Merge 72db217289 into a084c80f7b
Olivier Trichet
2 months ago
committed by
GitHub
commit
332493dda6
@ -1,73 +0,0 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
extract_attributes,
|
||||
int_or_none,
|
||||
)
|
||||
|
||||
|
||||
class FranceCultureIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emissions/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.franceculture.fr/emissions/carnet-nomade/rendez-vous-au-pays-des-geeks',
|
||||
'info_dict': {
|
||||
'id': 'rendez-vous-au-pays-des-geeks',
|
||||
'display_id': 'rendez-vous-au-pays-des-geeks',
|
||||
'ext': 'mp3',
|
||||
'title': 'Rendez-vous au pays des geeks',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'upload_date': '20140301',
|
||||
'timestamp': 1393700400,
|
||||
'vcodec': 'none',
|
||||
}
|
||||
}, {
|
||||
# no thumbnail
|
||||
'url': 'https://www.franceculture.fr/emissions/la-recherche-montre-en-main/la-recherche-montre-en-main-du-mercredi-10-octobre-2018',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
video_data = extract_attributes(self._search_regex(
|
||||
r'''(?sx)
|
||||
(?:
|
||||
</h1>|
|
||||
<div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*>
|
||||
).*?
|
||||
(<button[^>]+data-(?:url|asset-source)="[^"]+"[^>]+>)
|
||||
''',
|
||||
webpage, 'video data'))
|
||||
|
||||
video_url = video_data.get('data-url') or video_data['data-asset-source']
|
||||
title = video_data.get('data-asset-title') or video_data.get('data-diffusion-title') or self._og_search_title(webpage)
|
||||
|
||||
description = self._html_search_regex(
|
||||
r'(?s)<div[^>]+class="intro"[^>]*>.*?<h2>(.+?)</h2>',
|
||||
webpage, 'description', default=None)
|
||||
thumbnail = self._search_regex(
|
||||
r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+(?:data-dejavu-)?src="([^"]+)"',
|
||||
webpage, 'thumbnail', default=None)
|
||||
uploader = self._html_search_regex(
|
||||
r'(?s)<span class="author">(.*?)</span>',
|
||||
webpage, 'uploader', default=None)
|
||||
ext = determine_ext(video_url.lower())
|
||||
|
||||
return {
|
||||
'id': display_id,
|
||||
'display_id': display_id,
|
||||
'url': video_url,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'ext': ext,
|
||||
'vcodec': 'none' if ext == 'mp3' else None,
|
||||
'uploader': uploader,
|
||||
'timestamp': int_or_none(video_data.get('data-start-time')) or int_or_none(video_data.get('data-asset-created-date')),
|
||||
'duration': int_or_none(video_data.get('data-duration')),
|
||||
}
|
||||
@ -1,59 +0,0 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import month_by_name
|
||||
|
||||
|
||||
class FranceInterIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?franceinter\.fr/emissions/(?P<id>[^?#]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'https://www.franceinter.fr/emissions/affaires-sensibles/affaires-sensibles-07-septembre-2016',
|
||||
'md5': '9e54d7bdb6fdc02a841007f8a975c094',
|
||||
'info_dict': {
|
||||
'id': 'affaires-sensibles/affaires-sensibles-07-septembre-2016',
|
||||
'ext': 'mp3',
|
||||
'title': 'Affaire Cahuzac : le contentieux du compte en Suisse',
|
||||
'description': 'md5:401969c5d318c061f86bda1fa359292b',
|
||||
'thumbnail': r're:^https?://.*\.jpg',
|
||||
'upload_date': '20160907',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
video_url = self._search_regex(
|
||||
r'(?s)<div[^>]+class=["\']page-diffusion["\'][^>]*>.*?<button[^>]+data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
|
||||
webpage, 'video url', group='url')
|
||||
|
||||
title = self._og_search_title(webpage)
|
||||
description = self._og_search_description(webpage)
|
||||
thumbnail = self._html_search_meta(['og:image', 'twitter:image'], webpage)
|
||||
|
||||
upload_date_str = self._search_regex(
|
||||
r'class=["\']\s*cover-emission-period\s*["\'][^>]*>[^<]+\s+(\d{1,2}\s+[^\s]+\s+\d{4})<',
|
||||
webpage, 'upload date', fatal=False)
|
||||
if upload_date_str:
|
||||
upload_date_list = upload_date_str.split()
|
||||
upload_date_list.reverse()
|
||||
upload_date_list[1] = '%02d' % (month_by_name(upload_date_list[1], lang='fr') or 0)
|
||||
upload_date_list[2] = '%02d' % int(upload_date_list[2])
|
||||
upload_date = ''.join(upload_date_list)
|
||||
else:
|
||||
upload_date = None
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'upload_date': upload_date,
|
||||
'formats': [{
|
||||
'url': video_url,
|
||||
'vcodec': 'none',
|
||||
}],
|
||||
}
|
||||
Loading…
Reference in New Issue