debian/copyright: use spaces rather than tabs to start continuation lines.

[youtubedl] / youtube_dl / extractor / pornhd.py

diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py
index 57c78ba52a994a9c2aff224470b86b913702241f..c6052ac9f966f332d0cfb1f7acfe68b0a143d2b7 100644 (file)
--- a/youtube_dl/extractor/pornhd.py
+++ b/youtube_dl/extractor/pornhd.py
@@ -1,32 +1,50 @@
 from __future__ import unicode_literals
 
 import re
 from __future__ import unicode_literals
 
 import re

-import json

 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (

+    determine_ext,
+    ExtractorError,

     int_or_none,
     js_to_json,
     int_or_none,
     js_to_json,

-    qualities,
+    merge_dicts,
+    urljoin,

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

-    _VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
-    _TEST = {
+    _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': '87f1540746c1d32ec7a2305c12b96b25',
+        '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': r're:^https?://.*\.jpg',
+            'view_count': int,
+            'like_count': int,
+            'age_limit': 18,
+        },
+        'skip': 'HTTP Error 404: Not Found',
+    }, {

         'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
         'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',

-        'md5': '956b8ca569f7f4d8ec563e2c41598441',
+        'md5': '1b7b3a40b9d65a8e5b25f7ab9ee6d6de',

         'info_dict': {
             'id': '1962',
             'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
             'ext': 'mp4',
         'info_dict': {
             'id': '1962',
             'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
             'ext': 'mp4',

-            'title': 'Sierra loves doing laundry',
+            'title': 'md5:98c6f8b2d9c229d0f0fde47f61a1a759',

             'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
             'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',

-            'thumbnail': 're:^https?://.*\.jpg',
+            'thumbnail': r're:^https?://.*\.jpg',

             'view_count': int,
             'view_count': int,

+            'like_count': int,

             'age_limit': 18,
             'age_limit': 18,

-        }
-    }
+        },
+    }]

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


@@ -38,35 +56,66 @@ class PornHdIE(InfoExtractor):
         title = self._html_search_regex(
             [r'<span[^>]+class=["\']video-name["\'][^>]*>([^<]+)',
              r'<title>(.+?) - .*?[Pp]ornHD.*?</title>'], webpage, 'title')
         title = self._html_search_regex(
             [r'<span[^>]+class=["\']video-name["\'][^>]*>([^<]+)',
              r'<title>(.+?) - .*?[Pp]ornHD.*?</title>'], webpage, 'title')

-        description = self._html_search_regex(
-            r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False)
-        view_count = int_or_none(self._html_search_regex(
-            r'(\d+) views\s*</span>', webpage, 'view count', fatal=False))
-        thumbnail = self._search_regex(
-            r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)

 
 

-        quality = qualities(['sd', 'hd'])
-        sources = json.loads(js_to_json(self._search_regex(
-            r"(?s)'sources'\s*:\s*(\{.+?\})\s*\}[;,)]",
-            webpage, 'sources')))
+        sources = self._parse_json(js_to_json(self._search_regex(
+            r"(?s)sources'?\s*[:=]\s*(\{.+?\})",
+            webpage, 'sources', default='{}')), video_id)
+
+        info = {}
+        if not sources:
+            entries = self._parse_html5_media_entries(url, webpage, video_id)
+            if entries:
+                info = entries[0]
+
+        if not sources and not info:
+            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)
+

         formats = []
         formats = []

-        for qname, video_url in sources.items():
+        for format_id, video_url in sources.items():
+            video_url = urljoin(url, video_url)

             if not video_url:
                 continue
             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,
             formats.append({
                 'url': video_url,

-                'format_id': qname,
-                'quality': quality(qname),
+                'ext': determine_ext(video_url, 'mp4'),
+                'format_id': format_id,
+                'height': height,

             })
             })

-        self._sort_formats(formats)
+        if formats:
+            info['formats'] = formats
+        self._sort_formats(info['formats'])
+
+        description = self._html_search_regex(
+            (r'(?s)<section[^>]+class=["\']video-description[^>]+>(?P<value>.+?)</section>',
+             r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1'),
+            webpage, 'description', fatal=False,
+            group='value') or self._html_search_meta(
+            'description', webpage, default=None) or self._og_search_description(webpage)
+        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*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage,
+            'thumbnail', default=None, group='url')
+
+        like_count = int_or_none(self._search_regex(
+            (r'(\d+)</span>\s*likes',
+             r'(\d+)\s*</11[^>]+>(?:&nbsp;|\s)*\blikes',
+             r'class=["\']save-count["\'][^>]*>\s*(\d+)'),
+            webpage, 'like count', fatal=False))

 
 

-        return {
+        return merge_dicts(info, {

             'id': video_id,
             'display_id': display_id,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,
             'view_count': view_count,
             'id': video_id,
             'display_id': display_id,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,
             'view_count': view_count,

+            'like_count': like_count,

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

-        }
+        })