mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-21 20:46:36 -05:00
[condenast] improve extraction
This commit is contained in:
Remita Amine
parent
8a00ea567b
commit
4f427c4be8
1 changed files with 66 additions and 45 deletions
|
|
@ -5,13 +5,17 @@
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..compat import (
|
from ..compat import (
|
||||||
compat_urllib_parse_urlencode,
|
|
||||||
compat_urllib_parse_urlparse,
|
compat_urllib_parse_urlparse,
|
||||||
compat_urlparse,
|
compat_urlparse,
|
||||||
)
|
)
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
orderedSet,
|
orderedSet,
|
||||||
remove_end,
|
remove_end,
|
||||||
|
extract_attributes,
|
||||||
|
mimetype2ext,
|
||||||
|
determine_ext,
|
||||||
|
int_or_none,
|
||||||
|
parse_iso8601,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
|
|
@ -58,6 +62,9 @@ class CondeNastIE(InfoExtractor):
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': '3D Printed Speakers Lit With LED',
|
'title': '3D Printed Speakers Lit With LED',
|
||||||
'description': 'Check out these beautiful 3D printed LED speakers. You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.',
|
'description': 'Check out these beautiful 3D printed LED speakers. You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.',
|
||||||
|
'uploader': 'wired',
|
||||||
|
'upload_date': '20130314',
|
||||||
|
'timestamp': 1363219200,
|
||||||
}
|
}
|
||||||
}, {
|
}, {
|
||||||
# JS embed
|
# JS embed
|
||||||
|
|
@ -67,70 +74,84 @@ class CondeNastIE(InfoExtractor):
|
||||||
'id': '55f9cf8b61646d1acf00000c',
|
'id': '55f9cf8b61646d1acf00000c',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': '3D printed TSA Travel Sentry keys really do open TSA locks',
|
'title': '3D printed TSA Travel Sentry keys really do open TSA locks',
|
||||||
|
'uploader': 'arstechnica',
|
||||||
|
'upload_date': '20150916',
|
||||||
|
'timestamp': 1442434955,
|
||||||
}
|
}
|
||||||
}]
|
}]
|
||||||
|
|
||||||
def _extract_series(self, url, webpage):
|
def _extract_series(self, url, webpage):
|
||||||
title = self._html_search_regex(r'<div class="cne-series-info">.*?<h1>(.+?)</h1>',
|
title = self._html_search_regex(
|
||||||
webpage, 'series title', flags=re.DOTALL)
|
r'(?s)<div class="cne-series-info">.*?<h1>(.+?)</h1>',
|
||||||
|
webpage, 'series title')
|
||||||
url_object = compat_urllib_parse_urlparse(url)
|
url_object = compat_urllib_parse_urlparse(url)
|
||||||
base_url = '%s://%s' % (url_object.scheme, url_object.netloc)
|
base_url = '%s://%s' % (url_object.scheme, url_object.netloc)
|
||||||
m_paths = re.finditer(r'<p class="cne-thumb-title">.*?<a href="(/watch/.+?)["\?]',
|
m_paths = re.finditer(
|
||||||
webpage, flags=re.DOTALL)
|
r'(?s)<p class="cne-thumb-title">.*?<a href="(/watch/.+?)["\?]', webpage)
|
||||||
paths = orderedSet(m.group(1) for m in m_paths)
|
paths = orderedSet(m.group(1) for m in m_paths)
|
||||||
build_url = lambda path: compat_urlparse.urljoin(base_url, path)
|
build_url = lambda path: compat_urlparse.urljoin(base_url, path)
|
||||||
entries = [self.url_result(build_url(path), 'CondeNast') for path in paths]
|
entries = [self.url_result(build_url(path), 'CondeNast') for path in paths]
|
||||||
return self.playlist_result(entries, playlist_title=title)
|
return self.playlist_result(entries, playlist_title=title)
|
||||||
|
|
||||||
def _extract_video(self, webpage, url_type):
|
def _extract_video(self, webpage, url_type):
|
||||||
if url_type != 'embed':
|
query = {}
|
||||||
description = self._html_search_regex(
|
params = self._search_regex(
|
||||||
[
|
r'(?s)var params = {(.+?)}[;,]', webpage, 'player params', default=None)
|
||||||
r'<div class="cne-video-description">(.+?)</div>',
|
if params:
|
||||||
r'<div class="video-post-content">(.+?)</div>',
|
query.update({
|
||||||
],
|
'videoId': self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id'),
|
||||||
webpage, 'description', fatal=False, flags=re.DOTALL)
|
'playerId': self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, 'player id'),
|
||||||
|
'target': self._search_regex(r'target: [\'"](.+?)[\'"]', params, 'target'),
|
||||||
|
})
|
||||||
else:
|
else:
|
||||||
description = None
|
params = extract_attributes(self._search_regex(
|
||||||
params = self._search_regex(r'var params = {(.+?)}[;,]', webpage,
|
r'(<[^>]+data-js="video-player"[^>]+>)',
|
||||||
'player params', flags=re.DOTALL)
|
webpage, 'player params element'))
|
||||||
video_id = self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id')
|
query.update({
|
||||||
player_id = self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, 'player id')
|
'videoId': params['data-video'],
|
||||||
target = self._search_regex(r'target: [\'"](.+?)[\'"]', params, 'target')
|
'playerId': params['data-player'],
|
||||||
data = compat_urllib_parse_urlencode({'videoId': video_id,
|
'target': params['id'],
|
||||||
'playerId': player_id,
|
})
|
||||||
'target': target,
|
video_id = query['videoId']
|
||||||
})
|
info_page = self._download_webpage(
|
||||||
base_info_url = self._search_regex(r'url = [\'"](.+?)[\'"][,;]',
|
'http://player.cnevids.com/player/video.js',
|
||||||
webpage, 'base info url',
|
video_id, 'Downloading video info', query=query)
|
||||||
default='http://player.cnevids.com/player/loader.js?')
|
video_info = self._parse_json(self._search_regex(
|
||||||
info_url = base_info_url + data
|
r'loadCallback\(({.+})\)', info_page, 'video info'), video_id)['video']
|
||||||
info_page = self._download_webpage(info_url, video_id,
|
title = video_info['title']
|
||||||
'Downloading video info')
|
|
||||||
video_info = self._search_regex(r'var\s+video\s*=\s*({.+?});', info_page, 'video info')
|
|
||||||
video_info = self._parse_json(video_info, video_id)
|
|
||||||
|
|
||||||
formats = [{
|
formats = []
|
||||||
'format_id': '%s-%s' % (fdata['type'].split('/')[-1], fdata['quality']),
|
for fdata in video_info.get('sources', [{}])[0]:
|
||||||
'url': fdata['src'],
|
src = fdata.get('src')
|
||||||
'ext': fdata['type'].split('/')[-1],
|
if not src:
|
||||||
'quality': 1 if fdata['quality'] == 'high' else 0,
|
continue
|
||||||
} for fdata in video_info['sources'][0]]
|
ext = mimetype2ext(fdata.get('type')) or determine_ext(src)
|
||||||
|
quality = fdata.get('quality')
|
||||||
|
formats.append({
|
||||||
|
'format_id': ext + ('-%s' % quality if quality else ''),
|
||||||
|
'url': src,
|
||||||
|
'ext': ext,
|
||||||
|
'quality': 1 if quality == 'high' else 0,
|
||||||
|
})
|
||||||
self._sort_formats(formats)
|
self._sort_formats(formats)
|
||||||
|
|
||||||
return {
|
info = self._search_json_ld(webpage, video_id) if url_type != 'embed' else {}
|
||||||
|
info.update({
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'formats': formats,
|
'formats': formats,
|
||||||
'title': video_info['title'],
|
'title': title,
|
||||||
'thumbnail': video_info['poster_frame'],
|
'thumbnail': video_info.get('poster_frame'),
|
||||||
'description': description,
|
'uploader': video_info.get('brand'),
|
||||||
}
|
'duration': int_or_none(video_info.get('duration')),
|
||||||
|
'tags': video_info.get('tags'),
|
||||||
|
'series': video_info.get('series_title'),
|
||||||
|
'season': video_info.get('season_title'),
|
||||||
|
'timestamp': parse_iso8601(video_info.get('premiere_date')),
|
||||||
|
})
|
||||||
|
return info
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
mobj = re.match(self._VALID_URL, url)
|
site, url_type, item_id = re.match(self._VALID_URL, url).groups()
|
||||||
site = mobj.group('site')
|
|
||||||
url_type = mobj.group('type')
|
|
||||||
item_id = mobj.group('id')
|
|
||||||
|
|
||||||
# Convert JS embed to regular embed
|
# Convert JS embed to regular embed
|
||||||
if url_type == 'embedjs':
|
if url_type == 'embedjs':
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue