yt-dlp/yt_dlp/extractor/imdb.py

148 lines
5.6 KiB
Python
Raw Normal View History

2014-01-07 03:41:13 -05:00
from __future__ import unicode_literals
2020-02-22 16:33:29 -05:00
import base64
import json
import re
from .common import InfoExtractor
2015-10-18 08:13:06 -04:00
from ..utils import (
determine_ext,
int_or_none,
2016-05-13 13:25:05 -04:00
mimetype2ext,
2015-10-18 08:13:06 -04:00
qualities,
traverse_obj,
2020-02-22 16:33:29 -05:00
try_get,
2018-07-21 08:08:28 -04:00
url_or_none,
)
class ImdbIE(InfoExtractor):
2014-01-07 03:41:13 -05:00
IE_NAME = 'imdb'
IE_DESC = 'Internet Movie Database trailers'
2020-02-22 16:33:29 -05:00
_VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title|list).*?[/-]vi(?P<id>\d+)'
2016-05-13 12:19:00 -04:00
_TESTS = [{
2014-01-07 03:41:13 -05:00
'url': 'http://www.imdb.com/video/imdb/vi2524815897',
'info_dict': {
'id': '2524815897',
'ext': 'mp4',
2020-02-22 16:33:29 -05:00
'title': 'No. 2',
'description': 'md5:87bd0bdc61e351f21f20d2d7441cb4e7',
2020-02-22 16:33:29 -05:00
'duration': 152,
'thumbnail': r're:^https?://.+\.jpg',
}
}, {
'url': 'https://www.imdb.com/video/vi3516832537',
'info_dict': {
'id': '3516832537',
'ext': 'mp4',
'title': 'Paul: U.S. Trailer #1',
'description': 'md5:17fcc4fe11ec29b4399be9d4c5ef126c',
'duration': 153,
'thumbnail': r're:^https?://.+\.jpg',
}
2016-05-13 12:19:00 -04:00
}, {
'url': 'http://www.imdb.com/video/_/vi2524815897',
'only_matching': True,
}, {
'url': 'http://www.imdb.com/title/tt1667889/?ref_=ext_shr_eml_vi#lb-vi2524815897',
'only_matching': True,
}, {
'url': 'http://www.imdb.com/title/tt1667889/#lb-vi2524815897',
'only_matching': True,
}, {
'url': 'http://www.imdb.com/videoplayer/vi1562949145',
'only_matching': True,
}, {
'url': 'http://www.imdb.com/title/tt4218696/videoplayer/vi2608641561',
'only_matching': True,
}, {
'url': 'https://www.imdb.com/list/ls009921623/videoplayer/vi260482329',
'only_matching': True,
2016-05-13 12:19:00 -04:00
}]
def _real_extract(self, url):
2014-11-04 17:26:23 -05:00
video_id = self._match_id(url)
webpage = self._download_webpage(f'https://www.imdb.com/video/vi{video_id}', video_id)
info = self._search_nextjs_data(webpage, video_id)
video_info = traverse_obj(info, ('props', 'pageProps', 'videoPlaybackData', 'video'), default={})
title = (traverse_obj(video_info, ('name', 'value'), ('primaryTitle', 'titleText', 'text'))
or self._html_search_meta(('og:title', 'twitter:title'), webpage, default=None)
or self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title'))
data = video_info.get('playbackURLs') or try_get(self._download_json(
2020-02-22 16:33:29 -05:00
'https://www.imdb.com/ve/data/VIDEO_PLAYBACK_DATA', video_id,
query={
'key': base64.b64encode(json.dumps({
'type': 'VIDEO_PLAYER',
'subType': 'FORCE_LEGACY',
'id': 'vi%s' % video_id,
}).encode()).decode(),
}), lambda x: x[0]['videoLegacyEncodings'])
quality = qualities(('SD', '480p', '720p', '1080p'))
formats, subtitles = [], {}
for encoding in data:
if not encoding or not isinstance(encoding, dict):
2016-05-13 13:25:05 -04:00
continue
2020-02-22 16:33:29 -05:00
video_url = url_or_none(encoding.get('url'))
2018-07-21 08:08:28 -04:00
if not video_url:
2016-05-13 13:25:05 -04:00
continue
ext = mimetype2ext(encoding.get(
'mimeType')) or determine_ext(video_url)
if ext == 'm3u8':
fmts, subs = self._extract_m3u8_formats_and_subtitles(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
preference=1, m3u8_id='hls', fatal=False)
subtitles = self._merge_subtitles(subtitles, subs)
formats.extend(fmts)
2016-05-13 13:25:05 -04:00
continue
format_id = traverse_obj(encoding, ('displayName', 'value'), 'definition')
formats.append({
'format_id': format_id,
'url': video_url,
'ext': ext,
'quality': quality(format_id),
})
2015-10-18 08:13:06 -04:00
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
2020-02-22 16:33:29 -05:00
'alt_title': info.get('videoSubTitle'),
'formats': formats,
'description': try_get(video_info, lambda x: x['description']['value']),
'thumbnail': url_or_none(try_get(video_info, lambda x: x['thumbnail']['url'])),
'duration': int_or_none(try_get(video_info, lambda x: x['runtime']['value'])),
'subtitles': subtitles,
}
2013-12-24 20:34:41 -05:00
2014-01-07 03:41:13 -05:00
2013-12-24 20:34:41 -05:00
class ImdbListIE(InfoExtractor):
2014-01-07 03:41:13 -05:00
IE_NAME = 'imdb:list'
IE_DESC = 'Internet Movie Database lists'
2018-05-19 06:04:08 -04:00
_VALID_URL = r'https?://(?:www\.)?imdb\.com/list/ls(?P<id>\d{9})(?!/videoplayer/vi\d+)'
_TEST = {
'url': 'https://www.imdb.com/list/ls009921623/',
'info_dict': {
'id': '009921623',
'title': 'The Bourne Legacy',
'description': 'A list of trailers, clips, and more from The Bourne Legacy, starring Jeremy Renner and Rachel Weisz.',
},
'playlist_count': 8,
}
2014-11-23 14:41:03 -05:00
2013-12-24 20:34:41 -05:00
def _real_extract(self, url):
2014-11-04 17:26:23 -05:00
list_id = self._match_id(url)
webpage = self._download_webpage(url, list_id)
entries = [
self.url_result('http://www.imdb.com' + m, 'Imdb')
for m in re.findall(r'href="(/list/ls%s/videoplayer/vi[^"]+)"' % list_id, webpage)]
list_title = self._html_search_regex(
r'<h1[^>]+class="[^"]*header[^"]*"[^>]*>(.*?)</h1>',
webpage, 'list title')
list_description = self._html_search_regex(
r'<div[^>]+class="[^"]*list-description[^"]*"[^>]*><p>(.*?)</p>',
webpage, 'list description')
return self.playlist_result(entries, list_id, list_title, list_description)