[pornflip] Add extractor (closes #11556)

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index de5f94738fdb28f065236958a5cca6ebeff8d718..cfddf5b9263a14985b8983e3aeb09108e2f83240 100644 (file)
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -724,6 +724,7 @@ from .polskieradio import (
 )
 from .porn91 import Porn91IE
 from .porncom import PornComIE
+from .pornflip import PornFlipIE
 from .pornhd import PornHdIE
 from .pornhub import (
     PornHubIE,

diff --git a/youtube_dl/extractor/pornflip.py b/youtube_dl/extractor/pornflip.py
new file mode 100644 (file)
index 0000000..b6077f7
--- /dev/null
+++ b/youtube_dl/extractor/pornflip.py
@@ -0,0 +1,59 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_parse_qs,
+)
+from ..utils import (
+    int_or_none,
+    try_get,
+    RegexNotFoundError,
+)
+
+
+class PornFlipIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?pornflip\.com/v/(?P<id>[0-9A-Za-z]{11})'
+    _TEST = {
+        'url': 'https://www.pornflip.com/v/wz7DfNhMmep',
+        'md5': '98c46639849145ae1fd77af532a9278c',
+        'info_dict': {
+            'id': 'wz7DfNhMmep',
+            'ext': 'mp4',
+            'title': '2 Amateurs swallow make his dream cumshots true',
+            'uploader': 'figifoto',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        uploader = self._html_search_regex(
+            r'<span class="name">\s+<a class="ajax" href=".+>\s+<strong>([^<]+)<', webpage, 'uploader', fatal=False)
+        flashvars = compat_parse_qs(self._html_search_regex(
+            r'<embed.+?flashvars="([^"]+)"',
+            webpage, 'flashvars'))
+        title = flashvars['video_vars[title]'][0]
+        thumbnail = try_get(flashvars, lambda x: x['video_vars[big_thumb]'][0])
+        formats = []
+        for k, v in flashvars.items():
+            height = self._search_regex(r'video_vars\[video_urls\]\[(\d+).+?\]', k, 'height', default=None)
+            if height:
+                url = v[0]
+                formats.append({
+                    'height': int_or_none(height),
+                    'url': url
+                })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': title,
+            'uploader': uploader,
+            'thumbnail': thumbnail,
+            'age_limit': 18,
+        }