[radiofrance] Modernize

pull/2617/head
Philipp Hagemeister 2014-03-23 17:43:33 +01:00
parent 38d63d846e
commit 51fb2e98d2
1 changed files with 19 additions and 15 deletions

View File

@ -1,4 +1,6 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -6,16 +8,17 @@ from .common import InfoExtractor
class RadioFranceIE(InfoExtractor): class RadioFranceIE(InfoExtractor):
_VALID_URL = r'^https?://maison\.radiofrance\.fr/radiovisions/(?P<id>[^?#]+)' _VALID_URL = r'^https?://maison\.radiofrance\.fr/radiovisions/(?P<id>[^?#]+)'
IE_NAME = u'radiofrance' IE_NAME = 'radiofrance'
_TEST = { _TEST = {
u'url': u'http://maison.radiofrance.fr/radiovisions/one-one', 'url': 'http://maison.radiofrance.fr/radiovisions/one-one',
u'file': u'one-one.ogg', 'md5': 'bdbb28ace95ed0e04faab32ba3160daf',
u'md5': u'bdbb28ace95ed0e04faab32ba3160daf', 'info_dict': {
u'info_dict': { 'id': 'one-one',
u"title": u"One to one", 'ext': 'ogg',
u"description": u"Plutôt que d'imaginer la radio de demain comme technologie ou comme création de contenu, je veux montrer que quelles que soient ses évolutions, j'ai l'intime conviction que la radio continuera d'être un grand média de proximité pour les auditeurs.", "title": "One to one",
u"uploader": u"Thomas Hercouët", "description": "Plutôt que d'imaginer la radio de demain comme technologie ou comme création de contenu, je veux montrer que quelles que soient ses évolutions, j'ai l'intime conviction que la radio continuera d'être un grand média de proximité pour les auditeurs.",
"uploader": "Thomas Hercouët",
}, },
} }
@ -24,27 +27,28 @@ class RadioFranceIE(InfoExtractor):
video_id = m.group('id') video_id = m.group('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, u'title') title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
description = self._html_search_regex( description = self._html_search_regex(
r'<div class="bloc_page_wrapper"><div class="text">(.*?)</div>', r'<div class="bloc_page_wrapper"><div class="text">(.*?)</div>',
webpage, u'description', fatal=False) webpage, 'description', fatal=False)
uploader = self._html_search_regex( uploader = self._html_search_regex(
r'<div class="credit">&nbsp;&nbsp;&copy;&nbsp;(.*?)</div>', r'<div class="credit">&nbsp;&nbsp;&copy;&nbsp;(.*?)</div>',
webpage, u'uploader', fatal=False) webpage, 'uploader', fatal=False)
formats_str = self._html_search_regex( formats_str = self._html_search_regex(
r'class="jp-jplayer[^"]*" data-source="([^"]+)">', r'class="jp-jplayer[^"]*" data-source="([^"]+)">',
webpage, u'audio URLs') webpage, 'audio URLs')
formats = [ formats = [
{ {
'format_id': fm[0], 'format_id': fm[0],
'url': fm[1], 'url': fm[1],
'vcodec': 'none', 'vcodec': 'none',
'preference': i,
} }
for fm in for i, fm in
re.findall(r"([a-z0-9]+)\s*:\s*'([^']+)'", formats_str) enumerate(re.findall(r"([a-z0-9]+)\s*:\s*'([^']+)'", formats_str))
] ]
# No sorting, we don't know any more about these formats self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,