowser.__init__(self, *args, **kwargs)
def iter_search_results(self, pattern, sortby):
if not pattern:
self.home()

12
weboob/backends/youtube/pages/video.py
View file

@ -25,29 +25,28 @@ from weboob.tools.browser import BasePage
from weboob.capabilities.video import Video
class VideoPage(BasePage):
URL_REGEXP = re.compile("https?://[w\.]*youtube.com/watch\?v=(\w+)")
URL_REGEX = re.compile(r"https?://[w\.]*youtube.com/watch\?v=(\w+)")
VIDEO_SIGNATURE_REGEX = re.compile(r'&t=([^ ,&]*)')
def on_loaded(self):
self.video = Video(self.get_id())
self.video.title = self.get_title()
self.video.url = self.get_url()
self.set_details(self.video)
def get_id(self):
m = self.URL_REGEXP.match(self.url)
m = self.URL_REGEX.match(self.url)
if m:
return m.group(1)
warning("Unable to parse ID")
return 0
VIDEO_SIGNATURE_RE = re.compile(r'&t=([^ ,&]*)')
def get_url(self):
video_signature = None
for data in self.document.getiterator('script'):
if not data.text:
continue
for m in re.finditer(self.VIDEO_SIGNATURE_RE, data.text):
for m in re.finditer(self.VIDEO_SIGNATURE_REGEX, data.text):
video_signature = m.group(1)
return 'http://www.youtube.com/get_video?video_id=%s&t=%s&fmt=18' % (self.video.id, video_signature)
@ -58,9 +57,6 @@ class VideoPage(BasePage):
return unicode(content).strip()
return u''
DATE_REGEXP = re.compile("\w+ (\w+) (\d+) (\d+):(\d+):(\d+) (\d+)")
MONTH2I = ['', 'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']
def set_details(self, v):
div = self.document.getroot().cssselect('div[id=watch-description-body]')
if not div: