mirror of https://github.com/yt-dlp/yt-dlp
Merge branch 'master' into subtitles_rework
commit
cf1dd0c59e
@ -0,0 +1,77 @@
|
||||
# encoding: utf-8
|
||||
import re
|
||||
import xml.etree.ElementTree
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
compat_urlparse,
|
||||
)
|
||||
|
||||
|
||||
class FranceTVBaseInfoExtractor(InfoExtractor):
|
||||
def _extract_video(self, video_id):
|
||||
xml_desc = self._download_webpage(
|
||||
'http://www.francetvinfo.fr/appftv/webservices/video/'
|
||||
'getInfosOeuvre.php?id-diffusion='
|
||||
+ video_id, video_id, 'Downloading XML config')
|
||||
info = xml.etree.ElementTree.fromstring(xml_desc.encode('utf-8'))
|
||||
|
||||
manifest_url = info.find('videos/video/url').text
|
||||
video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8')
|
||||
video_url = video_url.replace('/z/', '/i/')
|
||||
thumbnail_path = info.find('image').text
|
||||
|
||||
return {'id': video_id,
|
||||
'ext': 'mp4',
|
||||
'url': video_url,
|
||||
'title': info.find('titre').text,
|
||||
'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path),
|
||||
'description': info.find('synopsis').text,
|
||||
}
|
||||
|
||||
|
||||
class PluzzIE(FranceTVBaseInfoExtractor):
|
||||
IE_NAME = u'pluzz.francetv.fr'
|
||||
_VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://pluzz.francetv.fr/videos/allo_rufo_saison5_,88439064.html',
|
||||
u'file': u'88439064.mp4',
|
||||
u'info_dict': {
|
||||
u'title': u'Allô Rufo',
|
||||
u'description': u'md5:d909f1ebdf963814b65772aea250400e',
|
||||
},
|
||||
u'params': {
|
||||
u'skip_download': True,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
title = re.match(self._VALID_URL, url).group(1)
|
||||
webpage = self._download_webpage(url, title)
|
||||
video_id = self._search_regex(
|
||||
r'data-diffusion="(\d+)"', webpage, 'ID')
|
||||
return self._extract_video(video_id)
|
||||
|
||||
|
||||
class FranceTvInfoIE(FranceTVBaseInfoExtractor):
|
||||
IE_NAME = u'francetvinfo.fr'
|
||||
_VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+).html'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
|
||||
u'file': u'84981923.mp4',
|
||||
u'info_dict': {
|
||||
u'title': u'Soir 3',
|
||||
},
|
||||
u'params': {
|
||||
u'skip_download': True,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
page_title = mobj.group('title')
|
||||
webpage = self._download_webpage(url, page_title)
|
||||
video_id = self._search_regex(r'id-video=(\d+?)"', webpage, u'video id')
|
||||
return self._extract_video(video_id)
|
@ -0,0 +1,47 @@
|
||||
import re
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
compat_urlparse,
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
|
||||
class SlideshareIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.slideshare\.net/[^/]+?/(?P<title>.+?)($|\?)'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://www.slideshare.net/Dataversity/keynote-presentation-managing-scale-and-complexity',
|
||||
u'file': u'25665706.mp4',
|
||||
u'info_dict': {
|
||||
u'title': u'Managing Scale and Complexity',
|
||||
u'description': u'This was a keynote presentation at the NoSQL Now! 2013 Conference & Expo (http://www.nosqlnow.com). This presentation was given by Adrian Cockcroft from Netflix',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
page_title = mobj.group('title')
|
||||
webpage = self._download_webpage(url, page_title)
|
||||
slideshare_obj = self._search_regex(
|
||||
r'var slideshare_object = ({.*?}); var user_info =',
|
||||
webpage, u'slideshare object')
|
||||
info = json.loads(slideshare_obj)
|
||||
if info['slideshow']['type'] != u'video':
|
||||
raise ExtractorError(u'Webpage type is "%s": only video extraction is supported for Slideshare' % info['slideshow']['type'], expected=True)
|
||||
|
||||
doc = info['doc']
|
||||
bucket = info['jsplayer']['video_bucket']
|
||||
ext = info['jsplayer']['video_extension']
|
||||
video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext)
|
||||
|
||||
return {
|
||||
'_type': 'video',
|
||||
'id': info['slideshow']['id'],
|
||||
'title': info['slideshow']['title'],
|
||||
'ext': ext,
|
||||
'url': video_url,
|
||||
'thumbnail': info['slideshow']['pin_image_url'],
|
||||
'description': self._og_search_description(webpage),
|
||||
}
|
@ -1,2 +1,2 @@
|
||||
|
||||
__version__ = '2013.09.06.1'
|
||||
__version__ = '2013.11.09'
|
||||
|
Loading…
Reference in New Issue