Start new release.

[youtubedl] / youtube_dl / extractor / go.py

diff --git a/youtube_dl/extractor/go.py b/youtube_dl/extractor/go.py
index c7776b1868e617cf78e37dd4c4b3bc742e89e8b7..5916f9a8f20b1a92ae63b2f4709a9d8bb8997fd0 100644 (file)
--- a/youtube_dl/extractor/go.py
+++ b/youtube_dl/extractor/go.py
@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 
 import re
 
 
 import re
 

-from .common import InfoExtractor
+from .adobepass import AdobePassIE

 from ..utils import (
     int_or_none,
     determine_ext,
 from ..utils import (
     int_or_none,
     determine_ext,


@@ -13,41 +13,108 @@ from ..utils import (
 )
 
 
 )
 
 

-class GoIE(InfoExtractor):
-    _BRANDS = {
-        'abc': '001',
-        'freeform': '002',
-        'watchdisneychannel': '004',
-        'watchdisneyjunior': '008',
-        'watchdisneyxd': '009',
+class GoIE(AdobePassIE):
+    _SITE_INFO = {
+        'abc': {
+            'brand': '001',
+            'requestor_id': 'ABC',
+        },
+        'freeform': {
+            'brand': '002',
+            'requestor_id': 'ABCFamily',
+        },
+        'watchdisneychannel': {
+            'brand': '004',
+            'resource_id': 'Disney',
+        },
+        'watchdisneyjunior': {
+            'brand': '008',
+            'resource_id': 'DisneyJunior',
+        },
+        'watchdisneyxd': {
+            'brand': '009',
+            'resource_id': 'DisneyXD',
+        }

     }
     }

-    _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|season-\d+/\d+-(?P<display_id>[^/?#]+))' % '|'.join(_BRANDS.keys())
+    _VALID_URL = r'https?://(?:(?:(?P<sub_domain>%s)\.)?go|disneynow)\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))'\
+                 % '|'.join(list(_SITE_INFO.keys()) + ['disneynow'])

     _TESTS = [{
     _TESTS = [{

-        'url': 'http://abc.go.com/shows/castle/video/most-recent/vdka0_g86w5onx',
+        'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',

         'info_dict': {
         'info_dict': {

-            'id': '0_g86w5onx',
+            'id': 'VDKA3807643',

             'ext': 'mp4',
             'ext': 'mp4',

-            'title': 'Sneak Peek: Language Arts',
-            'description': 'md5:7dcdab3b2d17e5217c953256af964e9c',
+            'title': 'The Traitor in the White House',
+            'description': 'md5:05b009d2d145a1e85d25111bd37222e8',

         },
         'params': {
             # m3u8 download
             'skip_download': True,
         },
     }, {
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         },
     }, {

-        'url': 'http://abc.go.com/shows/after-paradise/video/most-recent/vdka3335601',
+        'url': 'http://watchdisneyxd.go.com/doraemon',
+        'info_dict': {
+            'title': 'Doraemon',
+            'id': 'SH55574025',
+        },
+        'playlist_mincount': 51,
+    }, {
+        'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
+        'only_matching': True,
+    }, {
+        'url': 'http://abc.go.com/shows/world-news-tonight/episode-guide/2017-02/17-021717-intense-stand-off-between-man-with-rifle-and-police-in-oakland',
+        'only_matching': True,
+    }, {
+        # brand 004
+        'url': 'http://disneynow.go.com/shows/big-hero-6-the-series/season-01/episode-10-mr-sparkles-loses-his-sparkle/vdka4637915',
+        'only_matching': True,
+    }, {
+        # brand 008
+        'url': 'http://disneynow.go.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
+        'only_matching': True,
+    }, {
+        'url': 'https://disneynow.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',

         'only_matching': True,
     }]
 
         'only_matching': True,
     }]
 

+    def _extract_videos(self, brand, video_id='-1', show_id='-1'):
+        display_id = video_id if video_id != '-1' else show_id
+        return self._download_json(
+            'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/%s/-1/%s/-1/-1.json' % (brand, show_id, video_id),
+            display_id)['video']
+

     def _real_extract(self, url):
         sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
     def _real_extract(self, url):
         sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups()

-        if not video_id:
-            webpage = self._download_webpage(url, display_id)
-            video_id = self._search_regex(r'data-video-id=["\']VDKA(\w+)', webpage, 'video id')
-        brand = self._BRANDS[sub_domain]
-        video_data = self._download_json(
-            'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (brand, video_id),
-            video_id)['video'][0]
+        site_info = self._SITE_INFO.get(sub_domain, {})
+        brand = site_info.get('brand')
+        if not video_id or not site_info:
+            webpage = self._download_webpage(url, display_id or video_id)
+            video_id = self._search_regex(
+                # There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
+                # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
+                r'data-video-id=["\']*(VDKA\w+)', webpage, 'video id',
+                default=video_id)
+            if not site_info:
+                brand = self._search_regex(
+                    (r'data-brand=\s*["\']\s*(\d+)',
+                     r'data-page-brand=\s*["\']\s*(\d+)'), webpage, 'brand',
+                    default='004')
+                site_info = next(
+                    si for _, si in self._SITE_INFO.items()
+                    if si.get('brand') == brand)
+            if not video_id:
+                # show extraction works for Disney, DisneyJunior and DisneyXD
+                # ABC and Freeform has different layout
+                show_id = self._search_regex(r'data-show-id=["\']*(SH\d+)', webpage, 'show id')
+                videos = self._extract_videos(brand, show_id=show_id)
+                show_title = self._search_regex(r'data-show-title="([^"]+)"', webpage, 'show title', fatal=False)
+                entries = []
+                for video in videos:
+                    entries.append(self.url_result(
+                        video['url'], 'Go', video.get('id'), video.get('title')))
+                entries.reverse()
+                return self.playlist_result(entries, show_id, show_title)
+        video_data = self._extract_videos(brand, video_id)[0]
+        video_id = video_data['id']

         title = video_data['title']
 
         formats = []
         title = video_data['title']
 
         formats = []


@@ -59,28 +126,60 @@ class GoIE(InfoExtractor):
             ext = determine_ext(asset_url)
             if ext == 'm3u8':
                 video_type = video_data.get('type')
             ext = determine_ext(asset_url)
             if ext == 'm3u8':
                 video_type = video_data.get('type')

-                if video_type == 'lf':
-                    entitlement = self._download_json(
-                        'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
-                        video_id, data=urlencode_postdata({
-                            'video_id': video_data['id'],
-                            'video_type': video_type,
-                            'brand': brand,
-                            'device': '001',
-                        }))
-                    errors = entitlement.get('errors', {}).get('errors', [])
-                    if errors:
-                        error_message = ', '.join([error['message'] for error in errors])
-                        raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
-                    asset_url += '?' + entitlement['uplynkData']['sessionKey']
+                data = {
+                    'video_id': video_data['id'],
+                    'video_type': video_type,
+                    'brand': brand,
+                    'device': '001',
+                }
+                if video_data.get('accesslevel') == '1':
+                    requestor_id = site_info.get('requestor_id', 'DisneyChannels')
+                    resource = site_info.get('resource_id') or self._get_mvpd_resource(
+                        requestor_id, title, video_id, None)
+                    auth = self._extract_mvpd_auth(
+                        url, video_id, requestor_id, resource)
+                    data.update({
+                        'token': auth,
+                        'token_type': 'ap',
+                        'adobe_requestor_id': requestor_id,
+                    })
+                else:
+                    self._initialize_geo_bypass({'countries': ['US']})
+                entitlement = self._download_json(
+                    'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
+                    video_id, data=urlencode_postdata(data))
+                errors = entitlement.get('errors', {}).get('errors', [])
+                if errors:
+                    for error in errors:
+                        if error.get('code') == 1002:
+                            self.raise_geo_restricted(
+                                error['message'], countries=['US'])
+                    error_message = ', '.join([error['message'] for error in errors])
+                    raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
+                asset_url += '?' + entitlement['uplynkData']['sessionKey']

                 formats.extend(self._extract_m3u8_formats(
                     asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False))
             else:
                 formats.extend(self._extract_m3u8_formats(
                     asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False))
             else:

-                formats.append({
+                f = {

                     'format_id': format_id,
                     'url': asset_url,
                     'ext': ext,
                     'format_id': format_id,
                     'url': asset_url,
                     'ext': ext,

-                })
+                }
+                if re.search(r'(?:/mp4/source/|_source\.mp4)', asset_url):
+                    f.update({
+                        'format_id': ('%s-' % format_id if format_id else '') + 'SOURCE',
+                        'preference': 1,
+                    })
+                else:
+                    mobj = re.search(r'/(\d+)x(\d+)/', asset_url)
+                    if mobj:
+                        height = int(mobj.group(2))
+                        f.update({
+                            'format_id': ('%s-' % format_id if format_id else '') + '%dP' % height,
+                            'width': int(mobj.group(1)),
+                            'height': height,
+                        })
+                formats.append(f)

         self._sort_formats(formats)
 
         subtitles = {}
         self._sort_formats(formats)
 
         subtitles = {}