Merge branch 'PeterDing-porn91'
authorYen Chi Hsuan <yan12125@gmail.com>
Sat, 30 May 2015 16:33:30 +0000 (00:33 +0800)
committerYen Chi Hsuan <yan12125@gmail.com>
Sat, 30 May 2015 16:33:30 +0000 (00:33 +0800)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/porn91.py [new file with mode: 0644]

index e7e0a55f24d9bd2d08fa2d02d926ea2475139645..4dc07efe0e9f3c962a9880ecc5abc4d475dcf00f 100644 (file)
@@ -401,6 +401,7 @@ from .playfm import PlayFMIE
 from .playvid import PlayvidIE
 from .playwire import PlaywireIE
 from .podomatic import PodomaticIE
+from .porn91 import Porn91IE
 from .pornhd import PornHdIE
 from .pornhub import (
     PornHubIE,
diff --git a/youtube_dl/extractor/porn91.py b/youtube_dl/extractor/porn91.py
new file mode 100644 (file)
index 0000000..72d1b27
--- /dev/null
@@ -0,0 +1,71 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+from ..compat import compat_urllib_parse
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    int_or_none,
+    ExtractorError,
+)
+
+
+class Porn91IE(InfoExtractor):
+    IE_NAME = '91porn'
+    _VALID_URL = r'(?:https?://)(?:www\.|)91porn\.com/.+?\?viewkey=(?P<id>[\w\d]+)'
+
+    _TEST = {
+        'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134',
+        'md5': '6df8f6d028bc8b14f5dbd73af742fb20',
+        'info_dict': {
+            'id': '7e42283b4f5ab36da134',
+            'title': '18岁大一漂亮学妹,水嫩性感,再爽一次!',
+            'ext': 'mp4',
+            'duration': 431,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        url = 'http://91porn.com/view_video.php?viewkey=%s' % video_id
+        self._set_cookie('91porn.com', 'language', 'cn_CN')
+        webpage = self._download_webpage(url, video_id, 'get HTML content')
+
+        if '作为游客,你每天只可观看10个视频' in webpage:
+            raise ExtractorError('91 Porn says: Daily limit 10 videos exceeded', expected=True)
+
+        title = self._search_regex(
+            r'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title')
+        title = title.replace('\n', '')
+
+        # get real url
+        file_id = self._search_regex(
+            r'so.addVariable\(\'file\',\'(\d+)\'', webpage, 'file id')
+        sec_code = self._search_regex(
+            r'so.addVariable\(\'seccode\',\'([^\']+)\'', webpage, 'sec code')
+        max_vid = self._search_regex(
+            r'so.addVariable\(\'max_vid\',\'(\d+)\'', webpage, 'max vid')
+        url_params = compat_urllib_parse.urlencode({
+            'VID': file_id,
+            'mp4': '1',
+            'seccode': sec_code,
+            'max_vid': max_vid,
+        })
+        info_cn = self._download_webpage(
+            'http://91porn.com/getfile.php?' + url_params, video_id,
+            'get real video url')
+        video_url = self._search_regex(r'file=([^&]+)&', info_cn, 'url')
+
+        duration = parse_duration(self._search_regex(
+            r'时长:\s*</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False))
+
+        comment_count = int_or_none(self._search_regex(
+            r'留言:\s*</span>\s*(\d+)', webpage, 'comment count', fatal=False))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'duration': duration,
+            'comment_count': comment_count,
+        }