[franceculture] Rewrite for new HTML scheme (Fixes #4853)
parent
4c1a017e69
commit
23d9ded655
2 changed files with 42 additions and 40 deletions
@ -1,77 +1,69 @@ |
|||||||
# coding: utf-8 |
# coding: utf-8 |
||||||
from __future__ import unicode_literals |
from __future__ import unicode_literals |
||||||
|
|
||||||
import json |
|
||||||
import re |
|
||||||
|
|
||||||
from .common import InfoExtractor |
from .common import InfoExtractor |
||||||
from ..compat import ( |
from ..compat import ( |
||||||
compat_parse_qs, |
|
||||||
compat_urlparse, |
compat_urlparse, |
||||||
) |
) |
||||||
|
from ..utils import ( |
||||||
|
determine_ext, |
||||||
|
int_or_none, |
||||||
|
) |
||||||
|
|
||||||
|
|
||||||
class FranceCultureIE(InfoExtractor): |
class FranceCultureIE(InfoExtractor): |
||||||
_VALID_URL = r'(?P<baseurl>http://(?:www\.)?franceculture\.fr/)player/reecouter\?play=(?P<id>[0-9]+)' |
_VALID_URL = r'https?://(?:www\.)?franceculture\.fr/player/reecouter\?play=(?P<id>[0-9]+)' |
||||||
_TEST = { |
_TEST = { |
||||||
'url': 'http://www.franceculture.fr/player/reecouter?play=4795174', |
'url': 'http://www.franceculture.fr/player/reecouter?play=4795174', |
||||||
'info_dict': { |
'info_dict': { |
||||||
'id': '4795174', |
'id': '4795174', |
||||||
'ext': 'mp3', |
'ext': 'mp3', |
||||||
'title': 'Rendez-vous au pays des geeks', |
'title': 'Rendez-vous au pays des geeks', |
||||||
|
'alt_title': 'Carnet nomade | 13-14', |
||||||
'vcodec': 'none', |
'vcodec': 'none', |
||||||
'uploader': 'Colette Fellous', |
|
||||||
'upload_date': '20140301', |
'upload_date': '20140301', |
||||||
'duration': 3601, |
|
||||||
'thumbnail': r're:^http://www\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$', |
'thumbnail': r're:^http://www\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$', |
||||||
'description': 'Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche des « geeks », une enquête menée aux Etats-Unis dans la S ...', |
'description': 'startswith:Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche des « geeks », une enquête menée aux Etats', |
||||||
|
'timestamp': 1393700400, |
||||||
} |
} |
||||||
} |
} |
||||||
|
|
||||||
def _real_extract(self, url): |
def _real_extract(self, url): |
||||||
mobj = re.match(self._VALID_URL, url) |
video_id = self._match_id(url) |
||||||
video_id = mobj.group('id') |
|
||||||
baseurl = mobj.group('baseurl') |
|
||||||
|
|
||||||
webpage = self._download_webpage(url, video_id) |
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\?([^']+)' />", |
video_path = self._search_regex( |
||||||
webpage, 'parameter code') |
r'<a id="player".*?href="([^"]+)"', webpage, 'video path') |
||||||
params = compat_parse_qs(params_code) |
video_url = compat_urlparse.urljoin(url, video_path) |
||||||
video_url = compat_urlparse.urljoin(baseurl, params['urlAOD'][0]) |
timestamp = int_or_none(self._search_regex( |
||||||
|
r'<a id="player".*?data-date="([0-9]+)"', |
||||||
|
webpage, 'upload date', fatal=False)) |
||||||
|
thumbnail = self._search_regex( |
||||||
|
r'<a id="player".*?>\s+<img src="([^"]+)"', |
||||||
|
webpage, 'thumbnail', fatal=False) |
||||||
|
|
||||||
title = self._html_search_regex( |
title = self._html_search_regex( |
||||||
r'<h1 class="title[^"]+">(.+?)</h1>', webpage, 'title') |
r'<span class="title-diffusion">(.*?)</span>', webpage, 'title') |
||||||
uploader = self._html_search_regex( |
alt_title = self._html_search_regex( |
||||||
r'(?s)<div id="emission".*?<span class="author">(.*?)</span>', |
r'<span class="title">(.*?)</span>', |
||||||
webpage, 'uploader', fatal=False) |
webpage, 'alt_title', 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( |
description = self._html_search_regex( |
||||||
r'(?s)<p class="desc">(.*?)</p>', webpage, 'description') |
r'<span class="description">(.*?)</span>', |
||||||
|
webpage, 'description', fatal=False) |
||||||
|
|
||||||
info = json.loads(params['infoData'][0])[0] |
uploader = self._html_search_regex( |
||||||
duration = info.get('media_length') |
r'(?s)<div id="emission".*?<span class="author">(.*?)</span>', |
||||||
upload_date_candidate = info.get('media_section5') |
webpage, 'uploader', default=None) |
||||||
upload_date = ( |
vcodec = 'none' if determine_ext(video_url.lower()) == 'mp3' else None |
||||||
upload_date_candidate |
|
||||||
if (upload_date_candidate is not None and |
|
||||||
re.match(r'[0-9]{8}$', upload_date_candidate)) |
|
||||||
else None) |
|
||||||
|
|
||||||
return { |
return { |
||||||
'id': video_id, |
'id': video_id, |
||||||
'url': video_url, |
'url': video_url, |
||||||
'vcodec': 'none' if video_url.lower().endswith('.mp3') else None, |
'vcodec': vcodec, |
||||||
'duration': duration, |
|
||||||
'uploader': uploader, |
'uploader': uploader, |
||||||
'upload_date': upload_date, |
'timestamp': timestamp, |
||||||
'title': title, |
'title': title, |
||||||
|
'alt_title': alt_title, |
||||||
'thumbnail': thumbnail, |
'thumbnail': thumbnail, |
||||||
'description': description, |
'description': description, |
||||||
} |
} |
||||||
|
Loading…
Reference in new issue