debian/control: Update list of supported sites.

[youtubedl] / youtube_dl / extractor / imdb.py

diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py
index d8e9712a7acd39db97c8a55b2551137ca0e56a41..a31301985b0c7d212886a2e6e495c7d705714041 100644 (file)
--- a/youtube_dl/extractor/imdb.py
+++ b/youtube_dl/extractor/imdb.py
@@ -1,59 +1,147 @@
-import re
+from __future__ import unicode_literals
+
+import base64

 import json
 import json

+import re

 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (

-    compat_urlparse,
-    get_element_by_attribute,
+    determine_ext,
+    mimetype2ext,
+    parse_duration,
+    qualities,
+    try_get,
+    url_or_none,

 )
 
 
 class ImdbIE(InfoExtractor):
 )
 
 
 class ImdbIE(InfoExtractor):

-    IE_NAME = u'imdb'
-    IE_DESC = u'Internet Movie Database trailers'
-    _VALID_URL = r'http://www\.imdb\.com/video/imdb/vi(?P<id>\d+)'
+    IE_NAME = 'imdb'
+    IE_DESC = 'Internet Movie Database trailers'
+    _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title|list).*?[/-]vi(?P<id>\d+)'

 
 

-    _TEST = {
-        u'url': u'http://www.imdb.com/video/imdb/vi2524815897',
-        u'md5': u'9f34fa777ade3a6e57a054fdbcb3a068',
-        u'info_dict': {
-            u'id': u'2524815897',
-            u'ext': u'mp4',
-            u'title': u'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
-            u'description': u'md5:9061c2219254e5d14e03c25c98e96a81',
-            u'duration': 151,
+    _TESTS = [{
+        'url': 'http://www.imdb.com/video/imdb/vi2524815897',
+        'info_dict': {
+            'id': '2524815897',
+            'ext': 'mp4',
+            'title': 'No. 2',
+            'description': 'md5:87bd0bdc61e351f21f20d2d7441cb4e7',
+            'duration': 152,

         }
         }

-    }
+    }, {
+        '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):
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        webpage = self._download_webpage(url,video_id)
-        descr = get_element_by_attribute('itemprop', 'description', webpage)
-        available_formats = re.findall(
-            r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', webpage,
-            flags=re.MULTILINE)
+        video_id = self._match_id(url)
+
+        data = self._download_json(
+            '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(),
+            })[0]
+
+        quality = qualities(('SD', '480p', '720p', '1080p'))

         formats = []
         formats = []

-        for f_id, f_path in available_formats:
-            format_page = self._download_webpage(
-                compat_urlparse.urljoin(url, f_path),
-                u'Downloading info for %s format' % f_id)
-            json_data = self._search_regex(
-                r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
-                format_page, u'json data', flags=re.DOTALL)
-            info = json.loads(json_data)
-            format_info = info['videoPlayerObject']['video']
+        for encoding in data['videoLegacyEncodings']:
+            if not encoding or not isinstance(encoding, dict):
+                continue
+            video_url = url_or_none(encoding.get('url'))
+            if not video_url:
+                continue
+            ext = mimetype2ext(encoding.get(
+                'mimeType')) or determine_ext(video_url)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    preference=1, m3u8_id='hls', fatal=False))
+                continue
+            format_id = encoding.get('definition')

             formats.append({
             formats.append({

-                'format_id': f_id,
-                'url': format_info['url'],
-                'height': int(info['titleObject']['encoding']['selected'][:-1]),
+                'format_id': format_id,
+                'url': video_url,
+                'ext': ext,
+                'quality': quality(format_id),

             })
             })

+        self._sort_formats(formats)
+
+        webpage = self._download_webpage(
+            'https://www.imdb.com/video/vi' + video_id, video_id)
+        video_metadata = self._parse_json(self._search_regex(
+            r'args\.push\(\s*({.+?})\s*\)\s*;', webpage,
+            'video metadata'), video_id)
+
+        video_info = video_metadata.get('VIDEO_INFO')
+        if video_info and isinstance(video_info, dict):
+            info = try_get(
+                video_info, lambda x: x[list(video_info.keys())[0]][0], dict)
+        else:
+            info = {}
+
+        title = self._html_search_meta(
+            ['og:title', 'twitter:title'], webpage) or self._html_search_regex(
+            r'<title>(.+?)</title>', webpage, 'title',
+            default=None) or info['videoTitle']

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,

-            'title': self._og_search_title(webpage),
+            'title': title,
+            'alt_title': info.get('videoSubTitle'),

             'formats': formats,
             'formats': formats,

-            'description': descr,
-            'thumbnail': format_info['slate'],
-            'duration': int(info['titleObject']['title']['duration_seconds']),
+            'description': info.get('videoDescription'),
+            'thumbnail': url_or_none(try_get(
+                video_metadata, lambda x: x['videoSlate']['source'])),
+            'duration': parse_duration(info.get('videoRuntime')),

         }
         }

+
+
+class ImdbListIE(InfoExtractor):
+    IE_NAME = 'imdb:list'
+    IE_DESC = 'Internet Movie Database lists'
+    _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,
+    }
+
+    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="(/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)