1
0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-20 05:38:46 +08:00

[franceculture] improve extractor

This commit is contained in:
flatgreen 2015-12-27 15:30:45 +01:00
parent 607d65fbce
commit bd7b1dd250
2 changed files with 52 additions and 5 deletions

View File

@ -198,7 +198,10 @@ from .fourtube import FourTubeIE
from .foxgay import FoxgayIE
from .foxnews import FoxNewsIE
from .foxsports import FoxSportsIE
from .franceculture import FranceCultureIE
from .franceculture import (
FranceCultureIE,
FranceCultureUrlIE,
)
from .franceinter import FranceInterIE
from .francetv import (
PluzzIE,

View File

@ -1,6 +1,8 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
@ -22,14 +24,14 @@ class FranceCultureIE(InfoExtractor):
'alt_title': 'Carnet nomade | 13-14',
'vcodec': 'none',
'upload_date': '20140301',
'thumbnail': r're:^http://www\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$',
'description': 'startswith:Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche des « geeks », une enquête menée aux Etats',
'thumbnail': r're:^http://static\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$',
'description': 'startswith:Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche',
'timestamp': 1393700400,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
def _extract_infos_from_player(self, url, video_id):
webpage = self._download_webpage(url, video_id)
video_path = self._search_regex(
@ -42,6 +44,9 @@ class FranceCultureIE(InfoExtractor):
r'<a id="player".*?>\s+<img src="([^"]+)"',
webpage, 'thumbnail', fatal=False)
display_id = self._search_regex(
r'<span class="path-diffusion">emission-(.*?)</span>', webpage, 'display_id')
title = self._html_search_regex(
r'<span class="title-diffusion">(.*?)</span>', webpage, 'title')
alt_title = self._html_search_regex(
@ -66,4 +71,43 @@ class FranceCultureIE(InfoExtractor):
'alt_title': alt_title,
'thumbnail': thumbnail,
'description': description,
'display_id': display_id
}
def _real_extract(self, url):
video_id = self._match_id(url)
return self._extract_infos_from_player(url, video_id)
class FranceCultureUrlIE(FranceCultureIE):
_VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emission-(?P<id>[^?#]+)'
_TEST = {
'url': 'http://www.franceculture.fr/emission-les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13',
'info_dict': {
'title': 'Jean-Gabriel Périot, cinéaste',
'alt_title': 'Les Carnets de la création',
'id': '5093239',
'display_id': 'les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13',
'ext': 'mp3',
'timestamp': 1444762500,
'upload_date': '20151013',
'description': 'startswith:Aujourd\'hui dans "Les carnets de la création", le cinéaste',
}
}
# dl url
# find : <a class="rf-player-open" href="/player/reecouter?play=5093239"><img ...></a>
# extract '/player/reecouter?play=5093239' join to url base of franceculture
# extract mp3 with FranceCultureIE _extract_infos_from_player
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_path = self._html_search_regex(
r'<a class="rf-player-open".*?href="([^"]+)"', webpage, 'video path','no_path_player')
if video_path == 'no_path_player':
self.to_screen('no player : no sound in this page.')
return None
new_id = re.search('play=(?P<id>[0-9]+)', video_path).group('id')
video_url = compat_urlparse.urljoin(url, video_path)
return self._extract_infos_from_player(video_url, new_id)