Initiate new release.

[youtubedl] / youtube_dl / extractor / imdb.py

diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py
index 02e1e428e9e41ba75a2ff5c37c7cf0732682c111..0acce9f4c2525a62e3d3ad22b16743737dbb5b07 100644 (file)
--- a/youtube_dl/extractor/imdb.py
+++ b/youtube_dl/extractor/imdb.py
@@ -1,10 +1,10 @@
 from __future__ import unicode_literals
 
 import re
 from __future__ import unicode_literals
 
 import re

-import json

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

+    mimetype2ext,

     qualities,
 )
 
     qualities,
 )
 


@@ -12,9 +12,9 @@ from ..utils import (
 class ImdbIE(InfoExtractor):
     IE_NAME = 'imdb'
     IE_DESC = 'Internet Movie Database trailers'
 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/tt\d+.*?#lb-)vi(?P<id>\d+)'

 
 

-    _TEST = {
+    _TESTS = [{

         'url': 'http://www.imdb.com/video/imdb/vi2524815897',
         'info_dict': {
             'id': '2524815897',
         'url': 'http://www.imdb.com/video/imdb/vi2524815897',
         'info_dict': {
             'id': '2524815897',


@@ -22,7 +22,16 @@ class ImdbIE(InfoExtractor):
             'title': 'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
             'description': 'md5:9061c2219254e5d14e03c25c98e96a81',
         }
             'title': 'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
             'description': 'md5:9061c2219254e5d14e03c25c98e96a81',
         }

-    }
+    }, {
+        '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,
+    }]

 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)


@@ -42,19 +51,33 @@ class ImdbIE(InfoExtractor):
             for f_url, f_name in extra_formats]
         format_pages.append(player_page)
 
             for f_url, f_name in extra_formats]
         format_pages.append(player_page)
 

-        quality = qualities(['SD', '480p', '720p'])
+        quality = qualities(('SD', '480p', '720p', '1080p'))

         formats = []
         for format_page in format_pages:
             json_data = self._search_regex(
                 r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
                 format_page, 'json data', flags=re.DOTALL)
         formats = []
         for format_page in format_pages:
             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']
-            f_id = format_info['ffname']
+            info = self._parse_json(json_data, video_id, fatal=False)
+            if not info:
+                continue
+            format_info = info.get('videoPlayerObject', {}).get('video', {})
+            if not format_info:
+                continue
+            video_info_list = format_info.get('videoInfoList')
+            if not video_info_list or not isinstance(video_info_list, list):
+                continue
+            video_info = video_info_list[0]
+            if not video_info or not isinstance(video_info, dict):
+                continue
+            video_url = video_info.get('videoUrl')
+            if not video_url:
+                continue
+            format_id = format_info.get('ffname')

             formats.append({
             formats.append({

-                'format_id': f_id,
-                'url': format_info['videoInfoList'][0]['videoUrl'],
-                'quality': quality(f_id),
+                'format_id': format_id,
+                'url': video_url,
+                'ext': mimetype2ext(video_info.get('videoMimeType')),
+                'quality': quality(format_id),

             })
         self._sort_formats(formats)
 
             })
         self._sort_formats(formats)
 


@@ -70,7 +93,7 @@ class ImdbIE(InfoExtractor):
 class ImdbListIE(InfoExtractor):
     IE_NAME = 'imdb:list'
     IE_DESC = 'Internet Movie Database lists'
 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/(?P<id>[\da-zA-Z_-]{11})'

     _TEST = {
         'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
         'info_dict': {
     _TEST = {
         'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
         'info_dict': {