mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-01-31 09:41:18 +02:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[ie/francetv:site] Fix extractor (#12236)

Browse Source 
Closes #12209
Authored by: bashonly
This commit is contained in:
bashonly 2025-01-29 17:23:29 -06:00 committed by GitHub
parent 861aeec449
commit 817483ccc6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 29 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
yt_dlp/extractor/francetv.py
View File

@ -1,3 +1,4 @@
import json
import re import re
import urllib.parse import urllib.parse
@ -5,6 +6,7 @@ from .common import InfoExtractor
from .dailymotion import DailymotionIE from .dailymotion import DailymotionIE
from ..networking import HEADRequest from ..networking import HEADRequest
from ..utils import ( from ..utils import (
ExtractorError,
clean_html, clean_html,
determine_ext, determine_ext,
filter_dict, filter_dict,
@ -29,6 +31,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
class FranceTVIE(InfoExtractor): class FranceTVIE(InfoExtractor):
IE_NAME = 'francetv'
_VALID_URL = r'francetv:(?P<id>[^@#]+)' _VALID_URL = r'francetv:(?P<id>[^@#]+)'
_GEO_COUNTRIES = ['FR'] _GEO_COUNTRIES = ['FR']
_GEO_BYPASS = False _GEO_BYPASS = False
@ -248,18 +251,19 @@ class FranceTVIE(InfoExtractor):
class FranceTVSiteIE(FranceTVBaseInfoExtractor): class FranceTVSiteIE(FranceTVBaseInfoExtractor):
IE_NAME = 'francetv:site'
_VALID_URL = r'https?://(?:(?:www\.)?france\.tv|mobile\.france\.tv)/(?:[^/]+/)*(?P<id>[^/]+)\.html' _VALID_URL = r'https?://(?:(?:www\.)?france\.tv|mobile\.france\.tv)/(?:[^/]+/)*(?P<id>[^/]+)\.html'
_TESTS = [{ _TESTS = [{
'url': 'https://www.france.tv/france-2/13h15-le-dimanche/140921-les-mysteres-de-jesus.html', 'url': 'https://www.france.tv/france-2/13h15-le-dimanche/140921-les-mysteres-de-jesus.html',
'info_dict': { 'info_dict': {
'id': 'c5bda21d-2c6f-4470-8849-3d8327adb2ba', 'id': 'ec217ecc-0733-48cf-ac06-af1347b849d1', # old: c5bda21d-2c6f-4470-8849-3d8327adb2ba'
'ext': 'mp4', 'ext': 'mp4',
'title': '13h15, le dimanche... - Les mystères de Jésus', 'title': '13h15, le dimanche... - Les mystères de Jésus',
'timestamp': 1514118300, 'timestamp': 1502623500,
'duration': 2880, 'duration': 2580,
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20171224', 'upload_date': '20170813',
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
@ -282,6 +286,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'duration': 1441, 'duration': 1441,
}, },
'skip': 'No longer available',
}, { }, {
# geo-restricted livestream (workflow == 'token-akamai') # geo-restricted livestream (workflow == 'token-akamai')
'url': 'https://www.france.tv/france-4/direct.html', 'url': 'https://www.france.tv/france-4/direct.html',
@ -336,19 +341,32 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
# XXX: For parsing next.js v15+ data; see also yt_dlp.extractor.goplay
def _find_json(self, s):
return self._search_json(
r'\w+\s*:\s*', s, 'next js data', None, contains_pattern=r'\[(?s:.+)\]', default=None)
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
video_id = self._search_regex( nextjs_data = traverse_obj(
r'(?:data-main-video\s*=|videoId["\']?\s*[:=])\s*(["\'])(?P<id>(?:(?!\1).)+)\1', re.findall(r'<script[^>]*>\s*self\.__next_f\.push\(\s*(\[.+?\])\s*\);?\s*</script>', webpage),
webpage, 'video id', default=None, group='id') (..., {json.loads}, ..., {self._find_json}, ..., 'children', ..., ..., 'children', ..., ..., 'children'))
if traverse_obj(nextjs_data, (..., ..., 'children', ..., 'isLive', {bool}, any)):
# For livestreams we need the id of the stream instead of the currently airing episode id
video_id = traverse_obj(nextjs_data, (
..., ..., 'children', ..., 'children', ..., 'children', ..., 'children', ..., ...,
'children', ..., ..., 'children', ..., ..., 'children', ..., 'options', 'id', {str}, any))
else:
video_id = traverse_obj(nextjs_data, (
..., ..., ..., 'children',
lambda _, v: v['video']['url'] == urllib.parse.urlparse(url).path,
'video', ('playerReplayId', 'siId'), {str}, any))
if not video_id: if not video_id:
video_id = self._html_search_regex( raise ExtractorError('Unable to extract video ID')
r'(?:href=|player\.setVideo\(\s*)"http://videos?\.francetv\.fr/video/([^@"]+@[^"]+)"',
webpage, 'video ID')
return self._make_url_result(video_id, url=url) return self._make_url_result(video_id, url=url)