def obj_thumbnail(self):
url = Dict('VTU/IUR', default=NotAvailable)(self)
if empty(url):
return url
thumbnail = Thumbnail(url)
thumbnail.url = thumbnail.id
return thumbnail
def iter_videos(self):
# When no results are found, the website returns random results
sb = self.parser.select(self.document.getroot(), 'div.search form input.searchbox', 1)
if sb.value == 'No Results Found':
return
#Extracting meta data from results page
vidbackdrop_list = self.parser.select(self.document.getroot(), 'div.vidBackdrop ')
for vidbackdrop in vidbackdrop_list:
url = self.parser.select(vidbackdrop, 'a', 1).attrib['href']
_id = url[2:]
video = CappedVideo(_id)
video.set_empty_fields(NotAvailable, ('url',))
video.title = to_unicode(self.parser.select(vidbackdrop, 'div.vidTitle a', 1).text)
video.author = to_unicode(self.parser.select(vidbackdrop, 'div.vidAuthor a', 1).text)
thumbnail_url = 'http://cdn.capped.tv/pre/%s.png' % _id
video.thumbnail = Thumbnail(thumbnail_url)
video.thumbnail.url = to_unicode(video.thumbnail.id)
#we get the description field
duration_tmp = self.parser.select(vidbackdrop, 'div.vidInfo', 1)
#we remove tabs and spaces
duration_tmp2 = duration_tmp.text[7:]
#we remove all fields exept time
duration_tmp3 = duration_tmp2.split(' ')[0]
#we transform it in datetime format
parts = duration_tmp3.split(':')
if len(parts) == 1:
hours = minutes = 0
seconds = parts[0]
elif len(parts) == 2:
hours = 0
minutes, seconds = parts
elif len(parts) == 3:
hours, minutes, seconds = parts
else:
raise BrokenPageError('Unable to parse duration %r' % duration_tmp)
video.duration = datetime.timedelta(hours=int(hours), minutes=int(minutes), seconds=int(seconds))
yield video
def parse_video(self, el, video=None):
_id = el.find('ID').text
if _id == '-1':
# means the video is not found
return None
if not video:
video = CanalplusVideo(_id)
infos = el.find('INFOS')
video.title = u''
for part in infos.find('TITRAGE'):
if len(part.text.strip()) == 0:
continue
if len(video.title) > 0:
video.title += u' — '
video.title += part.text.strip()
video.description = infos.find('DESCRIPTION').text
media = el.find('MEDIA')
url = media.find('IMAGES').find('PETIT').text
if url:
video.thumbnail = Thumbnail(url)
video.thumbnail.url = video.thumbnail.id
else:
video.thumbnail = NotAvailable
for format in media.find('VIDEOS'):
if format.text is None:
continue
if format.tag == 'HLS':
video.ext = u'm3u8'
video.url = format.text
break
day, month, year = map(
int,
infos.find('PUBLICATION').find('DATE').text.split('/'))
hour, minute, second = map(
int,
infos.find('PUBLICATION').find('HEURE').text.split(':'))
video.date = datetime(year, month, day, hour, minute, second)
return video
def iter_videos(self):
for span in self.document.xpath('//ul[@id="list"]/li'):
a = self.parser.select(span, 'a', 1)
url = a.attrib['href']
_id = re.sub(r'/showvideo/(\d+)/.*', r'\1', url)
video = JacquieEtMichelVideo(_id)
url = span.find('.//img').attrib['src']
video.thumbnail = Thumbnail(url)
video.thumbnail.url = video.thumbnail.id
title_el = self.parser.select(span, 'h2', 1)
video.title = to_unicode(title_el.text.strip())
video.description = self.parser.tocleanstring(
span.xpath('.//div[@class="desc"]')[0])
video.set_empty_fields(NotAvailable, ('url,'))
yield video
def iter_videos(self):
for a in self.parser.select(
self.document.getroot(),
'section.conference ul.media_items li.featured a.session_item'
):
href = a.attrib.get('href', '')
# print href
m = re.match('/play/(\d+)/.*', href)
if not m:
continue
# print m.group(1)
video = GDCVaultVideo(m.group(1))
# get title
try:
video.title = unicode(
self.parser.select(a, 'div.conference_info p strong',
1).text)
except IndexError:
video.title = NotAvailable
# get description
try:
video.description = unicode(
self.parser.select(a, 'div.conference_info p', 1).text)
except IndexError:
video.description = NotAvailable
# get thumbnail
img = self.parser.select(a, 'div.featured_image img', 1)
if img is not None:
video.thumbnail = Thumbnail(img.attrib['src'])
video.thumbnail.url = video.thumbnail.id
else:
video.thumbnail = NotAvailable
#m = re.match('id-(\d+)', a.attrib.get('class', ''))
#if not m:
# continue
# FIXME
yield video
def fill_gallery(self, gallery):
gallery.title = self.document.xpath("//h1[@id='gn']/text()")[0]
cardinality_string = self.document.xpath("//div[@id='gdd']//tr[td[@class='gdt1']/text()='Length:']/td[@class='gdt2']/text()")[0]
gallery.cardinality = int(re.match(r"\d+", cardinality_string).group(0))
date_string = self.document.xpath("//div[@id='gdd']//tr[td[@class='gdt1']/text()='Posted:']/td[@class='gdt2']/text()")[0]
gallery.date = datetime.strptime(date_string, "%Y-%m-%d %H:%M")
rating_string = self.document.xpath("//td[@id='rating_label']/text()")[0]
rating_match = re.search(r"\d+\.\d+", rating_string)
if rating_match is None:
gallery.rating = None
else:
gallery.rating = float(rating_match.group(0))
gallery.rating_max = 5
try:
thumbnail_url = self.document.xpath("//div[@class='gdtm']/a/img/attribute::src")[0]
except IndexError:
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)
def iter_videos(self):
for div in self.parser.select(self.document.getroot(),
'li#contentsearch'):
title = self.parser.select(div, '#titlesearch span', 1)
a = self.parser.select(div, 'a', 1)
url = a.attrib['href']
m = re.match('/video-(.*)', url)
if not m:
self.logger.debug('url %s does not match' % url)
continue
_id = m.group(1)
video = TricTracTVVideo(_id)
video.title = unicode(title.text)
url = self.parser.select(div, 'img', 1).attrib['src']
stars = self.parser.select(div, '.etoile_on')
video.rating = len(stars)
video.rating_max = 5
video.thumbnail = Thumbnail('http://www.trictrac.tv/%s' % url)
video.thumbnail.url = video.thumbnail.id
yield video
def video_info(url):
"""Fetch info about a video using youtube-dl
:param url: URL of the web page containing the video
:rtype: :class:`weboob.capabilities.video.Video`
"""
if not MediaPlayer._find_in_path(os.environ['PATH'], 'youtube-dl'):
raise Exception('Please install youtube-dl')
try:
j = json.loads(
subprocess.check_output(['youtube-dl', '-f', 'best', '-J', url]))
except subprocess.CalledProcessError:
return
v = BaseVideo(id=url)
v.title = unicode(j.get('title')) if j.get('title') else NotAvailable
v.ext = unicode(j.get('ext')) if j.get('ext') else NotAvailable
v.description = unicode(
j.get('description')) if j.get('description') else NotAvailable
v.url = unicode(j['url'])
v.duration = timedelta(
seconds=j.get('duration')) if j.get('duration') else NotAvailable
v.author = unicode(
j.get('uploader')) if j.get('uploader') else NotAvailable
v.rating = j.get('average_rating') or NotAvailable
if j.get('thumbnail'):
v.thumbnail = Thumbnail(unicode(j['thumbnail']))
d = j.get('upload_date', j.get('release_date'))
if d:
v.date = parse_date(d)
return v
def obj_thumbnail(self):
thumbnail_url = Attr('.//img', 'data-original')(self)
thumbnail = Thumbnail(thumbnail_url)
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
url = Attr('a/img[@class="resultat-vignette"]', 'data-src')(self)
thumbnail = Thumbnail(url)
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
url = CleanText('./a/img/@src')(self)
thumbnail = Thumbnail(url)
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
t = CleanText('./thumbnails/thumbnail[1]', default='')(self)
if t:
thumbnail = Thumbnail(t)
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
thumbnail = Thumbnail(self.xpath('./a/div/img')[0].attrib['src'])
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
url = CleanText('./div/a/img/@data-src')(self)
thumbnail = Thumbnail(url)
thumbnail.url = url
return thumbnail
def obj_thumbnail(self):
thumbnail = Thumbnail(
self.xpath('.//img')[0].attrib['data-original'])
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
thumbnail = Thumbnail(
self.xpath('.//img')[0].attrib['data-original'])
thumbnail.url = thumbnail.id.replace('http://', 'https://')
return thumbnail
def obj_thumbnail(self):
t = CleanText('./thumbnails/thumbnail[1]', default='')(self)
if t:
thumbnail = Thumbnail(t)
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
url = CleanText('.//div[@class="article-primary "]/div[has-class("field-thumbnail")]/span/noscript/img/@src')(self)
thumbnail = Thumbnail(url)
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
thumbnail = Thumbnail(CleanText('//image[1]/url')(self))
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
if 'path_img_emission' in self.el:
thumbnail = Thumbnail(Dict('path_img_emission')(self))
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
thumbnail = Thumbnail(Dict('clip/pictures/sizes/0/link')(self))
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
try:
return Thumbnail(next(img['url'] for img in self.el['images'] if img['format'] == 'landscape'))
except StopIteration:
return NotAvailable
def obj_thumbnail(self):
url = Format('http://www.francetv.fr%s', Dict['image'])(self)
thumbnail = Thumbnail(url)
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
url = CleanText('.//div[@class="article-primary "]/div[has-class("field-thumbnail")]/span/noscript/img/@src')(self)
thumbnail = Thumbnail(url)
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
url = NormalizeThumbnail(CleanText('/html/head/meta[@property="og:image"]/@content'))(self)
if url:
thumbnail = Thumbnail(url)
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
thumbnail = Thumbnail(Dict('thumbnailUrl')(self.el))
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
thumbnail = Thumbnail(Dict('clip/pictures/sizes/0/link')(self))
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
url = CleanText('//meta[@property="og:image"]/@content')(self)
thumbnail = Thumbnail(url)
thumbnail.url = url
return thumbnail
def obj_thumbnail(self):
thumbnail = Thumbnail(CleanText('//image[1]/url')(self))
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
url = CleanText('div/div/a/figure/span/span/@data-src')(self)
thumbnail = Thumbnail(url)
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
thumbnail_url = Attr('./img', 'src')(self)
thumbnail = Thumbnail(thumbnail_url)
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
if 'path_img_emission' in self.el:
thumbnail = Thumbnail(Dict('path_img_emission')(self))
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
thumbnail = Thumbnail(self.xpath('.//img')[0].attrib['data-original'])
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
url = CleanText('//meta[@property="og:image"]/@content')(self)
thumbnail = Thumbnail(url)
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
url = Attr('a/img[@class="resultat-vignette"]',
'data-src')(self)
thumbnail = Thumbnail(url)
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
url = Dict('VTU/IUR')(self)
thumbnail = Thumbnail(url)
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
path = Attr('./a[has-class("thumbnail")]/img', 'src', default=None)(self)
if path is None:
raise SkipItem('not an image thread')
return Thumbnail(urljoin(self.page.url, path))
def obj_thumbnail(self):
thumbnail = Thumbnail(self.xpath('.//img')[0].attrib['data-original'])
thumbnail.url = thumbnail.id.replace('http://', 'https://')
return thumbnail
def obj_thumbnail(self):
thumbnail_url = Attr('./img', 'src')(self)
thumbnail = Thumbnail(thumbnail_url)
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
thumbnail_url = Attr('.//img', 'data-original')(self)
thumbnail = Thumbnail(thumbnail_url)
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
thumbnail = Thumbnail(Dict('thumbnailUrl')(self.el))
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
url = Format('http://www.francetv.fr%s', Dict['image'])(self)
thumbnail = Thumbnail(url)
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
thumbnail = Thumbnail(
self.xpath('./a/div/img')[0].attrib['src'])
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
return Thumbnail(Attr('.//img[@class="thumb-image-container__image"]', 'src')(self))
def obj_thumbnail(self):
url = CleanText('./div/a/img/@data-src')(self)
thumbnail = Thumbnail(url)
thumbnail.url = url
return thumbnail
def obj_thumbnail(self):
return Thumbnail(Attr('.//img[@class="thumb"]', 'src')(self))
def obj_thumbnail(self):
url = CleanText('./a/img/@src')(self)
thumbnail = Thumbnail(url)
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
thumbnail = Thumbnail(Attr('.//img[has-class("js-videoThumb")]', 'data-path')(self).replace('{index}', '1'))
thumbnail.url = thumbnail.id
return thumbnail
def obj_thumbnail(self):
url = CleanText('div/div/a/figure/span/span/@data-src')(self)
thumbnail = Thumbnail(url)
thumbnail.url = thumbnail.id
return thumbnail
