from __future__ import unicode_literals
import re
-import json
from .common import InfoExtractor
+from ..compat import compat_str
from ..utils import (
- compat_urlparse,
+ determine_ext,
+ mimetype2ext,
+ parse_duration,
+ qualities,
)
class ImdbIE(InfoExtractor):
IE_NAME = 'imdb'
IE_DESC = 'Internet Movie Database trailers'
- _VALID_URL = r'http://(?:www|m)\.imdb\.com/video/imdb/vi(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title|list).+?[/-]vi(?P<id>\d+)'
- _TEST = {
+ _TESTS = [{
'url': 'http://www.imdb.com/video/imdb/vi2524815897',
- 'md5': '9f34fa777ade3a6e57a054fdbcb3a068',
'info_dict': {
'id': '2524815897',
'ext': 'mp4',
- 'title': 'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
- 'description': 'md5:9061c2219254e5d14e03c25c98e96a81',
+ 'title': 'No. 2 from Ice Age: Continental Drift (2012)',
+ 'description': 'md5:87bd0bdc61e351f21f20d2d7441cb4e7',
}
- }
+ }, {
+ '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,
+ }]
def _real_extract(self, url):
video_id = self._match_id(url)
- webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id)
- descr = self._html_search_regex(
- r'(?s)<span itemprop="description">(.*?)</span>',
- webpage, 'description', fatal=False)
- available_formats = re.findall(
- r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', webpage,
- flags=re.MULTILINE)
+ webpage = self._download_webpage(
+ 'https://www.imdb.com/videoplayer/vi' + video_id, video_id)
+ video_metadata = self._parse_json(self._search_regex(
+ r'window\.IMDbReactInitialState\.push\(({.+?})\);', webpage,
+ 'video metadata'), video_id)['videos']['videoMetadata']['vi' + video_id]
+ title = self._html_search_meta(
+ ['og:title', 'twitter:title'], webpage) or self._html_search_regex(
+ r'<title>(.+?)</title>', webpage, 'title', fatal=False) or video_metadata['title']
+
+ quality = qualities(('SD', '480p', '720p', '1080p'))
formats = []
- for f_id, f_path in available_formats:
- f_path = f_path.strip()
- format_page = self._download_webpage(
- compat_urlparse.urljoin(url, f_path),
- 'Downloading info for %s format' % f_id)
- json_data = self._search_regex(
- r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
- format_page, 'json data', flags=re.DOTALL)
- info = json.loads(json_data)
- format_info = info['videoPlayerObject']['video']
+ for encoding in video_metadata.get('encodings', []):
+ if not encoding or not isinstance(encoding, dict):
+ continue
+ video_url = encoding.get('videoUrl')
+ if not video_url or not isinstance(video_url, compat_str):
+ continue
+ ext = determine_ext(video_url, mimetype2ext(encoding.get('mimeType')))
+ if ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+ m3u8_id='hls', fatal=False))
+ continue
+ format_id = encoding.get('definition')
formats.append({
- 'format_id': f_id,
- 'url': format_info['url'],
+ 'format_id': format_id,
+ 'url': video_url,
+ 'ext': ext,
+ 'quality': quality(format_id),
})
+ self._sort_formats(formats)
return {
'id': video_id,
- 'title': self._og_search_title(webpage),
+ 'title': title,
'formats': formats,
- 'description': descr,
- 'thumbnail': format_info['slate'],
+ 'description': video_metadata.get('description'),
+ 'thumbnail': video_metadata.get('slate', {}).get('url'),
+ 'duration': parse_duration(video_metadata.get('duration')),
}
class ImdbListIE(InfoExtractor):
IE_NAME = 'imdb:list'
IE_DESC = 'Internet Movie Database lists'
- _VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
+ _VALID_URL = r'https?://(?:www\.)?imdb\.com/list/ls(?P<id>\d{9})(?!/videoplayer/vi\d+)'
_TEST = {
- 'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
+ 'url': 'https://www.imdb.com/list/ls009921623/',
'info_dict': {
- 'id': 'JFs9NWw6XI0',
- 'title': 'March 23, 2012 Releases',
+ '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': 7,
+ 'playlist_count': 8,
}
-
+
def _real_extract(self, url):
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="(/video/imdb/vi[^"]+)"\s+data-type="playlist"', webpage)]
+ 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')
+ 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)
+ return self.playlist_result(entries, list_id, list_title, list_description)
Rapsys Git / youtubedl / blobdiff