Annotate changelog with bugs closed.

[youtubedl] / youtube_dl / extractor / pornhub.py

diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py
index fdda69f33064fe4bd4e89775c5e3c7d56e4946d2..a656ad85a1d5a6b7773e98c2a9be585803898db1 100644 (file)
--- a/youtube_dl/extractor/pornhub.py
+++ b/youtube_dl/extractor/pornhub.py
@@ -4,10 +4,15 @@ import os
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from ..utils import (
+from ..compat import (
+    compat_urllib_parse_unquote,
+    compat_urllib_parse_unquote_plus,

     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse_urlparse,
     compat_urllib_request,

-    compat_urllib_parse,
+)
+from ..utils import (
+    ExtractorError,
+    str_to_int,

 )
 from ..aes import (
     aes_decrypt_text
 )
 from ..aes import (
     aes_decrypt_text


@@ -15,36 +20,74 @@ from ..aes import (
 
 
 class PornHubIE(InfoExtractor):
 
 
 class PornHubIE(InfoExtractor):

-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>pornhub\.com/view_video\.php\?viewkey=(?P<videoid>[0-9a-f]+))'
-    _TEST = {
+    _VALID_URL = r'https?://(?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)(?P<id>[0-9a-z]+)'
+    _TESTS = [{

         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',

-        'file': '648719015.mp4',

         'md5': '882f488fa1f0026f023f33576004a2ed',
         'info_dict': {
         'md5': '882f488fa1f0026f023f33576004a2ed',
         'info_dict': {

-            "uploader": "BABES-COM",
+            'id': '648719015',
+            'ext': 'mp4',
+            "uploader": "Babes",

             "title": "Seductive Indian beauty strips down and fingers her pink pussy",
             "age_limit": 18
         }
             "title": "Seductive Indian beauty strips down and fingers her pink pussy",
             "age_limit": 18
         }

-    }
+    }, {
+        'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
+        'only_matching': True,
+    }, {
+        'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def _extract_url(cls, webpage):
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/\d+)\1', webpage)
+        if mobj:
+            return mobj.group('url')
+
+    def _extract_count(self, pattern, webpage, name):
+        return str_to_int(self._search_regex(
+            pattern, webpage, '%s count' % name, fatal=False))

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

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
-        url = 'http://www.' + mobj.group('url')
+        video_id = self._match_id(url)

 
 

-        req = compat_urllib_request.Request(url)
+        req = compat_urllib_request.Request(
+            'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id)

         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 

+        error_msg = self._html_search_regex(
+            r'(?s)<div class="userMessageSection[^"]*".*?>(.*?)</div>',
+            webpage, 'error message', default=None)
+        if error_msg:
+            error_msg = re.sub(r'\s+', ' ', error_msg)
+            raise ExtractorError(
+                'PornHub said: %s' % error_msg,
+                expected=True, video_id=video_id)
+

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

-        video_uploader = self._html_search_regex(r'<b>From: </b>(?:\s|<[^>]*>)*(.+?)<', webpage, 'uploader', fatal=False)
+        video_uploader = self._html_search_regex(
+            r'(?s)From:&nbsp;.+?<(?:a href="/users/|a href="/channels/|span class="username)[^>]+>(.+?)<',
+            webpage, 'uploader', fatal=False)

         thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False)
         if thumbnail:
         thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False)
         if thumbnail:

-            thumbnail = compat_urllib_parse.unquote(thumbnail)
+            thumbnail = compat_urllib_parse_unquote(thumbnail)

 
 

-        video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
+        view_count = self._extract_count(
+            r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
+        like_count = self._extract_count(
+            r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
+        dislike_count = self._extract_count(
+            r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
+        comment_count = self._extract_count(
+            r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
+
+        video_urls = list(map(compat_urllib_parse_unquote, re.findall(r"player_quality_[0-9]{3}p\s*=\s*'([^']+)'", webpage)))

         if webpage.find('"encrypted":true') != -1:
         if webpage.find('"encrypted":true') != -1:

-            password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, 'password').replace('+', ' ')
+            password = compat_urllib_parse_unquote_plus(
+                self._search_regex(r'"video_title":"([^"]+)', webpage, 'password'))

             video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
 
         formats = []
             video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
 
         formats = []


@@ -54,7 +97,7 @@ class PornHubIE(InfoExtractor):
             format = path.split('/')[5].split('_')[:2]
             format = "-".join(format)
 
             format = path.split('/')[5].split('_')[:2]
             format = "-".join(format)
 

-            m = re.match(r'^(?P<height>[0-9]+)P-(?P<tbr>[0-9]+)K$', format)
+            m = re.match(r'^(?P<height>[0-9]+)[pP]-(?P<tbr>[0-9]+)[kK]$', format)

             if m is None:
                 height = None
                 tbr = None
             if m is None:
                 height = None
                 tbr = None


@@ -77,6 +120,40 @@ class PornHubIE(InfoExtractor):
             'uploader': video_uploader,
             'title': video_title,
             'thumbnail': thumbnail,
             'uploader': video_uploader,
             'title': video_title,
             'thumbnail': thumbnail,

+            'view_count': view_count,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'comment_count': comment_count,

             'formats': formats,
             'age_limit': 18,
         }
             'formats': formats,
             'age_limit': 18,
         }

+
+
+class PornHubPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://www.pornhub.com/playlist/6201671',
+        'info_dict': {
+            'id': '6201671',
+            'title': 'P0p4',
+        },
+        'playlist_mincount': 35,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        entries = [
+            self.url_result('http://www.pornhub.com/%s' % video_url, 'PornHub')
+            for video_url in set(re.findall('href="/?(view_video\.php\?viewkey=\d+[^"]*)"', webpage))
+        ]
+
+        playlist = self._parse_json(
+            self._search_regex(
+                r'playlistObject\s*=\s*({.+?});', webpage, 'playlist'),
+            playlist_id)
+
+        return self.playlist_result(
+            entries, playlist_id, playlist.get('title'), playlist.get('description'))