[tnaflix] Generalize tnaflix extractors

youtube_dl/extractor/__init__.py

@@ -144,7 +144,6 @@
 )
 from .elpais import ElPaisIE
 from .embedly import EmbedlyIE
-from .empflix import EMPFlixIE
 from .engadget import EngadgetIE
 from .eporner import EpornerIE
 from .eroprofile import EroProfileIE
@@ -311,7 +310,6 @@
 from .motherless import MotherlessIE
 from .motorsport import MotorsportIE
 from .movieclips import MovieClipsIE
-from .moviefap import MovieFapIE
 from .moviezine import MoviezineIE
 from .movshare import MovShareIE
 from .mtv import (
@@ -578,7 +576,11 @@
     TMZIE,
     TMZArticleIE,
 )
-from .tnaflix import TNAFlixIE
+from .tnaflix import (
+    TNAFlixIE,
+    EMPFlixIE,
+    MovieFapIE,
+)
 from .thvideo import (
     THVideoIE,
     THVideoPlaylistIE

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/moviefap.py

@@ -1,135 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    xpath_text,
-    str_to_int
-)
-from ..compat import compat_str
-
-
-class MovieFapIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?moviefap\.com/videos/(?P<id>[0-9a-f]+)/(?P<name>[a-z-_]+)'
-    _TESTS = [{
-        # normal, multi-format video
-        'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html',
-        'md5': '26624b4e2523051b550067d547615906',
-        'info_dict': {
-            'id': 'be9867c9416c19f54a4a',
-            'ext': 'mp4',
-            'title': 'Experienced MILF Amazing Handjob',
-            'description': 'Experienced MILF giving an Amazing Handjob',
-            'thumbnail': 'http://img.moviefap.com/a16:9w990r/thumbs/be/322032-20l.jpg',
-            'uploader_id': 'darvinfred06',
-            'display_id': 'experienced-milf-amazing-handjob',
-            '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',
-            'ext': 'flv',
-            'title': 'Jeune Couple Russe',
-            'description': 'Amateur',
-            'thumbnail': 'http://pic.moviefap.com/thumbs/e5/949-18l.jpg',
-            'uploader_id': 'whiskeyjar',
-            'display_id': 'jeune-couple-russe',
-            'categories': ['Amateur', 'Teen']
-        }
-    }]
-
-    @staticmethod
-    def __get_thumbnail_data(xml):
-
-        """
-        Constructs a list of video thumbnails from timeline preview images.
-        :param xml: the information XML document to parse
-        """
-
-        timeline = xml.find('timeline')
-        if timeline is None:
-            # not all videos have the data - ah well
-            return []
-
-        # get the required information from the XML
-        width = str_to_int(timeline.find('imageWidth').text)
-        height = str_to_int(timeline.find('imageHeight').text)
-        first = str_to_int(timeline.find('imageFirst').text)
-        last = str_to_int(timeline.find('imageLast').text)
-        pattern = timeline.find('imagePattern').text
-
-        # generate the list of thumbnail information dicts
-        thumbnails = []
-        for i in range(first, last + 1):
-            thumbnails.append({
-                'url': pattern.replace('#', compat_str(i)),
-                'width': width,
-                'height': height
-            })
-        return thumbnails
-
-    def _real_extract(self, url):
-
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        # find and retrieve the XML document detailing video download URLs
-        info_url = self._html_search_regex(
-            r'flashvars\.config = escape\("(.+?)"', webpage, 'player parameters')
-        xml = self._download_xml(info_url, video_id)
-
-        # find the video container
-        if xml.find('videoConfig') is not None:
-            ext = xml.find('videoConfig').find('type').text
-        else:
-            ext = 'flv'  # guess...
-
-        # work out the video URL(s)
-        formats = []
-        if xml.find('videoLink') is not None:
-            # single format available
-            formats.append({
-                'url': xpath_text(xml, 'videoLink', 'url', True),
-                'ext': ext
-            })
-        else:
-            # multiple formats available
-            for item in xml.find('quality').findall('item'):
-                resolution = xpath_text(item, 'res', 'resolution', True)  # 480p etc.
-                formats.append({
-                    'url': xpath_text(item, 'videoLink', 'url', True),
-                    'ext': ext,
-                    'resolution': resolution,
-                    'height': int(re.findall(r'\d+', resolution)[0])
-                })
-
-            self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'formats': formats,
-            'title': self._html_search_regex(
-                r'<div id="view_title"><h1>(.*?)</h1>', webpage, 'title'),
-            'display_id': re.compile(self._VALID_URL).match(url).group('name'),
-            'thumbnails': self.__get_thumbnail_data(xml),
-            'thumbnail': xpath_text(xml, 'startThumb', 'thumbnail'),
-            'description': self._html_search_regex(
-                r'name="description" value="(.*?)"', webpage, 'description', fatal=False),
-            'uploader_id': self._html_search_regex(
-                r'name="username" value="(.*?)"', webpage, 'uploader_id', fatal=False),
-            'view_count': str_to_int(self._html_search_regex(
-                r'<br>Views <strong>([0-9]+)</strong>', webpage, 'view_count, fatal=False')),
-            'average_rating': float(self._html_search_regex(
-                r'Current Rating<br> <strong>(.*?)</strong>', webpage, 'average_rating', fatal=False)),
-            'comment_count': str_to_int(self._html_search_regex(
-                r'<span id="comCount">([0-9]+)</span>', webpage, 'comment_count', fatal=False)),
-            'age_limit': 18,
-            'webpage_url': self._html_search_regex(
-                r'name="link" value="(.*?)"', webpage, 'webpage_url', fatal=False),
-            'categories': self._html_search_regex(
-                r'</div>\s*(.*?)\s*<br>', webpage, 'categories', fatal=False).split(', ')
-        }

youtube_dl/extractor/tnaflix.py

@@ -3,39 +3,70 @@
 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 = [
-    _TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>'
+        r'flashvars\.config\s*=\s*escape\("([^"]+)"',
-    _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>'
+        r'<input[^>]+name="config\d?" value="([^"]+)"',
-    _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
-
-    _TESTS = [
-        {
-            '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',
-                'description': '',
-                'thumbnail': 're:https?://.*\.jpg$',
-                'duration': 91,
-                'age_limit': 18,
-            }
-        },
-        {
-            'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
-            'only_matching': True,
-        }
     ]
+    _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>'
+
+    def _extract_thumbnails(self, flix_xml):
+
+        def get_child(elem, names):
+            for name in names:
+                child = elem.find(name)
+                if child is not None:
+                    return child
+
+        timeline = get_child(flix_xml, ['timeline', 'rolloverBarImage'])
+        if timeline is None:
+            return
+
+        pattern_el = get_child(timeline, ['imagePattern', 'pattern'])
+        if pattern_el is None or not pattern_el.text:
+            return
+
+        first_el = get_child(timeline, ['imageFirst', 'first'])
+        last_el = get_child(timeline, ['imageLast', 'last'])
+        if first_el is None or last_el is None:
+            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)
@@ -44,39 +75,64 @@ def _real_extract(self, url):
 
         webpage = self._download_webpage(url, display_id)
 
+        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, 'Downloading metadata',
+            transform_source=fix_xml_ampersands)
+
+        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_link = item.find('./videoLink')
+            if video_link is None:
+                continue
+            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,
+            })
+
+        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)
-        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(
+        def extract_field(pattern, name):
-            self._CONFIG_REGEX, webpage, 'flashvars.config'), 'http:')
+            return self._html_search_regex(pattern, webpage, name, default=None) if pattern else None
 
-        cfg_xml = self._download_xml(
+        description = extract_field(self._DESCRIPTION_REGEX, 'description')
-            cfg_url, display_id, note='Downloading metadata',
+        uploader = extract_field(self._UPLOADER_REGEX, 'uploader')
-            transform_source=fix_xml_ampersands)
+        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'))
 
-        thumbnail = self._proto_relative_url(
+        categories_str = extract_field(self._CATEGORIES_REGEX, 'categories')
-            cfg_xml.find('./startThumb').text, 'http:')
+        categories = categories_str.split(', ') if categories_str is not None else []
-
-        formats = []
-        for item in cfg_xml.findall('./quality/item'):
-            video_url = re.sub('speed=\d+', 'speed=', item.find('videoLink').text)
-            format_id = item.find('res').text
-            fmt = {
-                'url': self._proto_relative_url(video_url, 'http:'),
-                'format_id': format_id,
-            }
-            m = re.search(r'^(\d+)', format_id)
-            if m:
-                fmt['height'] = int(m.group(1))
-            formats.append(fmt)
-        self._sort_formats(formats)
 
         return {
             'id': video_id,
@@ -84,7 +140,130 @@ def _real_extract(self, url):
             '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'],
+        }
+    }]