Merge branch 'gebn-moviefap'

youtube_dl/YoutubeDL.py

@@ -1008,7 +1008,7 @@ class YoutubeDL(object):
                 t.get('preference'), t.get('width'), t.get('height'),
                 t.get('id'), t.get('url')))
             for i, t in enumerate(thumbnails):
-                if 'width' in t and 'height' in t:
+                if t.get('width') and t.get('height'):
                     t['resolution'] = '%dx%d' % (t['width'], t['height'])
                 if t.get('id') is None:
                     t['id'] = '%d' % i

youtube_dl/extractor/__init__.py

@@ -144,7 +144,6 @@ from .ellentv import (
 )
 from .elpais import ElPaisIE
 from .embedly import EmbedlyIE
-from .empflix import EMPFlixIE
 from .engadget import EngadgetIE
 from .eporner import EpornerIE
 from .eroprofile import EroProfileIE
@@ -577,7 +576,11 @@ from .tmz import (
     TMZIE,
     TMZArticleIE,
 )
-from .tnaflix import TNAFlixIE
+from .tnaflix import (
+    TNAFlixIE,
+    EMPFlixIE,
+    MovieFapIE,
+)
 from .thvideo import (
     THVideoIE,
     THVideoPlaylistIE

youtube_dl/extractor/common.py

@@ -22,6 +22,7 @@ from ..compat import (
     compat_str,
 )
 from ..utils import (
+    NO_DEFAULT,
     age_restricted,
     bug_reports_message,
     clean_html,
@@ -33,7 +34,7 @@ from ..utils import (
     sanitize_filename,
     unescapeHTML,
 )
-_NO_DEFAULT = object()
+
 
 
 class InfoExtractor(object):
@@ -523,7 +524,7 @@ class InfoExtractor(object):
             video_info['description'] = playlist_description
         return video_info
 
-    def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
+    def _search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None):
         """
         Perform a regex search on the given string, using a single or a list of
         patterns returning the first matching group.
@@ -549,7 +550,7 @@ class InfoExtractor(object):
                 return next(g for g in mobj.groups() if g is not None)
             else:
                 return mobj.group(group)
-        elif default is not _NO_DEFAULT:
+        elif default is not NO_DEFAULT:
             return default
         elif fatal:
             raise RegexNotFoundError('Unable to extract %s' % _name)
@@ -557,7 +558,7 @@ class InfoExtractor(object):
             self._downloader.report_warning('unable to extract %s' % _name + bug_reports_message())
             return None
 
-    def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
+    def _html_search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None):
         """
         Like _search_regex, but strips HTML tags and unescapes entities.
         """

youtube_dl/extractor/empflix.py

@@ -1,31 +0,0 @@
-from __future__ import unicode_literals
-
-from .tnaflix import TNAFlixIE
-
-
-class EMPFlixIE(TNAFlixIE):
-    _VALID_URL = r'https?://(?:www\.)?empflix\.com/videos/(?P<display_id>.+?)-(?P<id>[0-9]+)\.html'
-
-    _TITLE_REGEX = r'name="title" value="(?P<title>[^"]*)"'
-    _DESCRIPTION_REGEX = r'name="description" value="([^"]*)"'
-    _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
-
-    _TESTS = [
-        {
-            'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
-            'md5': 'b1bc15b6412d33902d6e5952035fcabc',
-            'info_dict': {
-                'id': '33051',
-                'display_id': 'Amateur-Finger-Fuck',
-                'ext': 'mp4',
-                'title': 'Amateur Finger Fuck',
-                'description': 'Amateur solo finger fucking.',
-                'thumbnail': 're:https?://.*\.jpg$',
-                'age_limit': 18,
-            }
-        },
-        {
-            'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
-            'only_matching': True,
-        }
-    ]

youtube_dl/extractor/tnaflix.py

@@ -3,39 +3,70 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
-    parse_duration,
     fix_xml_ampersands,
+    float_or_none,
+    int_or_none,
+    parse_duration,
+    str_to_int,
+    xpath_text,
 )
 
 
-class TNAFlixIE(InfoExtractor):
+class TNAFlixNetworkBaseIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
+    # May be overridden in descendants if necessary
+    _CONFIG_REGEX = [
+        r'flashvars\.config\s*=\s*escape\("([^"]+)"',
+        r'<input[^>]+name="config\d?" value="([^"]+)"',
+    ]
+    _TITLE_REGEX = r'<input[^>]+name="title" value="([^"]+)"'
+    _DESCRIPTION_REGEX = r'<input[^>]+name="description" value="([^"]+)"'
+    _UPLOADER_REGEX = r'<input[^>]+name="username" value="([^"]+)"'
+    _VIEW_COUNT_REGEX = None
+    _COMMENT_COUNT_REGEX = None
+    _AVERAGE_RATING_REGEX = None
+    _CATEGORIES_REGEX = r'<li[^>]*>\s*<span[^>]+class="infoTitle"[^>]*>Categories:</span>\s*<span[^>]+class="listView"[^>]*>(.+?)</span>\s*</li>'
 
-    _TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>'
+    def _extract_thumbnails(self, flix_xml):
-    _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>'
-    _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
 
-    _TESTS = [
+        def get_child(elem, names):
-        {
+            for name in names:
-            'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
+                child = elem.find(name)
-            'md5': 'ecf3498417d09216374fc5907f9c6ec0',
+                if child is not None:
-            'info_dict': {
+                    return child
-                'id': '553878',
+
-                'display_id': 'Carmella-Decesare-striptease',
+        timeline = get_child(flix_xml, ['timeline', 'rolloverBarImage'])
-                'ext': 'mp4',
+        if timeline is None:
-                'title': 'Carmella Decesare - striptease',
+            return
-                'description': '',
+
-                'thumbnail': 're:https?://.*\.jpg$',
+        pattern_el = get_child(timeline, ['imagePattern', 'pattern'])
-                'duration': 91,
+        if pattern_el is None or not pattern_el.text:
-                'age_limit': 18,
+            return
-            }
+
-        },
+        first_el = get_child(timeline, ['imageFirst', 'first'])
-        {
+        last_el = get_child(timeline, ['imageLast', 'last'])
-            'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
+        if first_el is None or last_el is None:
-            'only_matching': True,
+            return
-        }
+
-    ]
+        first_text = first_el.text
+        last_text = last_el.text
+        if not first_text.isdigit() or not last_text.isdigit():
+            return
+
+        first = int(first_text)
+        last = int(last_text)
+        if first > last:
+            return
+
+        width = int_or_none(xpath_text(timeline, './imageWidth', 'thumbnail width'))
+        height = int_or_none(xpath_text(timeline, './imageHeight', 'thumbnail height'))
+
+        return [{
+            'url': self._proto_relative_url(pattern_el.text.replace('#', compat_str(i)), 'http:'),
+            'width': width,
+            'height': height,
+        } for i in range(first, last + 1)]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -44,47 +75,195 @@ class TNAFlixIE(InfoExtractor):
 
         webpage = self._download_webpage(url, display_id)
 
-        title = self._html_search_regex(
-            self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage)
-        description = self._html_search_regex(
-            self._DESCRIPTION_REGEX, webpage, 'description', fatal=False, default='')
-
-        age_limit = self._rta_search(webpage)
-
-        duration = parse_duration(self._html_search_meta(
-            'duration', webpage, 'duration', default=None))
-
         cfg_url = self._proto_relative_url(self._html_search_regex(
             self._CONFIG_REGEX, webpage, 'flashvars.config'), 'http:')
 
         cfg_xml = self._download_xml(
-            cfg_url, display_id, note='Downloading metadata',
+            cfg_url, display_id, 'Downloading metadata',
             transform_source=fix_xml_ampersands)
 
-        thumbnail = self._proto_relative_url(
-            cfg_xml.find('./startThumb').text, 'http:')
-
         formats = []
+
+        def extract_video_url(vl):
+            return re.sub('speed=\d+', 'speed=', vl.text)
+
+        video_link = cfg_xml.find('./videoLink')
+        if video_link is not None:
+            formats.append({
+                'url': extract_video_url(video_link),
+                'ext': xpath_text(cfg_xml, './videoConfig/type', 'type', default='flv'),
+            })
+
         for item in cfg_xml.findall('./quality/item'):
-            video_url = re.sub('speed=\d+', 'speed=', item.find('videoLink').text)
+            video_link = item.find('./videoLink')
-            format_id = item.find('res').text
+            if video_link is None:
-            fmt = {
+                continue
-                'url': self._proto_relative_url(video_url, 'http:'),
+            res = item.find('res')
+            format_id = None if res is None else res.text
+            height = int_or_none(self._search_regex(
+                r'^(\d+)[pP]', format_id, 'height', default=None))
+            formats.append({
+                'url': self._proto_relative_url(extract_video_url(video_link), 'http:'),
                 'format_id': format_id,
-            }
+                'height': height,
-            m = re.search(r'^(\d+)', format_id)
+            })
-            if m:
+
-                fmt['height'] = int(m.group(1))
-            formats.append(fmt)
         self._sort_formats(formats)
 
+        thumbnail = self._proto_relative_url(
+            xpath_text(cfg_xml, './startThumb', 'thumbnail'), 'http:')
+        thumbnails = self._extract_thumbnails(cfg_xml)
+
+        title = self._html_search_regex(
+            self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage)
+
+        age_limit = self._rta_search(webpage)
+
+        duration = parse_duration(self._html_search_meta(
+            'duration', webpage, 'duration', default=None))
+
+        def extract_field(pattern, name):
+            return self._html_search_regex(pattern, webpage, name, default=None) if pattern else None
+
+        description = extract_field(self._DESCRIPTION_REGEX, 'description')
+        uploader = extract_field(self._UPLOADER_REGEX, 'uploader')
+        view_count = str_to_int(extract_field(self._VIEW_COUNT_REGEX, 'view count'))
+        comment_count = str_to_int(extract_field(self._COMMENT_COUNT_REGEX, 'comment count'))
+        average_rating = float_or_none(extract_field(self._AVERAGE_RATING_REGEX, 'average rating'))
+
+        categories_str = extract_field(self._CATEGORIES_REGEX, 'categories')
+        categories = categories_str.split(', ') if categories_str is not None else []
+
         return {
             'id': video_id,
             'display_id': display_id,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,
+            'thumbnails': thumbnails,
             'duration': duration,
             'age_limit': age_limit,
+            'uploader': uploader,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'average_rating': average_rating,
+            'categories': categories,
             'formats': formats,
         }
+
+
+class TNAFlixIE(TNAFlixNetworkBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
+
+    _TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>'
+    _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>'
+    _UPLOADER_REGEX = r'(?s)<span[^>]+class="infoTitle"[^>]*>Uploaded By:</span>(.+?)<div'
+
+    _TESTS = [{
+        # anonymous uploader, no categories
+        'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
+        'md5': 'ecf3498417d09216374fc5907f9c6ec0',
+        'info_dict': {
+            'id': '553878',
+            'display_id': 'Carmella-Decesare-striptease',
+            'ext': 'mp4',
+            'title': 'Carmella Decesare - striptease',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'duration': 91,
+            'age_limit': 18,
+            'uploader': 'Anonymous',
+            'categories': [],
+        }
+    }, {
+        # non-anonymous uploader, categories
+        'url': 'https://www.tnaflix.com/teen-porn/Educational-xxx-video/video6538',
+        'md5': '0f5d4d490dbfd117b8607054248a07c0',
+        'info_dict': {
+            'id': '6538',
+            'display_id': 'Educational-xxx-video',
+            'ext': 'mp4',
+            'title': 'Educational xxx video',
+            'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'duration': 164,
+            'age_limit': 18,
+            'uploader': 'bobwhite39',
+            'categories': ['Amateur Porn', 'Squirting Videos', 'Teen Girls 18+'],
+        }
+    }, {
+        'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
+        'only_matching': True,
+    }]
+
+
+class EMPFlixIE(TNAFlixNetworkBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?empflix\.com/videos/(?P<display_id>.+?)-(?P<id>[0-9]+)\.html'
+
+    _UPLOADER_REGEX = r'<span[^>]+class="infoTitle"[^>]*>Uploaded By:</span>(.+?)</li>'
+
+    _TESTS = [{
+        'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
+        'md5': 'b1bc15b6412d33902d6e5952035fcabc',
+        'info_dict': {
+            'id': '33051',
+            'display_id': 'Amateur-Finger-Fuck',
+            'ext': 'mp4',
+            'title': 'Amateur Finger Fuck',
+            'description': 'Amateur solo finger fucking.',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'duration': 83,
+            'age_limit': 18,
+            'uploader': 'cwbike',
+            'categories': ['Amateur', 'Anal', 'Fisting', 'Home made', 'Solo'],
+        }
+    }, {
+        'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
+        'only_matching': True,
+    }]
+
+
+class MovieFapIE(TNAFlixNetworkBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?moviefap\.com/videos/(?P<id>[0-9a-f]+)/(?P<display_id>[^/]+)\.html'
+
+    _VIEW_COUNT_REGEX = r'<br>Views\s*<strong>([\d,.]+)</strong>'
+    _COMMENT_COUNT_REGEX = r'<span[^>]+id="comCount"[^>]*>([\d,.]+)</span>'
+    _AVERAGE_RATING_REGEX = r'Current Rating\s*<br>\s*<strong>([\d.]+)</strong>'
+    _CATEGORIES_REGEX = r'(?s)<div[^>]+id="vid_info"[^>]*>\s*<div[^>]*>.+?</div>(.*?)<br>'
+
+    _TESTS = [{
+        # normal, multi-format video
+        'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html',
+        'md5': '26624b4e2523051b550067d547615906',
+        'info_dict': {
+            'id': 'be9867c9416c19f54a4a',
+            'display_id': 'experienced-milf-amazing-handjob',
+            'ext': 'mp4',
+            'title': 'Experienced MILF Amazing Handjob',
+            'description': 'Experienced MILF giving an Amazing Handjob',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
+            'uploader': 'darvinfred06',
+            'view_count': int,
+            'comment_count': int,
+            'average_rating': float,
+            'categories': ['Amateur', 'Masturbation', 'Mature', 'Flashing'],
+        }
+    }, {
+        # quirky single-format case where the extension is given as fid, but the video is really an flv
+        'url': 'http://www.moviefap.com/videos/e5da0d3edce5404418f5/jeune-couple-russe.html',
+        'md5': 'fa56683e291fc80635907168a743c9ad',
+        'info_dict': {
+            'id': 'e5da0d3edce5404418f5',
+            'display_id': 'jeune-couple-russe',
+            'ext': 'flv',
+            'title': 'Jeune Couple Russe',
+            'description': 'Amateur',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
+            'uploader': 'whiskeyjar',
+            'view_count': int,
+            'comment_count': int,
+            'average_rating': float,
+            'categories': ['Amateur', 'Teen'],
+        }
+    }]

youtube_dl/utils.py

@@ -62,6 +62,8 @@ std_headers = {
 }
 
 
+NO_DEFAULT = object()
+
 ENGLISH_MONTH_NAMES = [
     'January', 'February', 'March', 'April', 'May', 'June',
     'July', 'August', 'September', 'October', 'November', 'December']
@@ -171,13 +173,15 @@ def xpath_with_ns(path, ns_map):
     return '/'.join(replaced)
 
 
-def xpath_text(node, xpath, name=None, fatal=False):
+def xpath_text(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
     if sys.version_info < (2, 7):  # Crazy 2.6
         xpath = xpath.encode('ascii')
 
     n = node.find(xpath)
     if n is None or n.text is None:
-        if fatal:
+        if default is not NO_DEFAULT:
+            return default
+        elif fatal:
             name = xpath if name is None else name
             raise ExtractorError('Could not find XML element %s' % name)
         else: