From 7eb21356f98315b15fc05d9e616951511253076f Mon Sep 17 00:00:00 2001
From: peugeot <peugeot@psa.fr>
Date: Sun, 31 Aug 2014 12:48:34 +0200
Subject: [PATCH 1/2] Add support for sunporno.com
---
youtube_dl/extractor/__init__.py | 1 +
youtube_dl/extractor/sunporno.py | 57 ++++++++++++++++++++++++++++++++
2 files changed, 58 insertions(+)
create mode 100644 youtube_dl/extractor/sunporno.py
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 1479d998a2..72b01505de 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -322,6 +322,7 @@ from .stanfordoc import StanfordOpenClassroomIE
from .steam import SteamIE
from .streamcloud import StreamcloudIE
from .streamcz import StreamCZIE
+from .sunporno import SunPornoIE
from .swrmediathek import SWRMediathekIE
from .syfy import SyfyIE
from .sztvhu import SztvHuIE
diff --git a/youtube_dl/extractor/sunporno.py b/youtube_dl/extractor/sunporno.py
new file mode 100644
index 0000000000..2a193dee3d
--- /dev/null
+++ b/youtube_dl/extractor/sunporno.py
@@ -0,0 +1,57 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ parse_duration,
+ int_or_none,
+)
+
+
+class SunPornoIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?sunporno\.com/videos/(?P<id>\d+)'
+ _TEST = {
+ 'url': 'http://www.sunporno.com/videos/807778/',
+ 'md5': '6457d3c165fd6de062b99ef6c2ff4c86',
+ 'info_dict': {
+ 'id': '807778',
+ 'ext': 'flv',
+ 'title': 'md5:0a400058e8105d39e35c35e7c5184164',
+ 'description': 'md5:a31241990e1bd3a64e72ae99afb325fb',
+ 'duration': 302,
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, video_id)
+
+ video_url = self._html_search_regex(
+ r'videoSource\s*=\s*\'<source\s*src="([^"]*)"', webpage, 'video URL')
+
+ title = self._html_search_regex(r'<title>([^<]*)</title>', webpage, 'title')
+
+ description = self._html_search_regex(
+ r'<meta name="description" content="([^"]*)"', webpage, 'description', fatal=False)
+
+ thumbnail = self._html_search_regex(
+ r'poster="([^"]*)"', webpage, 'thumbnail', fatal=False)
+
+ duration = parse_duration(self._search_regex(
+ r'<span>Duration: (\d+:\d+)</span>', webpage, 'duration', fatal=False))
+
+ view_count = int_or_none(self._html_search_regex(
+ r'<span class="views">(\d+)</span>', webpage, 'view count', fatal=False))
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'view_count': view_count,
+ }
From ae7246e7d57654381fb629be46662f8e4ded615f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com>
Date: Mon, 1 Sep 2014 01:08:19 +0700
Subject: [PATCH 2/2] [sunporno] Extract all formats and metadata
---
youtube_dl/extractor/sunporno.py | 31 +++++++++++++++++++++----------
1 file changed, 21 insertions(+), 10 deletions(-)
diff --git a/youtube_dl/extractor/sunporno.py b/youtube_dl/extractor/sunporno.py
index 2a193dee3d..c7a46eb718 100644
--- a/youtube_dl/extractor/sunporno.py
+++ b/youtube_dl/extractor/sunporno.py
@@ -6,6 +6,8 @@ from .common import InfoExtractor
from ..utils import (
parse_duration,
int_or_none,
+ qualities,
+ determine_ext,
)
@@ -19,6 +21,7 @@ class SunPornoIE(InfoExtractor):
'ext': 'flv',
'title': 'md5:0a400058e8105d39e35c35e7c5184164',
'description': 'md5:a31241990e1bd3a64e72ae99afb325fb',
+ 'thumbnail': 're:^https?://.*\.jpg$',
'duration': 302,
}
}
@@ -29,29 +32,37 @@ class SunPornoIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
- video_url = self._html_search_regex(
- r'videoSource\s*=\s*\'<source\s*src="([^"]*)"', webpage, 'video URL')
-
- title = self._html_search_regex(r'<title>([^<]*)</title>', webpage, 'title')
-
- description = self._html_search_regex(
- r'<meta name="description" content="([^"]*)"', webpage, 'description', fatal=False)
-
+ title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'title')
+ description = self._html_search_meta('description', webpage, 'description')
thumbnail = self._html_search_regex(
- r'poster="([^"]*)"', webpage, 'thumbnail', fatal=False)
+ r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
duration = parse_duration(self._search_regex(
r'<span>Duration: (\d+:\d+)</span>', webpage, 'duration', fatal=False))
view_count = int_or_none(self._html_search_regex(
r'<span class="views">(\d+)</span>', webpage, 'view count', fatal=False))
+ comment_count = int_or_none(self._html_search_regex(
+ r'(\d+)</b> Comments?', webpage, 'comment count', fatal=False))
+
+ formats = []
+ quality = qualities(['mp4', 'flv'])
+ for video_url in re.findall(r'<source src="([^"]+)"', webpage):
+ video_ext = determine_ext(video_url)
+ formats.append({
+ 'url': video_url,
+ 'format_id': video_ext,
+ 'quality': quality(video_ext),
+ })
+ self._sort_formats(formats)
return {
'id': video_id,
- 'url': video_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'view_count': view_count,
+ 'comment_count': comment_count,
+ 'formats': formats,
}