Merge 14a087ec62 into c5098961b0

* improve title extraction
* add uploader_id
* update test
* but don't check file md5

youtube_dl/extractor/extractors.py

@@ -1179,6 +1179,7 @@ from .southpark import (
 from .spankbang import (
     SpankBangIE,
     SpankBangPlaylistIE,
+    SpankBangListIE,
 )
 from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE

youtube_dl/extractor/spankbang.py

@@ -1,11 +1,17 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
+import itertools
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
     determine_ext,
+    extract_attributes,
     ExtractorError,
+    get_element_by_class,
+    get_element_by_id,
     merge_dicts,
     parse_duration,
     parse_resolution,
@@ -26,19 +32,24 @@ class SpankBangIE(InfoExtractor):
                         )
                     '''
     _TESTS = [{
-        'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
+        'url': 'https://spankbang.com/56b3d/video/the+slut+maker+hmv',
-        'md5': '1cc433e1d6aa14bc376535b8679302f7',
+        'md5': '5039ba9d26f6124a7fdea6df2f21e765',
         'info_dict': {
-            'id': '3vvn',
+            'id': '56b3d',
             'ext': 'mp4',
-            'title': 'fantasy solo',
+            'title': 'The Slut Maker HMV',
-            'description': 'dillion harper masturbates on a bed',
+            'description': 'Girls getting converted into cock slaves.',
             'thumbnail': r're:^https?://.*\.jpg$',
-            'uploader': 'silly2587',
+            'uploader': 'Mindself',
-            'timestamp': 1422571989,
+            'uploader_id': 'mindself',
-            'upload_date': '20150129',
+            'timestamp': 1617109572,
+            'upload_date': '20210330',
             'age_limit': 18,
-        }
+        },
+        'params': {
+            # adaptive download
+            'skip_download': True,
+        },
     }, {
         # 480p only
         'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
@@ -134,15 +145,15 @@ class SpankBangIE(InfoExtractor):
         info = self._search_json_ld(webpage, video_id, default={})
 
         title = self._html_search_regex(
-            r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title', default=None)
+            r'(?s)<h1[^>]+\btitle=["\']([^"]+)["\']>', webpage, 'title', default=None)
         description = self._search_regex(
             r'<div[^>]+\bclass=["\']bottom[^>]+>\s*<p>[^<]*</p>\s*<p>([^<]+)',
             webpage, 'description', default=None)
         thumbnail = self._og_search_thumbnail(webpage, default=None)
         uploader = self._html_search_regex(
-            (r'(?s)<li[^>]+class=["\']profile[^>]+>(.+?)</a>',
+            r'<svg[^>]+\bclass="(?:[^"]*?user[^"]*?)">.*?</svg>([^<]+)', webpage, 'uploader', default=None)
-             r'class="user"[^>]*><img[^>]+>([^<]+)'),
+        uploader_id = self._html_search_regex(
-            webpage, 'uploader', default=None)
+            r'<a[^>]+href="/profile/([^"]+)"', webpage, 'uploader_id', default=None)
         duration = parse_duration(self._search_regex(
             r'<div[^>]+\bclass=["\']right_side[^>]+>\s*<span>([^<]+)',
             webpage, 'duration', default=None))
@@ -157,6 +168,7 @@ class SpankBangIE(InfoExtractor):
             'description': description,
             'thumbnail': thumbnail,
             'uploader': uploader,
+            'uploader_id': uploader_id,
             'duration': duration,
             'view_count': view_count,
             'formats': formats,
@@ -167,32 +179,166 @@ class SpankBangIE(InfoExtractor):
 
 class SpankBangPlaylistIE(InfoExtractor):
     _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/(?P<display_id>[^/]+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties',
         'info_dict': {
             'id': 'ug0k',
             'title': 'Big Ass Titties',
+            'description': 'md5:65b01bb13a9276cf172a67a41304bafd',
         },
-        'playlist_mincount': 40,
+        'playlist_mincount': 35,
-    }
+    }, {
+        # pagination required
+        'url': 'https://spankbang.com/51wxk/playlist/dance',
+        'info_dict': {
+            'id': '51wxk',
+            'title': 'Dance',
+            'description': 'md5:7aae6991c65d561a9319ecab31f857e2',
+        },
+        'playlist_mincount': 60,
+    }]
+
+    def _entries(self, url, playlist_id, webpage=None):
+        for ii in itertools.count(1):
+            if not webpage:
+                webpage = self._download_webpage(
+                    url, playlist_id,
+                    note='Downloading playlist page %d' % (ii, ),
+                    fatal=False)
+            if not webpage:
+                break
+            # search <main id="container">...</main>.innerHTML
+            for mobj in re.finditer(
+                    r'''<a\b[^>]*?\bclass\s*=\s*('|")(?:(?:(?!\1).)+?\s)?\s*thumb\b[^>]*>''',
+                    get_element_by_id('container', webpage) or webpage):
+                item_url = extract_attributes(mobj.group(0)).get('href')
+                if item_url:
+                    yield urljoin(url, item_url)
+            next_url = self._search_regex(
+                r'''\bhref\s*=\s*(["'])(?P<path>(?!\1).+?)/?\1''',
+                get_element_by_class('next', webpage) or '',
+                'continuation page', group='path', default=None)
+            if next_url is None or next_url in url:
+                break
+            url, webpage = urljoin(url, next_url), None
+            p_url = compat_urlparse.urlparse(url)
+            url = compat_urlparse.urlunparse(p_url._replace(path=p_url.path + '/'))
+
+    def _get_title(self, list_id, webpage, url):
+        return self._html_search_regex(
+            r'<h1>([^<]+)\s+playlist\s*<', webpage, 'playlist title',
+            fatal=False) or re.sub(r'(\w)\+(\w)', r'\1 \2', list_id).title()
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        mobj = re.match(self._VALID_URL, url).groupdict()
-        playlist_id = mobj.group('id')
+        playlist_id = mobj['id']
-        display_id = mobj.group('display_id')
+        display_id = mobj.get('display_id') or playlist_id
+        related = mobj.get('related')
 
-        webpage = self._download_webpage(
+        webpage = self._download_webpage(url, playlist_id)
-            url, playlist_id, headers={'Cookie': 'country=US; mobile=on'})
 
-        entries = [self.url_result(
+        def get_title():
-            urljoin(url, mobj.group('path')),
+            t = self._get_title(display_id, webpage, url)
-            ie=SpankBangIE.ie_key(), video_id=mobj.group('id'))
+            if related:
-            for mobj in re.finditer(
+                t = '%s of %s' % (related.title(), t, )
-                r'<a[^>]+\bhref=(["\'])(?P<path>/?[\da-z]+-(?P<id>[\da-z]+)/playlist/%s(?:(?!\1).)*)\1'
+            return t
-                % re.escape(display_id), webpage)]
 
-        title = self._html_search_regex(
+        result = self.playlist_from_matches(self._entries(url, playlist_id, webpage), playlist_id, get_title(), ie=SpankBangIE.ie_key())
-            r'<h1>([^<]+)\s+playlist\s*<', webpage, 'playlist title',
+        description = self._html_search_meta(('description', 'og:description'), webpage)
-            fatal=False)
+        if description:
+            result['description'] = description
+        return result
 
-        return self.playlist_result(entries, playlist_id, title)
+
+class SpankBangListIE(SpankBangPlaylistIE):
+    _VALID_URL = r'''(?x)
+            https?://(?:[^/]+\.)?spankbang\.com/
+                (?:
+                    category|tag|s|
+                    [^/]+/channel|
+                    [^/]+/pornstar|
+                    (?P<profile>profile)
+                )/(?P<id>[^/?#]+)(?(profile)/(?P<related>videos|likes|playlists)?|)'''
+    _TESTS = [{
+        'url': 'https://spankbang.com/category/striptease/?p=d',
+        'info_dict': {
+            'id': 'striptease',
+            'title': 'Category: Striptease Porn (Jun 2022) - Joi & Strip (today)',
+            'description': 'md5:d4580b5fc1e8fae9f627178964989959',
+        },
+        'playlist_mincount': 1,
+    }, {
+        'url': 'https://spankbang.com/tag/monty/',
+        'info_dict': {
+            'id': 'monty',
+            'title': 'Tag: Monty Porn - Jenni Lee & British',
+            'description': 'md5:93535d53455f10b934034bfb9562de35',
+        },
+        'playlist_mincount': 40,
+    }, {
+        'url': 'https://spankbang.com/s/silly/?q=fhd&d=10',
+        'info_dict': {
+            'id': 'silly',
+            'title': 'Search: Silly HD Porn - Chubby Teens & Cum Swallow (FHD, 10+ mins)',
+            'description': 'md5:a241b24847f1efd7cc3cfc4ef2b22429',
+        },
+        'playlist_mincount': 20,
+    }, {
+        'url': 'https://spankbang.com/er/channel/purexxxfilms/?o=new',
+        'info_dict': {
+            'id': 'purexxxfilms',
+            'title': 'PureXXXFilms Channel (new)',
+            'description': 'md5:bb61fbf523511f3bd15aea0360bdbdc0',
+        },
+        'playlist_mincount': 65,
+    }, {
+        'url': 'https://spankbang.com/5pj/pornstar/promise/',
+        'info_dict': {
+            'id': 'promise',
+            'title': 'Promise Pornstar Page',
+            'description': 'md5:ff08a6ac2d6cd1225f0fae74ac896d63',
+        },
+        'playlist_mincount': 90,
+    }, {
+        'url': 'https://spankbang.com/profile/migouche/likes',
+        'info_dict': {
+            'id': 'migouche',
+            'title': 'Likes of migouche Profile',
+            'description': 'md5:b97540209879a62cadf2af6b0934bbc9',
+        },
+        'playlist_mincount': 2,
+    },
+    ]
+
+    def _get_title(self, list_id, webpage, url):
+        title = (
+            self._og_search_title(webpage, default=None)
+            or self._html_search_regex(
+                r'<title\b[^>]*>([^<]+)</title', webpage, 'channel title',
+                fatal=False))
+        if title:
+            title = re.sub(r'\s*(?:&\s+(?:Porn\s+))?(?:Videos\s+)?[@-]\s*SpankBang\s*$', '', title)
+        title = title or re.sub(r'(\w)\+(\w)', r'\1 \2', list_id).title()
+        qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+        quals = []
+        for q in ('o', 'q', 'd', 'p'):
+            v = qs.get(q, [None])[-1]
+            if not v:
+                continue
+            if q == 'q':
+                v = v.upper()
+            elif q == 'd':
+                v += '+ mins'
+            elif q == 'p':
+                v = {'d': 'today', 'w': 'this week', 'm': 'this month', 'y': 'this year'}.get(v, v)
+            quals.append(v)
+        quals = ', '.join(quals)
+        if quals:
+            title += ' (%s)' % (quals, )
+        m = re.search(r'/(category|tag|s)/', url)
+        if m:
+            pfx = m.group(1)
+            if pfx == 's':
+                pfx = 'search'
+            title = '%s: %s' % (pfx.title(), title)
+        return title