[franceculture] Add extractor (Fixes #2669)

This commit is contained in:
Philipp Hagemeister 2014-04-03 08:55:38 +02:00
parent b6cfde99b7
commit cce929eaac
3 changed files with 79 additions and 1 deletions

View File

@ -743,7 +743,7 @@ class YoutubeDL(object):
) )
# Automatically determine file extension if missing # Automatically determine file extension if missing
if 'ext' not in format: if 'ext' not in format:
format['ext'] = determine_ext(format['url']) format['ext'] = determine_ext(format['url']).lower()
format_limit = self.params.get('format_limit', None) format_limit = self.params.get('format_limit', None)
if format_limit: if format_limit:

View File

@ -83,6 +83,7 @@ from .fktv import (
) )
from .flickr import FlickrIE from .flickr import FlickrIE
from .fourtube import FourTubeIE from .fourtube import FourTubeIE
from .franceculture import FranceCultureIE
from .franceinter import FranceInterIE from .franceinter import FranceInterIE
from .francetv import ( from .francetv import (
PluzzIE, PluzzIE,

View File

@ -0,0 +1,77 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import (
compat_parse_qs,
compat_urlparse,
)
class FranceCultureIE(InfoExtractor):
_VALID_URL = r'(?P<baseurl>http://(?:www\.)?franceculture\.fr/)player/reecouter\?play=(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.franceculture.fr/player/reecouter?play=4795174',
'info_dict': {
'id': '4795174',
'ext': 'mp3',
'title': 'Rendez-vous au pays des geeks',
'vcodec': 'none',
'uploader': 'Colette Fellous',
'upload_date': '20140301',
'duration': 3601,
'thumbnail': r're:^http://www\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$',
'description': 'Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche des « geeks », une enquête menée aux Etats-Unis dans la S ...',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
baseurl = mobj.group('baseurl')
webpage = self._download_webpage(url, video_id)
params_code = self._search_regex(
r"<param name='movie' value='/sites/all/modules/rf/rf_player/swf/loader.swf\?([^']+)' />",
webpage, 'parameter code')
params = compat_parse_qs(params_code)
video_url = compat_urlparse.urljoin(baseurl, params['urlAOD'][0])
title = self._html_search_regex(
r'<h1 class="title[^"]+">(.+?)</h1>', webpage, 'title')
uploader = self._html_search_regex(
r'(?s)<div id="emission".*?<span class="author">(.*?)</span>',
webpage, 'uploader', fatal=False)
thumbnail_part = self._html_search_regex(
r'(?s)<div id="emission".*?<img src="([^"]+)"', webpage,
'thumbnail', fatal=False)
if thumbnail_part is None:
thumbnail = None
else:
thumbnail = compat_urlparse.urljoin(baseurl, thumbnail_part)
description = self._html_search_regex(
r'(?s)<p class="desc">(.*?)</p>', webpage, 'description')
info = json.loads(params['infoData'][0])[0]
duration = info.get('media_length')
upload_date_candidate = info.get('media_section5')
upload_date = (
upload_date_candidate
if (upload_date_candidate is not None and
re.match(r'[0-9]{8}$', upload_date_candidate))
else None)
return {
'id': video_id,
'url': video_url,
'vcodec': 'none' if video_url.lower().endswith('.mp3') else None,
'duration': duration,
'uploader': uploader,
'upload_date': upload_date,
'title': title,
'thumbnail': thumbnail,
'description': description,
}