Merge pull request #3 from unit193/master

[youtubedl] / youtube_dl / extractor / xhamster.py

diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index 36a8c98407bcaf8466660279f2e444df48083a3a..a5b94d2794166d452464b728ec40b2b258459c64 100644 (file)
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -1,36 +1,56 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

+import itertools

 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

+from ..compat import compat_str

 from ..utils import (
 from ..utils import (

+    clean_html,
+    determine_ext,

     dict_get,
     dict_get,

+    extract_attributes,
+    ExtractorError,

     int_or_none,
     parse_duration,
     int_or_none,
     parse_duration,

+    try_get,

     unified_strdate,
     unified_strdate,

+    url_or_none,

 )
 
 
 class XHamsterIE(InfoExtractor):
 )
 
 
 class XHamsterIE(InfoExtractor):

-    _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.*?)\.html(?:\?.*)?'
+    _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster[27]\.com)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:.+?\.)?%s/
+                        (?:
+                            movies/(?P<id>\d+)/(?P<display_id>[^/]*)\.html|
+                            videos/(?P<display_id_2>[^/]*)-(?P<id_2>\d+)
+                        )
+                    ''' % _DOMAINS

     _TESTS = [{
     _TESTS = [{

-        'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
-        'md5': '8281348b8d3c53d39fffb377d24eac4e',
+        'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
+        'md5': '98b4687efb1ffd331c4197854dc09e8f',

         'info_dict': {
             'id': '1509445',
         'info_dict': {
             'id': '1509445',

+            'display_id': 'femaleagent-shy-beauty-takes-the-bait',

             'ext': 'mp4',
             'title': 'FemaleAgent Shy beauty takes the bait',
             'ext': 'mp4',
             'title': 'FemaleAgent Shy beauty takes the bait',

+            'timestamp': 1350194821,

             'upload_date': '20121014',
             'uploader': 'Ruseful2011',
             'duration': 893,
             'age_limit': 18,
         },
     }, {
             'upload_date': '20121014',
             'uploader': 'Ruseful2011',
             'duration': 893,
             'age_limit': 18,
         },
     }, {

-        'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
+        'url': 'https://xhamster.com/videos/britney-spears-sexy-booty-2221348?hd=',

         'info_dict': {
             'id': '2221348',
         'info_dict': {
             'id': '2221348',

+            'display_id': 'britney-spears-sexy-booty',

             'ext': 'mp4',
             'title': 'Britney Spears  Sexy Booty',
             'ext': 'mp4',
             'title': 'Britney Spears  Sexy Booty',

+            'timestamp': 1379123460,

             'upload_date': '20130914',
             'uploader': 'jojo747400',
             'duration': 200,
             'upload_date': '20130914',
             'uploader': 'jojo747400',
             'duration': 200,


@@ -40,12 +60,13 @@ class XHamsterIE(InfoExtractor):
             'skip_download': True,
         },
     }, {
             'skip_download': True,
         },
     }, {

-        # empty seo
+        # empty seo, unavailable via new URL schema

         'url': 'http://xhamster.com/movies/5667973/.html',
         'info_dict': {
             'id': '5667973',
             'ext': 'mp4',
             'title': '....',
         'url': 'http://xhamster.com/movies/5667973/.html',
         'info_dict': {
             'id': '5667973',
             'ext': 'mp4',
             'title': '....',

+            'timestamp': 1454948101,

             'upload_date': '20160208',
             'uploader': 'parejafree',
             'duration': 72,
             'upload_date': '20160208',
             'uploader': 'parejafree',
             'duration': 72,


@@ -54,29 +75,129 @@ class XHamsterIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
         'params': {
             'skip_download': True,
         },

+    }, {
+        # mobile site
+        'url': 'https://m.xhamster.com/videos/cute-teen-jacqueline-solo-masturbation-8559111',
+        'only_matching': True,

     }, {
         'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
         'only_matching': True,
     }, {
         'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
         'only_matching': True,

+    }, {
+        # This video is visible for marcoalfa123456's friends only
+        'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
+        'only_matching': True,
+    }, {
+        # new URL schema
+        'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
+        'only_matching': True,
+    }, {
+        'url': 'https://xhamster.one/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
+        'only_matching': True,
+    }, {
+        'url': 'https://xhamster.desi/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
+        'only_matching': True,
+    }, {
+        'url': 'https://xhamster2.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
+        'only_matching': True,
+    }, {
+        'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
+        'only_matching': True,

     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):

-        def extract_video_url(webpage, name):
-            return self._search_regex(
-                [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
-                 r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
-                 r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
-                webpage, name, group='mp4')
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id') or mobj.group('id_2')
+        display_id = mobj.group('display_id') or mobj.group('display_id_2')

 
 

-        def is_hd(webpage):
-            return '<div class=\'icon iconHD\'' in webpage
+        desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
+        webpage = self._download_webpage(desktop_url, video_id)

 
 

-        mobj = re.match(self._VALID_URL, url)
+        error = self._html_search_regex(
+            r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
+            webpage, 'error', default=None)
+        if error:
+            raise ExtractorError(error, expected=True)
+
+        age_limit = self._rta_search(webpage)

 
 

-        video_id = mobj.group('id')
-        seo = mobj.group('seo')
-        proto = mobj.group('proto')
-        mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
-        webpage = self._download_webpage(mrss_url, video_id)
+        def get_height(s):
+            return int_or_none(self._search_regex(
+                r'^(\d+)[pP]', s, 'height', default=None))
+
+        initials = self._parse_json(
+            self._search_regex(
+                r'window\.initials\s*=\s*({.+?})\s*;\s*\n', webpage, 'initials',
+                default='{}'),
+            video_id, fatal=False)
+        if initials:
+            video = initials['videoModel']
+            title = video['title']
+            formats = []
+            for format_id, formats_dict in video['sources'].items():
+                if not isinstance(formats_dict, dict):
+                    continue
+                for quality, format_item in formats_dict.items():
+                    if format_id == 'download':
+                        # Download link takes some time to be generated,
+                        # skipping for now
+                        continue
+                        if not isinstance(format_item, dict):
+                            continue
+                        format_url = format_item.get('link')
+                        filesize = int_or_none(
+                            format_item.get('size'), invscale=1000000)
+                    else:
+                        format_url = format_item
+                        filesize = None
+                    format_url = url_or_none(format_url)
+                    if not format_url:
+                        continue
+                    formats.append({
+                        'format_id': '%s-%s' % (format_id, quality),
+                        'url': format_url,
+                        'ext': determine_ext(format_url, 'mp4'),
+                        'height': get_height(quality),
+                        'filesize': filesize,
+                    })
+            self._sort_formats(formats)
+
+            categories_list = video.get('categories')
+            if isinstance(categories_list, list):
+                categories = []
+                for c in categories_list:
+                    if not isinstance(c, dict):
+                        continue
+                    c_name = c.get('name')
+                    if isinstance(c_name, compat_str):
+                        categories.append(c_name)
+            else:
+                categories = None
+
+            return {
+                'id': video_id,
+                'display_id': display_id,
+                'title': title,
+                'description': video.get('description'),
+                'timestamp': int_or_none(video.get('created')),
+                'uploader': try_get(
+                    video, lambda x: x['author']['name'], compat_str),
+                'thumbnail': video.get('thumbURL'),
+                'duration': int_or_none(video.get('duration')),
+                'view_count': int_or_none(video.get('views')),
+                'like_count': int_or_none(try_get(
+                    video, lambda x: x['rating']['likes'], int)),
+                'dislike_count': int_or_none(try_get(
+                    video, lambda x: x['rating']['dislikes'], int)),
+                'comment_count': int_or_none(video.get('views')),
+                'age_limit': age_limit,
+                'categories': categories,
+                'formats': formats,
+            }
+
+        # Old layout fallback

 
         title = self._html_search_regex(
             [r'<h1[^>]*>([^<]+)</h1>',
 
         title = self._html_search_regex(
             [r'<h1[^>]*>([^<]+)</h1>',


@@ -84,6 +205,39 @@ class XHamsterIE(InfoExtractor):
              r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
             webpage, 'title')
 
              r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
             webpage, 'title')
 

+        formats = []
+        format_urls = set()
+
+        sources = self._parse_json(
+            self._search_regex(
+                r'sources\s*:\s*({.+?})\s*,?\s*\n', webpage, 'sources',
+                default='{}'),
+            video_id, fatal=False)
+        for format_id, format_url in sources.items():
+            format_url = url_or_none(format_url)
+            if not format_url:
+                continue
+            if format_url in format_urls:
+                continue
+            format_urls.add(format_url)
+            formats.append({
+                'format_id': format_id,
+                'url': format_url,
+                'height': get_height(format_id),
+            })
+
+        video_url = self._search_regex(
+            [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
+             r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
+             r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
+            webpage, 'video url', group='mp4', default=None)
+        if video_url and video_url not in format_urls:
+            formats.append({
+                'url': video_url,
+            })
+
+        self._sort_formats(formats)
+

         # Only a few videos have an description
         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
         description = mobj.group(1) if mobj else None
         # Only a few videos have an description
         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
         description = mobj.group(1) if mobj else None


@@ -93,56 +247,38 @@ class XHamsterIE(InfoExtractor):
             webpage, 'upload date', fatal=False))
 
         uploader = self._html_search_regex(
             webpage, 'upload date', fatal=False))
 
         uploader = self._html_search_regex(

-            r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+href=["\'].+?xhamster\.com/user/[^>]+>(?P<uploader>.+?)</a>',
+            r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',

             webpage, 'uploader', default='anonymous')
 
         thumbnail = self._search_regex(
             webpage, 'uploader', default='anonymous')
 
         thumbnail = self._search_regex(

-            [r'''thumb\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
-             r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
+            [r'''["']thumbUrl["']\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
+             r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],

             webpage, 'thumbnail', fatal=False, group='thumbnail')
 
         duration = parse_duration(self._search_regex(
             webpage, 'thumbnail', fatal=False, group='thumbnail')
 
         duration = parse_duration(self._search_regex(

-            r'Runtime:\s*</span>\s*([\d:]+)', webpage,
+            [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
+             r'Runtime:\s*</span>\s*([\d:]+)'], webpage,

             'duration', fatal=False))
 
         view_count = int_or_none(self._search_regex(
             r'content=["\']User(?:View|Play)s:(\d+)',
             webpage, 'view count', fatal=False))
 
             'duration', fatal=False))
 
         view_count = int_or_none(self._search_regex(
             r'content=["\']User(?:View|Play)s:(\d+)',
             webpage, 'view count', fatal=False))
 

-        mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
+        mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)

         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 
         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
         comment_count = mobj.group('commentcount') if mobj else 0
 
         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 
         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
         comment_count = mobj.group('commentcount') if mobj else 0
 

-        age_limit = self._rta_search(webpage)
-
-        hd = is_hd(webpage)
-
-        format_id = 'hd' if hd else 'sd'
-
-        video_url = extract_video_url(webpage, format_id)
-        formats = [{
-            'url': video_url,
-            'format_id': 'hd' if hd else 'sd',
-            'preference': 1,
-        }]
-
-        if not hd:
-            mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
-            webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
-            if is_hd(webpage):
-                video_url = extract_video_url(webpage, 'hd')
-                formats.append({
-                    'url': video_url,
-                    'format_id': 'hd',
-                    'preference': 2,
-                })
-
-        self._sort_formats(formats)
+        categories_html = self._search_regex(
+            r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
+            'categories', default=None)
+        categories = [clean_html(category) for category in re.findall(
+            r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,

+            'display_id': display_id,

             'title': title,
             'description': description,
             'upload_date': upload_date,
             'title': title,
             'description': description,
             'upload_date': upload_date,


@@ -154,20 +290,22 @@ class XHamsterIE(InfoExtractor):
             'dislike_count': int_or_none(dislike_count),
             'comment_count': int_or_none(comment_count),
             'age_limit': age_limit,
             'dislike_count': int_or_none(dislike_count),
             'comment_count': int_or_none(comment_count),
             'age_limit': age_limit,

+            'categories': categories,

             'formats': formats,
         }
 
 
 class XHamsterEmbedIE(InfoExtractor):
             'formats': formats,
         }
 
 
 class XHamsterEmbedIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:.+?\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS

     _TEST = {
         'url': 'http://xhamster.com/xembed.php?video=3328539',
         'info_dict': {
             'id': '3328539',
             'ext': 'mp4',
             'title': 'Pen Masturbation',
     _TEST = {
         'url': 'http://xhamster.com/xembed.php?video=3328539',
         'info_dict': {
             'id': '3328539',
             'ext': 'mp4',
             'title': 'Pen Masturbation',

+            'timestamp': 1406581861,

             'upload_date': '20140728',
             'upload_date': '20140728',

-            'uploader_id': 'anonymous',
+            'uploader': 'ManyakisArt',

             'duration': 5,
             'age_limit': 18,
         }
             'duration': 5,
             'age_limit': 18,
         }


@@ -185,7 +323,7 @@ class XHamsterEmbedIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         video_url = self._search_regex(
         webpage = self._download_webpage(url, video_id)
 
         video_url = self._search_regex(

-            r'href="(https?://xhamster\.com/movies/%s/[^"]*\.html[^"]*)"' % video_id,
+            r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id),

             webpage, 'xhamster url', default=None)
 
         if not video_url:
             webpage, 'xhamster url', default=None)
 
         if not video_url:


@@ -195,3 +333,49 @@ class XHamsterEmbedIE(InfoExtractor):
             video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 
         return self.url_result(video_url, 'XHamster')
             video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 
         return self.url_result(video_url, 'XHamster')

+
+
+class XHamsterUserIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:.+?\.)?%s/users/(?P<id>[^/?#&]+)' % XHamsterIE._DOMAINS
+    _TESTS = [{
+        # Paginated user profile
+        'url': 'https://xhamster.com/users/netvideogirls/videos',
+        'info_dict': {
+            'id': 'netvideogirls',
+        },
+        'playlist_mincount': 267,
+    }, {
+        # Non-paginated user profile
+        'url': 'https://xhamster.com/users/firatkaan/videos',
+        'info_dict': {
+            'id': 'firatkaan',
+        },
+        'playlist_mincount': 1,
+    }]
+
+    def _entries(self, user_id):
+        next_page_url = 'https://xhamster.com/users/%s/videos/1' % user_id
+        for pagenum in itertools.count(1):
+            page = self._download_webpage(
+                next_page_url, user_id, 'Downloading page %s' % pagenum)
+            for video_tag in re.findall(
+                    r'(<a[^>]+class=["\'].*?\bvideo-thumb__image-container[^>]+>)',
+                    page):
+                video = extract_attributes(video_tag)
+                video_url = url_or_none(video.get('href'))
+                if not video_url or not XHamsterIE.suitable(video_url):
+                    continue
+                video_id = XHamsterIE._match_id(video_url)
+                yield self.url_result(
+                    video_url, ie=XHamsterIE.ie_key(), video_id=video_id)
+            mobj = re.search(r'<a[^>]+data-page=["\']next[^>]+>', page)
+            if not mobj:
+                break
+            next_page = extract_attributes(mobj.group(0))
+            next_page_url = url_or_none(next_page.get('href'))
+            if not next_page_url:
+                break
+
+    def _real_extract(self, url):
+        user_id = self._match_id(url)
+        return self.playlist_result(self._entries(user_id), user_id)