X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ffrancetv.py;h=66aa3aa0d081fedd285331b2f295b2a0814def95;hb=673d1273ff6f6d3267728fbe6f79c9c801598fd2;hp=6e11764704b9afbf1a25e33a62cee92a49b7a805;hpb=5d8afe69f7be840c6494333e84c46f0a1ca93147;p=youtube-dl
diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py
index 6e1176470..66aa3aa0d 100644
--- a/youtube_dl/extractor/francetv.py
+++ b/youtube_dl/extractor/francetv.py
@@ -1,6 +1,6 @@
# encoding: utf-8
import re
-import xml.etree.ElementTree
+import json
from .common import InfoExtractor
from ..utils import (
@@ -8,16 +8,50 @@ from ..utils import (
)
-class PluzzIE(InfoExtractor):
+class FranceTVBaseInfoExtractor(InfoExtractor):
+ def _extract_video(self, video_id):
+ info = self._download_xml(
+ 'http://www.francetvinfo.fr/appftv/webservices/video/'
+ 'getInfosOeuvre.php?id-diffusion='
+ + video_id, video_id, 'Downloading XML config')
+
+ 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'
+ # Can't use tests, videos expire in 7 days
+
+ 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
.+)\.html'
+
_TEST = {
- u'url': u'http://pluzz.francetv.fr/videos/allo_rufo_saison5_,88439064.html',
- u'file': u'88439064.mp4',
+ 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'Allô Rufo',
- u'description': u'md5:d909f1ebdf963814b65772aea250400e',
+ u'title': u'Soir 3',
},
u'params': {
u'skip_download': True,
@@ -25,26 +59,69 @@ class PluzzIE(InfoExtractor):
}
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')
+ 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)
- xml_desc = self._download_webpage(
- 'http://www.pluzz.fr/appftv/webservices/video/'
- 'getInfosOeuvre.php?id-diffusion='
- + video_id, title, '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
+class France2IE(FranceTVBaseInfoExtractor):
+ IE_NAME = u'france2.fr'
+ _VALID_URL = r'''(?x)https?://www\.france2\.fr/
+ (?:
+ emissions/.*?/videos/(?P\d+)
+ | emission/(?P[^/?]+)
+ )'''
- return {'id': video_id,
- 'ext': 'mp4',
- 'url': video_url,
- 'title': info.find('titre').text,
- 'thumbnail': compat_urlparse.urljoin(url, thumbnail_path),
- 'description': info.find('synopsis').text,
- }
+ _TEST = {
+ u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
+ u'file': u'75540104.mp4',
+ u'info_dict': {
+ u'title': u'13h15, le samedi...',
+ u'description': u'md5:2e5b58ba7a2d3692b35c792be081a03d',
+ },
+ u'params': {
+ u'skip_download': True,
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj.group('key'):
+ webpage = self._download_webpage(url, mobj.group('key'))
+ video_id = self._html_search_regex(
+ r'''(?x)\s*
+
''',
+ webpage, u'video ID')
+ else:
+ video_id = mobj.group('id')
+ return self._extract_video(video_id)
+
+
+class GenerationQuoiIE(InfoExtractor):
+ IE_NAME = u'france2.fr:generation-quoi'
+ _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P.*)(\?|$)'
+
+ _TEST = {
+ u'url': u'http://generation-quoi.france2.fr/portrait/garde-a-vous',
+ u'file': u'k7FJX8VBcvvLmX4wA5Q.mp4',
+ u'info_dict': {
+ u'title': u'Génération Quoi - Garde à Vous',
+ u'uploader': u'Génération Quoi',
+ },
+ u'params': {
+ # It uses Dailymotion
+ u'skip_download': True,
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ name = mobj.group('name')
+ info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % name)
+ info_json = self._download_webpage(info_url, name)
+ info = json.loads(info_json)
+ return self.url_result('http://www.dailymotion.com/video/%s' % info['id'],
+ ie='Dailymotion')