]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/motherless.py
d/p/remove-autoupdate-mechanism.patch: Update patch with metadata at the top.
[youtubedl] / youtube_dl / extractor / motherless.py
index 97d5da626a7a5d2555ac3107eb89d1a4fd11b510..e24396e791cfddf88e53a34639e563b54795694e 100644 (file)
@@ -4,63 +4,77 @@ import datetime
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
+    ExtractorError,
+    InAdvancePagedList,
+    orderedSet,
     str_to_int,
     unified_strdate,
 )
 
 
 class MotherlessIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P<id>[A-Z0-9]+)'
-    _TESTS = [
-        {
-            'url': 'http://motherless.com/AC3FFE1',
-            'md5': '310f62e325a9fafe64f68c0bccb6e75f',
-            'info_dict': {
-                'id': 'AC3FFE1',
-                'ext': 'mp4',
-                'title': 'Fucked in the ass while playing PS3',
-                'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'],
-                'upload_date': '20100913',
-                'uploader_id': 'famouslyfuckedup',
-                'thumbnail': 're:http://.*\.jpg',
-                'age_limit': 18,
-            }
-        },
-        {
-            'url': 'http://motherless.com/532291B',
-            'md5': 'bc59a6b47d1f958e61fbd38a4d31b131',
-            'info_dict': {
-                'id': '532291B',
-                'ext': 'mp4',
-                'title': 'Amazing girl playing the omegle game, PERFECT!',
-                'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen', 'game', 'hairy'],
-                'upload_date': '20140622',
-                'uploader_id': 'Sulivana7x',
-                'thumbnail': 're:http://.*\.jpg',
-                'age_limit': 18,
-            }
+    _VALID_URL = r'https?://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P<id>[A-Z0-9]+)'
+    _TESTS = [{
+        'url': 'http://motherless.com/AC3FFE1',
+        'md5': '310f62e325a9fafe64f68c0bccb6e75f',
+        'info_dict': {
+            'id': 'AC3FFE1',
+            'ext': 'mp4',
+            'title': 'Fucked in the ass while playing PS3',
+            'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'],
+            'upload_date': '20100913',
+            'uploader_id': 'famouslyfuckedup',
+            'thumbnail': r're:http://.*\.jpg',
+            'age_limit': 18,
+        }
+    }, {
+        'url': 'http://motherless.com/532291B',
+        'md5': 'bc59a6b47d1f958e61fbd38a4d31b131',
+        'info_dict': {
+            'id': '532291B',
+            'ext': 'mp4',
+            'title': 'Amazing girl playing the omegle game, PERFECT!',
+            'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen',
+                           'game', 'hairy'],
+            'upload_date': '20140622',
+            'uploader_id': 'Sulivana7x',
+            'thumbnail': r're:http://.*\.jpg',
+            'age_limit': 18,
         },
-        {
-            'url': 'http://motherless.com/g/cosplay/633979F',
-            'md5': '0b2a43f447a49c3e649c93ad1fafa4a0',
-            'info_dict': {
-                'id': '633979F',
-                'ext': 'mp4',
-                'title': 'Turtlette',
-                'categories': ['superheroine heroine  superher'],
-                'upload_date': '20140827',
-                'uploader_id': 'shade0230',
-                'thumbnail': 're:http://.*\.jpg',
-                'age_limit': 18,
-            }
+        'skip': '404',
+    }, {
+        'url': 'http://motherless.com/g/cosplay/633979F',
+        'md5': '0b2a43f447a49c3e649c93ad1fafa4a0',
+        'info_dict': {
+            'id': '633979F',
+            'ext': 'mp4',
+            'title': 'Turtlette',
+            'categories': ['superheroine heroine  superher'],
+            'upload_date': '20140827',
+            'uploader_id': 'shade0230',
+            'thumbnail': r're:http://.*\.jpg',
+            'age_limit': 18,
         }
-    ]
+    }, {
+        # no keywords
+        'url': 'http://motherless.com/8B4BBC1',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
+        if any(p in webpage for p in (
+                '<title>404 - MOTHERLESS.COM<',
+                ">The page you're looking for cannot be found.<")):
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
+        if '>The content you are trying to view is for friends only.' in webpage:
+            raise ExtractorError('Video %s is for friends only' % video_id, expected=True)
+
         title = self._html_search_regex(
             r'id="view-upload-title">\s+([^<]+)<', webpage, 'title')
         video_url = self._html_search_regex(
@@ -86,7 +100,7 @@ class MotherlessIE(InfoExtractor):
             r'"thumb-member-username">\s+<a href="/m/([^"]+)"',
             webpage, 'uploader_id')
 
-        categories = self._html_search_meta('keywords', webpage)
+        categories = self._html_search_meta('keywords', webpage, default=None)
         if categories:
             categories = [cat.strip() for cat in categories.split(',')]
 
@@ -103,3 +117,86 @@ class MotherlessIE(InfoExtractor):
             'age_limit': age_limit,
             'url': video_url,
         }
+
+
+class MotherlessGroupIE(InfoExtractor):
+    _VALID_URL = 'https?://(?:www\.)?motherless\.com/gv?/(?P<id>[a-z0-9_]+)'
+    _TESTS = [{
+        'url': 'http://motherless.com/g/movie_scenes',
+        'info_dict': {
+            'id': 'movie_scenes',
+            'title': 'Movie Scenes',
+            'description': 'Hot and sexy scenes from "regular" movies... '
+                           'Beautiful actresses fully nude... A looot of '
+                           'skin! :)Enjoy!',
+        },
+        'playlist_mincount': 662,
+    }, {
+        'url': 'http://motherless.com/gv/sex_must_be_funny',
+        'info_dict': {
+            'id': 'sex_must_be_funny',
+            'title': 'Sex must be funny',
+            'description': 'Sex can be funny. Wide smiles,laugh, games, fun of '
+                           'any kind!'
+        },
+        'playlist_mincount': 9,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return (False if MotherlessIE.suitable(url)
+                else super(MotherlessGroupIE, cls).suitable(url))
+
+    def _extract_entries(self, webpage, base):
+        entries = []
+        for mobj in re.finditer(
+                r'href="(?P<href>/[^"]+)"[^>]*>(?:\s*<img[^>]+alt="[^-]+-\s(?P<title>[^"]+)")?',
+                webpage):
+            video_url = compat_urlparse.urljoin(base, mobj.group('href'))
+            if not MotherlessIE.suitable(video_url):
+                continue
+            video_id = MotherlessIE._match_id(video_url)
+            title = mobj.group('title')
+            entries.append(self.url_result(
+                video_url, ie=MotherlessIE.ie_key(), video_id=video_id,
+                video_title=title))
+        # Alternative fallback
+        if not entries:
+            entries = [
+                self.url_result(
+                    compat_urlparse.urljoin(base, '/' + video_id),
+                    ie=MotherlessIE.ie_key(), video_id=video_id)
+                for video_id in orderedSet(re.findall(
+                    r'data-codename=["\']([A-Z0-9]+)', webpage))]
+        return entries
+
+    def _real_extract(self, url):
+        group_id = self._match_id(url)
+        page_url = compat_urlparse.urljoin(url, '/gv/%s' % group_id)
+        webpage = self._download_webpage(page_url, group_id)
+        title = self._search_regex(
+            r'<title>([\w\s]+\w)\s+-', webpage, 'title', fatal=False)
+        description = self._html_search_meta(
+            'description', webpage, fatal=False)
+        page_count = self._int(self._search_regex(
+            r'(\d+)</(?:a|span)><(?:a|span)[^>]+>\s*NEXT',
+            webpage, 'page_count'), 'page_count')
+        PAGE_SIZE = 80
+
+        def _get_page(idx):
+            webpage = self._download_webpage(
+                page_url, group_id, query={'page': idx + 1},
+                note='Downloading page %d/%d' % (idx + 1, page_count)
+            )
+            for entry in self._extract_entries(webpage, url):
+                yield entry
+
+        playlist = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
+
+        return {
+            '_type': 'playlist',
+            'id': group_id,
+            'title': title,
+            'description': description,
+            'entries': playlist
+        }