X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;ds=inline;f=youtube_dl%2Fextractor%2Ffrancetv.py;h=ad85bc16d7796cfcf42331a05bb0392e773f70c5;hb=8d0bdeba18962688f1fadfc246c69da5ad17a237;hp=b1530e54964530157ce22476b0ee7d5f49f48143;hpb=2de957c7e10763dbed5729254e045c06c30562d1;p=youtube-dl.git
diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py
index b1530e549..ad85bc16d 100644
--- a/youtube_dl/extractor/francetv.py
+++ b/youtube_dl/extractor/francetv.py
@@ -1,6 +1,5 @@
# encoding: utf-8
import re
-import xml.etree.ElementTree
import json
from .common import InfoExtractor
@@ -11,11 +10,10 @@ from ..utils import (
class FranceTVBaseInfoExtractor(InfoExtractor):
def _extract_video(self, video_id):
- xml_desc = self._download_webpage(
+ info = self._download_xml(
'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')
@@ -23,7 +21,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
thumbnail_path = info.find('image').text
return {'id': video_id,
- 'ext': 'mp4',
+ 'ext': 'flv' if video_url.startswith('rtmp') else 'mp4',
'url': video_url,
'title': info.find('titre').text,
'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path),
@@ -47,7 +45,7 @@ class PluzzIE(FranceTVBaseInfoExtractor):
class FranceTvInfoIE(FranceTVBaseInfoExtractor):
IE_NAME = u'francetvinfo.fr'
- _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P
.+).html'
+ _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P.+)\.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',
@@ -68,30 +66,108 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
return self._extract_video(video_id)
-class France2IE(FranceTVBaseInfoExtractor):
- IE_NAME = u'france2.fr'
- _VALID_URL = r'https?://www\.france2\.fr/emissions/.*?/videos/(?P\d+)'
-
- _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',
+class FranceTVIE(FranceTVBaseInfoExtractor):
+ IE_NAME = u'francetv'
+ IE_DESC = u'France 2, 3, 4, 5 and Ã'
+ _VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/
+ (?:
+ emissions/.*?/(videos|emissions)/(?P[^/?]+)
+ | (emissions?|jt)/(?P[^/?]+)
+ )'''
+
+ _TESTS = [
+ # france2
+ {
+ 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': {
+ # m3u8 download
+ u'skip_download': True,
+ },
},
- u'params': {
- u'skip_download': True,
+ # france3
+ {
+ u'url': u'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
+ u'info_dict': {
+ u'id': u'000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
+ u'ext': u'flv',
+ u'title': u'Le scandale du prix des médicaments',
+ u'description': u'md5:1384089fbee2f04fc6c9de025ee2e9ce',
+ },
+ u'params': {
+ # rtmp download
+ u'skip_download': True,
+ },
},
- }
+ # france4
+ {
+ u'url': u'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
+ u'info_dict': {
+ u'id': u'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
+ u'ext': u'flv',
+ u'title': u'Hero Corp Making of - Extrait 1',
+ u'description': u'md5:c87d54871b1790679aec1197e73d650a',
+ },
+ u'params': {
+ # rtmp download
+ u'skip_download': True,
+ },
+ },
+ # france5
+ {
+ u'url': u'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
+ u'info_dict': {
+ u'id': u'92837968',
+ u'ext': u'mp4',
+ u'title': u'C Ã dire ?!',
+ u'description': u'md5:fb1db1cbad784dcce7c7a7bd177c8e2f',
+ },
+ u'params': {
+ # m3u8 download
+ u'skip_download': True,
+ },
+ },
+ # franceo
+ {
+ u'url': u'http://www.franceo.fr/jt/info-afrique/04-12-2013',
+ u'info_dict': {
+ u'id': u'92327925',
+ u'ext': u'mp4',
+ u'title': u'Infô-Afrique',
+ u'description': u'md5:ebf346da789428841bee0fd2a935ea55',
+ },
+ u'params': {
+ # m3u8 download
+ u'skip_download': True,
+ },
+ u'skip': u'The id changes frequently',
+ },
+ ]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ if mobj.group('key'):
+ webpage = self._download_webpage(url, mobj.group('key'))
+ id_res = [
+ (r'''(?x)