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

fix module with new upstream website

Browse source
This commit is contained in:
Romain Bignon 2012-12-23 19:24:25 +01:00
commit 31d7e317fe
3 changed files with 21 additions and 35 deletions
Download patch file Download diff file Expand all files Collapse all files

20
modules/francetelevisions/browser.py
View file

@ -32,12 +32,10 @@ __all__ = ['PluzzBrowser']
class PluzzBrowser(BaseBrowser):
DOMAIN = 'pluzz.fr'
ENCODING = 'ISO-8859-1'
PAGES = {r'http://[w\.]*pluzz.fr/replay/1': IndexPage,
r'http://[w\.]*pluzz.fr/recherche.html.*': IndexPage,
r'http://[w\.]*pluzz.fr/[-\w]+/.*': IndexPage,
r'http://[w\.]*pluzz.fr/((?!recherche).+)\.html': VideoPage,
DOMAIN = 'pluzz.francetv.fr'
PAGES = {r'http://[w\.]*pluzz.francetv.fr/replay/1': IndexPage,
r'http://[w\.]*pluzz.francetv.fr/recherche.*': IndexPage,
r'http://[w\.]*pluzz.francetv.fr/videos/(.+).html': VideoPage,
}
@id2url(PluzzVideo.id2url)
@ -56,10 +54,10 @@ class PluzzBrowser(BaseBrowser):
return video
def home(self):
self.location('/replay/1')
self.search_videos('')
def search_videos(self, pattern):
self.location(self.buildurl('/recherche.html', q=pattern.encode('utf-8')))
self.location(self.buildurl('/recherche', recherche=pattern.encode('utf-8')))
assert self.is_on_page(IndexPage)
return self.page.iter_videos()
@ -75,19 +73,19 @@ class PluzzBrowser(BaseBrowser):
root = etree.XML(data, parser)
assert root.tag == 'oeuvre'
video.title = root.findtext('titre')
video.title = unicode(root.findtext('titre'))
hours, minutes, seconds = root.findtext('duree').split(':')
video.duration = datetime.timedelta(hours=int(hours), minutes=int(minutes), seconds=int(seconds))
for vid in root.find('videos'):
if vid.findtext('statut') == 'ONLINE' and vid.findtext('format') == 'wmv':
video.url = vid.findtext('url')
video.url = unicode(vid.findtext('url'))
date = root.findtext('diffusions/diffusion')
if date:
video.date = datetime.datetime.strptime(date, '%d/%m/%Y %H:%M')
video.description = root.findtext('synopsis')
video.description = unicode(root.findtext('synopsis'))
return video

34
modules/francetelevisions/pages.py
View file

@ -19,6 +19,7 @@
import datetime
import re
from dateutil.parser import parse as parse_dt
from weboob.capabilities import UserError
from weboob.tools.capabilities.thumbnail import Thumbnail
@ -33,35 +34,22 @@ __all__ = ['IndexPage', 'VideoPage']
class IndexPage(BasePage):
def iter_videos(self):
for div in self.parser.select(self.document.getroot(), 'li.vignette'):
title = self.parser.select(div, 'h4 a', 1)
for div in self.parser.select(self.document.getroot(), 'article.rs-cell'):
title = self.parser.select(div, 'h3 a', 1)
url = title.attrib['href']
m = re.match('^http://www.pluzz.fr/([^/]+)\.html$', url)
m = re.match('^http://pluzz.francetv.fr/videos/(.+).html$', url)
if not m:
self.logger.debug('url %s does not match' % url)
continue
_id = m.group(1)
video = PluzzVideo(_id)
m = re.match('^(.+) - ([0-2][0-9])h([0-5][0-9])$', title.text)
if m:
video.title = m.group(1)
hour = int(m.group(2))
minute = int(m.group(3))
else:
video.title = title.text
hour = 0
minute = 0
video.title = unicode(title.text.strip())
video.date = parse_dt(div.find('span').attrib['data-date'])
t = map(int, div.xpath('.//a[@class="rs-genre-temps"]')[0].text.split('|')[1].strip().split(':'))
video.duration = datetime.timedelta(hours=t[0], minutes=t[1])
m = re.match('(\d+)/(\d+)/(\d+)', self.parser.select(div, 'p.date', 1).text)
if m:
video.date = datetime.datetime(int(m.group(3)),
int(m.group(2)),
int(m.group(1)),
hour,
minute)
url = self.parser.select(div, 'img.illustration', 1).attrib['src']
video.thumbnail = Thumbnail(u'http://www.pluzz.fr/%s' % url)
url = self.parser.select(div, 'figure.rs-cell-image img', 1).attrib['src']
video.thumbnail = Thumbnail(url)
yield video
@ -82,7 +70,7 @@ class VideoPage(BasePage):
'^%s(\d+)$' % re.escape('http://info.francetelevisions.fr/?id-video='),
div.attrib['href'])
if m:
return r'http://www.pluzz.fr/appftv/webservices/video/getInfosOeuvre.php?mode=zeri&id-diffusion=%s' % m.group(1)
return r'http://pluzz.francetv.fr/appftv/webservices/video/getInfosOeuvre.php?mode=zeri&id-diffusion=%s' % m.group(1)
def get_id(self):
return self.groups[0]

2
modules/francetelevisions/video.py
View file

@ -31,4 +31,4 @@ class PluzzVideo(BaseVideo):
@classmethod
def id2url(cls, _id):
return 'http://www.pluzz.fr/%s.html' % _id
return 'http://pluzz.francetv.fr/videos/%s.html' % _id