Merge tag 'upstream/2016.06.25'

[youtubedl] / youtube_dl / extractor / pornhd.py

diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py
index e9ff8d1af893c8e22830bbfd41d37b56d5815c9a..8df12eec0d44c371d99b536b55694cfd2211f9d0 100644 (file)
--- a/youtube_dl/extractor/pornhd.py
+++ b/youtube_dl/extractor/pornhd.py
@@ -1,38 +1,96 @@
+from __future__ import unicode_literals
+

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

-from ..utils import compat_urllib_parse
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    js_to_json,
+)

 
 
 class PornHdIE(InfoExtractor):
 
 
 class PornHdIE(InfoExtractor):

-    _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<video_id>[0-9]+)/(?P<video_title>.+)'
-    _TEST = {
-        u'url': u'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
-        u'file': u'1962.flv',
-        u'md5': u'35272469887dca97abd30abecc6cdf75',
-        u'info_dict': {
-            u"title": u"sierra-day-gets-his-cum-all-over-herself-hd-porn-video",
-            u"age_limit": 18,
+    _VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
+    _TESTS = [{
+        'url': 'http://www.pornhd.com/videos/9864/selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
+        'md5': 'c8b964b1f0a4b5f7f28ae3a5c9f86ad5',
+        'info_dict': {
+            'id': '9864',
+            'display_id': 'selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
+            'ext': 'mp4',
+            'title': 'Restroom selfie masturbation',
+            'description': 'md5:3748420395e03e31ac96857a8f125b2b',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'view_count': int,
+            'age_limit': 18,

         }
         }

-    }
+    }, {
+        # removed video
+        'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
+        'md5': '956b8ca569f7f4d8ec563e2c41598441',
+        'info_dict': {
+            'id': '1962',
+            'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
+            'ext': 'mp4',
+            'title': 'Sierra loves doing laundry',
+            'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'view_count': int,
+            'age_limit': 18,
+        },
+        'skip': 'Not available anymore',
+    }]

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id or video_id)
+
+        title = self._html_search_regex(
+            [r'<span[^>]+class=["\']video-name["\'][^>]*>([^<]+)',
+             r'<title>(.+?) - .*?[Pp]ornHD.*?</title>'], webpage, 'title')
+
+        sources = self._parse_json(js_to_json(self._search_regex(
+            r"(?s)'sources'\s*:\s*(\{.+?\})\s*\}[;,)]",
+            webpage, 'sources', default='{}')), video_id)

 
 

-        video_id = mobj.group('video_id')
-        video_title = mobj.group('video_title')
+        if not sources:
+            message = self._html_search_regex(
+                r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P<value>.+?)</\1',
+                webpage, 'error message', group='value')
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)

 
 

-        webpage = self._download_webpage(url, video_id)
+        formats = []
+        for format_id, video_url in sources.items():
+            if not video_url:
+                continue
+            height = int_or_none(self._search_regex(
+                r'^(\d+)[pP]', format_id, 'height', default=None))
+            formats.append({
+                'url': video_url,
+                'format_id': format_id,
+                'height': height,
+            })
+        self._sort_formats(formats)

 
 

-        video_url = self._html_search_regex(
-            r'&hd=(http.+?)&', webpage, u'video URL')
-        video_url = compat_urllib_parse.unquote(video_url)
-        age_limit = 18
+        description = self._html_search_regex(
+            r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1',
+            webpage, 'description', fatal=False, group='value')
+        view_count = int_or_none(self._html_search_regex(
+            r'(\d+) views\s*<', webpage, 'view count', fatal=False))
+        thumbnail = self._search_regex(
+            r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)

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

-            'url': video_url,
-            'ext': 'flv',
-            'title': video_title,
-            'age_limit': age_limit,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'view_count': view_count,
+            'formats': formats,
+            'age_limit': 18,

         }
         }