debian/control: Update list of extractors/supported sites.

[youtubedl] / youtube_dl / extractor / spankbang.py

diff --git a/youtube_dl/extractor/spankbang.py b/youtube_dl/extractor/spankbang.py
index 67500b69c1b8b076f147c5da3afb3df8cc5bd6fd..e040ada29b24542582f72f08f31b843d928af251 100644 (file)
--- a/youtube_dl/extractor/spankbang.py
+++ b/youtube_dl/extractor/spankbang.py
@@ -5,14 +5,18 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,

+    merge_dicts,
+    orderedSet,

     parse_duration,
     parse_resolution,
     str_to_int,
     parse_duration,
     parse_resolution,
     str_to_int,

+    url_or_none,
+    urlencode_postdata,

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

-    _VALID_URL = r'https?://(?:(?:www|m|[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',


@@ -23,6 +27,8 @@ class SpankBangIE(InfoExtractor):
             'description': 'dillion harper masturbates on a bed',
             'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'silly2587',
             'description': 'dillion harper masturbates on a bed',
             'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'silly2587',

+            'timestamp': 1422571989,
+            'upload_date': '20150129',

             'age_limit': 18,
         }
     }, {
             'age_limit': 18,
         }
     }, {


@@ -41,51 +47,98 @@ class SpankBangIE(InfoExtractor):
         # 4k
         'url': 'https://spankbang.com/1vwqx/video/jade+kush+solo+4k',
         '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, headers={
-            'Cookie': 'country=US'
-        })
+        webpage = self._download_webpage(
+            url.replace('/%s/embed' % video_id, '/%s/video' % video_id),
+            video_id, headers={'Cookie': 'country=US'})

 
         if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
             raise ExtractorError(
                 'Video %s is not available' % video_id, expected=True)
 
         formats = []
 
         if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
             raise ExtractorError(
                 'Video %s is not available' % video_id, expected=True)
 
         formats = []

-        for mobj in re.finditer(
-                r'stream_url_(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2',
-                webpage):
-            format_id, format_url = mobj.group('id', 'url')
+
+        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({
             f = parse_resolution(format_id)
             f.update({

-                'url': format_url,
+                'url': f_url,

                 'format_id': format_id,
             })
             formats.append(f)
                 '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):
+                    if format_url and isinstance(format_url, list):
+                        format_url = format_url[0]
+                    extract_format(
+                        format_id[len(STREAM_URL_PREFIX):], format_url)
+

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

+        info = self._search_json_ld(webpage, video_id, default={})
+

         title = self._html_search_regex(
         title = self._html_search_regex(

-            r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')
+            r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title', default=None)

         description = self._search_regex(
             r'<div[^>]+\bclass=["\']bottom[^>]+>\s*<p>[^<]*</p>\s*<p>([^<]+)',
         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[^>]+>([^<]+)',
+            webpage, 'description', default=None)
+        thumbnail = self._og_search_thumbnail(webpage, default=None)
+        uploader = self._html_search_regex(
+            (r'(?s)<li[^>]+class=["\']profile[^>]+>(.+?)</a>',
+             r'class="user"[^>]*><img[^>]+>([^<]+)'),

             webpage, 'uploader', default=None)
         duration = parse_duration(self._search_regex(
             r'<div[^>]+\bclass=["\']right_side[^>]+>\s*<span>([^<]+)',
             webpage, 'uploader', default=None)
         duration = parse_duration(self._search_regex(
             r'<div[^>]+\bclass=["\']right_side[^>]+>\s*<span>([^<]+)',

-            webpage, 'duration', fatal=False))
+            webpage, 'duration', default=None))

         view_count = str_to_int(self._search_regex(
         view_count = str_to_int(self._search_regex(

-            r'([\d,.]+)\s+plays', webpage, 'view count', fatal=False))
+            r'([\d,.]+)\s+plays', webpage, 'view count', default=None))

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

-        return {
+        return merge_dicts({

             'id': video_id,
             'id': video_id,

-            'title': title,
+            'title': title or video_id,

             'description': description,
             'thumbnail': thumbnail,
             'uploader': uploader,
             'description': description,
             'thumbnail': thumbnail,
             'uploader': uploader,


@@ -93,4 +146,35 @@ class SpankBangIE(InfoExtractor):
             'view_count': view_count,
             'formats': formats,
             'age_limit': age_limit,
             'view_count': view_count,
             'formats': formats,
             'age_limit': age_limit,

-        }
+        }, info
+        )
+
+
+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)