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

Fix many CapVideo-related ConversionWarnings

Browse source
This commit is contained in:
Laurent Bachelier 2012-11-09 13:06:08 +01:00 • committed by Romain Bignon
commit 1f310a3d33
14 changed files with 23 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

6
modules/dailymotion/pages.py
View file

@ -45,7 +45,7 @@ class IndexPage(BasePage):
video = DailymotionVideo(_id)
video.title = unicode(self.parser.select(div, 'h3 a', 1).text).strip()
video.author = unicode(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() or unicode()
try:
parts = self.parser.select(div, 'div.duration', 1).text.split(':')
except BrokenPageError:
@ -68,7 +68,7 @@ class IndexPage(BasePage):
url = re.sub('\?\d+', '', url)
# use the bigger thumbnail
url = url.replace('jpeg_preview_medium.jpg', 'jpeg_preview_large.jpg')
video.thumbnail = Thumbnail(url)
video.thumbnail = Thumbnail(unicode(url))
rating_div = self.parser.select(div, 'div.small_stars', 1)
video.rating_max = self.get_rate(rating_div)
@ -95,7 +95,7 @@ class VideoPage(BasePage):
video.title = unicode(self.parser.select(div, 'span.title', 1).text).strip()
video.author = unicode(self.parser.select(div, 'a.name, span.name', 1).text).strip()
try:
video.description = html2text(self.parser.tostring(self.parser.select(div, 'div#video_description', 1))).strip()
video.description = html2text(self.parser.tostring(self.parser.select(div, 'div#video_description', 1))).strip() or unicode()
except BrokenPageError:
video.description = u''
for script in self.parser.select(self.document.getroot(), 'div.dmco_html'):

2
modules/ehentai/pages.py
View file

@ -96,7 +96,7 @@ class GalleryPage(BasePage):
thumbnail_style = self.document.xpath("//div[@class='gdtm']/div/attribute::style")[0]
thumbnail_url = re.search(r"background:[^;]+url\((.+?)\)", thumbnail_style).group(1)
gallery.thumbnail = Thumbnail(thumbnail_url)
gallery.thumbnail = Thumbnail(unicode(thumbnail_url))
def _prev_page_link(self):
try:

2
modules/francetelevisions/pages.py
View file

@ -61,7 +61,7 @@ class IndexPage(BasePage):
minute)
url = self.parser.select(div, 'img.illustration', 1).attrib['src']
video.thumbnail = Thumbnail('http://www.pluzz.fr/%s' % url)
video.thumbnail = Thumbnail(u'http://www.pluzz.fr/%s' % url)
yield video

2
modules/francetelevisions/video.py
View file

@ -27,7 +27,7 @@ __all__ = ['PluzzVideo']
class PluzzVideo(BaseVideo):
def __init__(self, *args, **kwargs):
BaseVideo.__init__(self, *args, **kwargs)
self.ext = 'wmv'
self.ext = u'wmv'
@classmethod
def id2url(cls, _id):

4
modules/ina/pages/search.py
View file

@ -44,9 +44,9 @@ class SearchPage(BasePage):
video = InaVideo('boutique.%s' % id)
video.thumbnail = Thumbnail('http://boutique.ina.fr%s' % li.find('a').find('img').attrib['src'])
video.thumbnail = Thumbnail(u'http://boutique.ina.fr%s' % li.find('a').find('img').attrib['src'])
video.title = self.parser.select(li, 'p.titre', 1).text
video.title = unicode(self.parser.select(li, 'p.titre', 1).text)
date = self.parser.select(li, 'p.date', 1).text
day, month, year = [int(s) for s in date.split('/')]

8
modules/ina/pages/video.py
View file

@ -60,7 +60,7 @@ class BaseVideoPage(BasePage):
qs = parse_qs(self.document.getroot().cssselect('param[name="flashvars"]')[0].attrib['value'])
s = self.browser.readurl('http://boutique.ina.fr/player/infovideo/id_notice/%s' % qs['id_notice'][0])
s = s[s.find('<Media>')+7:s.find('</Media>')]
return '%s/pkey/%s' % (s, qs['pkey'][0])
return u'%s/pkey/%s' % (s, qs['pkey'][0])
def parse_date_and_duration(self, text):
duration_regexp = re.compile('(.* - )?(.+) - ((.+)h)?((.+)min)?(.+)s')
@ -99,10 +99,10 @@ class VideoPage(BaseVideoPage):
def get_title(self):
qr = self.parser.select(self.document.getroot(), 'div.container-global-qr')[0].find('div').findall('div')[1]
return qr.find('h2').text.strip()
return unicode(qr.find('h2').text.strip())
def get_description(self):
return self.parser.select(self.document.getroot(), 'div.container-global-qr')[1].find('div').find('p').text.strip()
return unicode(self.parser.select(self.document.getroot(), 'div.container-global-qr')[1].find('div').find('p').text.strip())
class BoutiqueVideoPage(BaseVideoPage):
@ -114,7 +114,7 @@ class BoutiqueVideoPage(BaseVideoPage):
def get_description(self):
el = self.document.getroot().cssselect('div.bloc-produit-haut div.contenu p')[0]
if el is not None:
return el.text.strip()
return unicode(el.text.strip())
def get_date_and_duration(self):
el = self.document.getroot().cssselect('div.bloc-produit-haut p.date')[0]

2
modules/radiofrance/backend.py
View file

@ -193,7 +193,7 @@ class RadioFranceBackend(BaseBackend, ICapRadio, ICapCollection, ICapVideo):
def fill_video(self, video, fields):
if 'url' in fields:
with self.browser:
video.url = self.browser.get_url(video.id)
video.url = unicode(self.browser.get_url(video.id))
return video

2
modules/radiofrance/browser.py
View file

@ -40,7 +40,7 @@ class RadioFranceVideo(BaseVideo):
def __init__(self, *args, **kwargs):
BaseVideo.__init__(self, *args, **kwargs)
self.ext = 'mp3'
self.ext = u'mp3'
@classmethod
def id2url(cls, _id):

5
modules/youjizz/pages/index.py
View file

@ -23,6 +23,7 @@ import re
from weboob.tools.browser import BasePage, BrokenPageError
from weboob.tools.capabilities.thumbnail import Thumbnail
from weboob.tools.misc import to_unicode
from ..video import YoujizzVideo
@ -40,10 +41,10 @@ class IndexPage(BasePage):
video = YoujizzVideo(_id)
video.thumbnail = Thumbnail(span.find('.//img').attrib['src'])
video.thumbnail = Thumbnail(unicode(span.find('.//img').attrib['src']))
title_el = self.parser.select(span, 'span#title1', 1)
video.title = title_el.text.strip()
video.title = to_unicode(title_el.text.strip())
time_span = self.parser.select(span, 'span.thumbtime span', 1)
time_txt = time_span.text.strip().replace(';', ':')

2
modules/youjizz/pages/video.py
View file

@ -62,6 +62,6 @@ class VideoPage(BasePage):
elif len(video_file_urls) > 1:
raise BrokenPageError('Many video file URL found')
else:
video.url = video_file_urls[0]
video.url = to_unicode(video_file_urls[0])
return video

2
modules/youjizz/video.py
View file

@ -28,7 +28,7 @@ class YoujizzVideo(BaseVideo):
def __init__(self, *args, **kwargs):
BaseVideo.__init__(self, *args, **kwargs)
self.nsfw = True
self.ext = 'flv'
self.ext = u'flv'
@classmethod
def id2url(cls, _id):

2
modules/youporn/pages/video.py
View file

@ -52,7 +52,7 @@ class VideoPage(PornPage):
if m:
ext = m.group(1).lower()
else:
ext = 'flv'
ext = u'flv'
return unicode(a.attrib['href']), unicode(ext)
def get_title(self):

4
modules/youtube/backend.py
View file

@ -89,8 +89,8 @@ class YoutubeBackend(BaseBackend, ICapVideo, ICapCollection):
with self.browser:
url, ext = self.browser.get_video_url(player_url)
video.url = url
video.ext = ext
video.url = unicode(url)
video.ext = unicode(ext)
def get_video(self, _id):
m = self.URL_RE.match(_id)

2
weboob/tools/capabilities/thumbnail.py
View file

@ -33,7 +33,7 @@ class Thumbnail(CapBaseObject):
def __init__(self, url):
CapBaseObject.__init__(self, url)
self.url = url.replace(' ', '%20')
self.url = url.replace(u' ', u'%20')
def __str__(self):
return self.url