Annotate changelog with bug being closed.

[youtubedl] / youtube_dl / extractor / spankbang.py

diff --git a/youtube_dl/extractor/spankbang.py b/youtube_dl/extractor/spankbang.py
index 123c33ac36e275d8b624c8830153235c3a4ef338..f11d728caac1e73e9fe746a87d95f4261fa11c0d 100644 (file)
--- a/youtube_dl/extractor/spankbang.py
+++ b/youtube_dl/extractor/spankbang.py
@@ -3,10 +3,19 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

+from ..utils import (
+    ExtractorError,
+    orderedSet,
+    parse_duration,
+    parse_resolution,
+    str_to_int,
+    url_or_none,
+    urlencode_postdata,
+)

 
 
 class SpankBangIE(InfoExtractor):
 
 
 class SpankBangIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:(?:www|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
+    _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)\b'

     _TESTS = [{
         'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
         'md5': '1cc433e1d6aa14bc376535b8679302f7',
     _TESTS = [{
         'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
         'md5': '1cc433e1d6aa14bc376535b8679302f7',


@@ -14,7 +23,7 @@ class SpankBangIE(InfoExtractor):
             'id': '3vvn',
             'ext': 'mp4',
             'title': 'fantasy solo',
             'id': '3vvn',
             'ext': 'mp4',
             'title': 'fantasy solo',

-            'description': 'Watch fantasy solo free HD porn video - 05 minutes - dillion harper masturbates on a bed free adult movies.',
+            'description': 'dillion harper masturbates on a bed',

             'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'silly2587',
             'age_limit': 18,
             'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'silly2587',
             'age_limit': 18,


@@ -23,32 +32,99 @@ class SpankBangIE(InfoExtractor):
         # 480p only
         'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
         'only_matching': True,
         # 480p only
         'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
         'only_matching': True,

+    }, {
+        # no uploader
+        'url': 'http://spankbang.com/lklg/video/sex+with+anyone+wedding+edition+2',
+        'only_matching': True,
+    }, {
+        # mobile page
+        'url': 'http://m.spankbang.com/1o2de/video/can+t+remember+her+name',
+        'only_matching': True,
+    }, {
+        # 4k
+        'url': 'https://spankbang.com/1vwqx/video/jade+kush+solo+4k',
+        'only_matching': True,
+    }, {
+        'url': 'https://m.spankbang.com/3vvn/play/fantasy+solo/480p/',
+        'only_matching': True,
+    }, {
+        'url': 'https://m.spankbang.com/3vvn/play',
+        'only_matching': True,
+    }, {
+        'url': 'https://spankbang.com/2y3td/embed/',
+        '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)

-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            url.replace('/%s/embed' % video_id, '/%s/video' % video_id),
+            video_id, headers={'Cookie': 'country=US'})

 
 

-        stream_key = self._html_search_regex(
-            r'''var\s+stream_key\s*=\s*['"](.+?)['"]''',
-            webpage, 'stream key')
+        if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
+            raise ExtractorError(
+                'Video %s is not available' % video_id, expected=True)
+
+        formats = []
+
+        def extract_format(format_id, format_url):
+            f_url = url_or_none(format_url)
+            if not f_url:
+                return
+            f = parse_resolution(format_id)
+            f.update({
+                'url': f_url,
+                'format_id': format_id,
+            })
+            formats.append(f)
+
+        STREAM_URL_PREFIX = 'stream_url_'
+
+        for mobj in re.finditer(
+                r'%s(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2'
+                % STREAM_URL_PREFIX, webpage):
+            extract_format(mobj.group('id', 'url'))
+
+        if not formats:
+            stream_key = self._search_regex(
+                r'data-streamkey\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
+                webpage, 'stream key', group='value')
+
+            sb_csrf_session = self._get_cookies(
+                'https://spankbang.com')['sb_csrf_session'].value
+
+            stream = self._download_json(
+                'https://spankbang.com/api/videos/stream', video_id,
+                'Downloading stream JSON', data=urlencode_postdata({
+                    'id': stream_key,
+                    'data': 0,
+                    'sb_csrf_session': sb_csrf_session,
+                }), headers={
+                    'Referer': url,
+                    'X-CSRFToken': sb_csrf_session,
+                })
+
+            for format_id, format_url in stream.items():
+                if format_id.startswith(STREAM_URL_PREFIX):
+                    extract_format(
+                        format_id[len(STREAM_URL_PREFIX):], format_url)

 
 

-        formats = [{
-            'url': 'http://spankbang.com/_%s/%s/title/%sp__mp4' % (video_id, stream_key, height),
-            'ext': 'mp4',
-            'format_id': '%sp' % height,
-            'height': int(height),
-        } for height in re.findall(r'<(?:span|li|p)[^>]+[qb]_(\d+)p', webpage)]
-        self._check_formats(formats, video_id)

         self._sort_formats(formats)
 
         title = self._html_search_regex(
             r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')
         self._sort_formats(formats)
 
         title = self._html_search_regex(
             r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')

-        description = self._og_search_description(webpage)
+        description = self._search_regex(
+            r'<div[^>]+\bclass=["\']bottom[^>]+>\s*<p>[^<]*</p>\s*<p>([^<]+)',
+            webpage, 'description', fatal=False)

         thumbnail = self._og_search_thumbnail(webpage)
         uploader = self._search_regex(
             r'class="user"[^>]*><img[^>]+>([^<]+)',
         thumbnail = self._og_search_thumbnail(webpage)
         uploader = self._search_regex(
             r'class="user"[^>]*><img[^>]+>([^<]+)',

-            webpage, 'uploader', fatal=False)
+            webpage, 'uploader', default=None)
+        duration = parse_duration(self._search_regex(
+            r'<div[^>]+\bclass=["\']right_side[^>]+>\s*<span>([^<]+)',
+            webpage, 'duration', fatal=False))
+        view_count = str_to_int(self._search_regex(
+            r'([\d,.]+)\s+plays', webpage, 'view count', fatal=False))

 
         age_limit = self._rta_search(webpage)
 
 
         age_limit = self._rta_search(webpage)
 


@@ -58,6 +134,38 @@ class SpankBangIE(InfoExtractor):
             'description': description,
             'thumbnail': thumbnail,
             'uploader': uploader,
             'description': description,
             'thumbnail': thumbnail,
             'uploader': uploader,

+            'duration': duration,
+            'view_count': view_count,

             'formats': formats,
             'age_limit': age_limit,
         }
             'formats': formats,
             'age_limit': age_limit,
         }

+
+
+class SpankBangPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/[^/]+'
+    _TEST = {
+        'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties',
+        'info_dict': {
+            'id': 'ug0k',
+            'title': 'Big Ass Titties',
+        },
+        'playlist_mincount': 50,
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            url, playlist_id, headers={'Cookie': 'country=US; mobile=on'})
+
+        entries = [self.url_result(
+            'https://spankbang.com/%s/video' % video_id,
+            ie=SpankBangIE.ie_key(), video_id=video_id)
+            for video_id in orderedSet(re.findall(
+                r'<a[^>]+\bhref=["\']/?([\da-z]+)/play/', webpage))]
+
+        title = self._html_search_regex(
+            r'<h1>([^<]+)\s+playlist</h1>', webpage, 'playlist title',
+            fatal=False)
+
+        return self.playlist_result(entries, playlist_id, title)