mirror of https://github.com/yt-dlp/yt-dlp
Update to ytdl-commit-4460329
pull/111/head44603290e5Except: gedi, tmz7422a2194f8cb4b71909d81421af4b
pukkandan
3 years ago
parent
0744a815b7
commit
7c60c33efe
@ -0,0 +1,100 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
extract_attributes,
|
||||
get_element_by_attribute,
|
||||
int_or_none,
|
||||
)
|
||||
|
||||
|
||||
class SampleFocusIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?samplefocus\.com/samples/(?P<id>[^/?&#]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://samplefocus.com/samples/lil-peep-sad-emo-guitar',
|
||||
'md5': '48c8d62d60be467293912e0e619a5120',
|
||||
'info_dict': {
|
||||
'id': '40316',
|
||||
'display_id': 'lil-peep-sad-emo-guitar',
|
||||
'ext': 'mp3',
|
||||
'title': 'Lil Peep Sad Emo Guitar',
|
||||
'thumbnail': r're:^https?://.+\.png',
|
||||
'license': 'Standard License',
|
||||
'uploader': 'CapsCtrl',
|
||||
'uploader_id': 'capsctrl',
|
||||
'like_count': int,
|
||||
'comment_count': int,
|
||||
'categories': ['Samples', 'Guitar', 'Electric guitar'],
|
||||
},
|
||||
}, {
|
||||
'url': 'https://samplefocus.com/samples/dababy-style-bass-808',
|
||||
'only_matching': True
|
||||
}, {
|
||||
'url': 'https://samplefocus.com/samples/young-chop-kick',
|
||||
'only_matching': True
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
sample_id = self._search_regex(
|
||||
r'<input[^>]+id=(["\'])sample_id\1[^>]+value=(?:["\'])(?P<id>\d+)',
|
||||
webpage, 'sample id', group='id')
|
||||
|
||||
title = self._og_search_title(webpage, fatal=False) or self._html_search_regex(
|
||||
r'<h1>(.+?)</h1>', webpage, 'title')
|
||||
|
||||
mp3_url = self._search_regex(
|
||||
r'<input[^>]+id=(["\'])sample_mp3\1[^>]+value=(["\'])(?P<url>(?:(?!\2).)+)',
|
||||
webpage, 'mp3', fatal=False, group='url') or extract_attributes(self._search_regex(
|
||||
r'<meta[^>]+itemprop=(["\'])contentUrl\1[^>]*>',
|
||||
webpage, 'mp3 url', group=0))['content']
|
||||
|
||||
thumbnail = self._og_search_thumbnail(webpage) or self._html_search_regex(
|
||||
r'<img[^>]+class=(?:["\'])waveform responsive-img[^>]+src=(["\'])(?P<url>(?:(?!\1).)+)',
|
||||
webpage, 'mp3', fatal=False, group='url')
|
||||
|
||||
comments = []
|
||||
for author_id, author, body in re.findall(r'(?s)<p[^>]+class="comment-author"><a[^>]+href="/users/([^"]+)">([^"]+)</a>.+?<p[^>]+class="comment-body">([^>]+)</p>', webpage):
|
||||
comments.append({
|
||||
'author': author,
|
||||
'author_id': author_id,
|
||||
'text': body,
|
||||
})
|
||||
|
||||
uploader_id = uploader = None
|
||||
mobj = re.search(r'>By <a[^>]+href="/users/([^"]+)"[^>]*>([^<]+)', webpage)
|
||||
if mobj:
|
||||
uploader_id, uploader = mobj.groups()
|
||||
|
||||
breadcrumb = get_element_by_attribute('typeof', 'BreadcrumbList', webpage)
|
||||
categories = []
|
||||
if breadcrumb:
|
||||
for _, name in re.findall(r'<span[^>]+property=(["\'])name\1[^>]*>([^<]+)', breadcrumb):
|
||||
categories.append(name)
|
||||
|
||||
def extract_count(klass):
|
||||
return int_or_none(self._html_search_regex(
|
||||
r'<span[^>]+class=(?:["\'])?%s-count[^>]*>(\d+)' % klass,
|
||||
webpage, klass, fatal=False))
|
||||
|
||||
return {
|
||||
'id': sample_id,
|
||||
'title': title,
|
||||
'url': mp3_url,
|
||||
'display_id': display_id,
|
||||
'thumbnail': thumbnail,
|
||||
'uploader': uploader,
|
||||
'license': self._html_search_regex(
|
||||
r'<a[^>]+href=(["\'])/license\1[^>]*>(?P<license>[^<]+)<',
|
||||
webpage, 'license', fatal=False, group='license'),
|
||||
'uploader_id': uploader_id,
|
||||
'like_count': extract_count('sample-%s-favorites' % sample_id),
|
||||
'comment_count': extract_count('comments'),
|
||||
'comments': comments,
|
||||
'categories': categories,
|
||||
}
|
||||
@ -1,92 +1,87 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class TF1IE(InfoExtractor):
|
||||
"""TF1 uses the wat.tv player."""
|
||||
_VALID_URL = r'https?://(?:(?:videos|www|lci)\.tf1|(?:www\.)?(?:tfou|ushuaiatv|histoire|tvbreizh))\.fr/(?:[^/]+/)*(?P<id>[^/?#.]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?tf1\.fr/[^/]+/(?P<program_slug>[^/]+)/videos/(?P<id>[^/?&#]+)\.html'
|
||||
_TESTS = [{
|
||||
'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
|
||||
'info_dict': {
|
||||
'id': '10635995',
|
||||
'ext': 'mp4',
|
||||
'title': 'Citroën Grand C4 Picasso 2013 : présentation officielle',
|
||||
'description': 'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.',
|
||||
},
|
||||
'params': {
|
||||
# Sometimes wat serves the whole file with the --test option
|
||||
'skip_download': True,
|
||||
},
|
||||
'expected_warnings': ['HTTP Error 404'],
|
||||
}, {
|
||||
'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html',
|
||||
'url': 'https://www.tf1.fr/tmc/quotidien-avec-yann-barthes/videos/quotidien-premiere-partie-11-juin-2019.html',
|
||||
'info_dict': {
|
||||
'id': 'le-grand-mysterioso-chuggington-7085291-739',
|
||||
'id': '13641379',
|
||||
'ext': 'mp4',
|
||||
'title': 'Le grand Mystérioso - Chuggington',
|
||||
'description': 'Le grand Mystérioso - Emery rêve qu\'un article lui soit consacré dans le journal.',
|
||||
'upload_date': '20150103',
|
||||
'title': 'md5:f392bc52245dc5ad43771650c96fb620',
|
||||
'description': 'md5:a02cdb217141fb2d469d6216339b052f',
|
||||
'upload_date': '20190611',
|
||||
'timestamp': 1560273989,
|
||||
'duration': 1738,
|
||||
'series': 'Quotidien avec Yann Barthès',
|
||||
'tags': ['intégrale', 'quotidien', 'Replay'],
|
||||
},
|
||||
'params': {
|
||||
# Sometimes wat serves the whole file with the --test option
|
||||
'skip_download': True,
|
||||
'format': 'bestvideo',
|
||||
},
|
||||
'skip': 'HTTP Error 410: Gone',
|
||||
}, {
|
||||
'url': 'http://www.tf1.fr/tf1/koh-lanta/videos/replay-koh-lanta-22-mai-2015.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://lci.tf1.fr/sept-a-huit/videos/sept-a-huit-du-24-mai-2015-8611550.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.tf1.fr/hd1/documentaire/videos/mylene-farmer-d-une-icone.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.tf1.fr/tmc/quotidien-avec-yann-barthes/videos/quotidien-premiere-partie-11-juin-2019.html',
|
||||
'info_dict': {
|
||||
'id': '13641379',
|
||||
'ext': 'mp4',
|
||||
'title': 'md5:f392bc52245dc5ad43771650c96fb620',
|
||||
'description': 'md5:44bc54f0a21322f5b91d68e76a544eae',
|
||||
'upload_date': '20190611',
|
||||
},
|
||||
'params': {
|
||||
# Sometimes wat serves the whole file with the --test option
|
||||
'skip_download': True,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
wat_id = None
|
||||
program_slug, slug = re.match(self._VALID_URL, url).groups()
|
||||
video = self._download_json(
|
||||
'https://www.tf1.fr/graphql/web', slug, query={
|
||||
'id': '9b80783950b85247541dd1d851f9cc7fa36574af015621f853ab111a679ce26f',
|
||||
'variables': json.dumps({
|
||||
'programSlug': program_slug,
|
||||
'slug': slug,
|
||||
})
|
||||
})['data']['videoBySlug']
|
||||
wat_id = video['streamId']
|
||||
|
||||
data = self._parse_json(
|
||||
self._search_regex(
|
||||
r'__APOLLO_STATE__\s*=\s*({.+?})\s*(?:;|</script>)', webpage,
|
||||
'data', default='{}'), video_id, fatal=False)
|
||||
tags = []
|
||||
for tag in (video.get('tags') or []):
|
||||
label = tag.get('label')
|
||||
if not label:
|
||||
continue
|
||||
tags.append(label)
|
||||
|
||||
if data:
|
||||
try:
|
||||
wat_id = next(
|
||||
video.get('streamId')
|
||||
for key, video in data.items()
|
||||
if isinstance(video, dict)
|
||||
and video.get('slug') == video_id)
|
||||
if not isinstance(wat_id, compat_str) or not wat_id.isdigit():
|
||||
wat_id = None
|
||||
except StopIteration:
|
||||
pass
|
||||
decoration = video.get('decoration') or {}
|
||||
|
||||
if not wat_id:
|
||||
wat_id = self._html_search_regex(
|
||||
(r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1',
|
||||
r'(["\']?)streamId\1\s*:\s*(["\']?)(?P<id>\d+)\2'),
|
||||
webpage, 'wat id', group='id')
|
||||
thumbnails = []
|
||||
for source in (try_get(decoration, lambda x: x['image']['sources'], list) or []):
|
||||
source_url = source.get('url')
|
||||
if not source_url:
|
||||
continue
|
||||
thumbnails.append({
|
||||
'url': source_url,
|
||||
'width': int_or_none(source.get('width')),
|
||||
})
|
||||
|
||||
return self.url_result('wat:%s' % wat_id, 'Wat')
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': wat_id,
|
||||
'url': 'wat:' + wat_id,
|
||||
'title': video.get('title'),
|
||||
'thumbnails': thumbnails,
|
||||
'description': decoration.get('description'),
|
||||
'timestamp': parse_iso8601(video.get('date')),
|
||||
'duration': int_or_none(try_get(video, lambda x: x['publicPlayingInfos']['duration'])),
|
||||
'tags': tags,
|
||||
'series': decoration.get('programLabel'),
|
||||
'season_number': int_or_none(video.get('season')),
|
||||
'episode_number': int_or_none(video.get('episode')),
|
||||
}
|
||||
|
||||
Loading…
Reference in New Issue