From 474086450808541954e402dd3d58bad38b75b1d5 Mon Sep 17 00:00:00 2001
From: CkuT <s3cu@hotmail.fr>
Date: Wed, 15 Oct 2014 18:24:32 +0200
Subject: [PATCH 1/4] [SexyKarma] Add new extractor
---
youtube_dl/extractor/__init__.py | 1 +
youtube_dl/extractor/sexykarma.py | 43 +++++++++++++++++++++++++++++++
2 files changed, 44 insertions(+)
create mode 100644 youtube_dl/extractor/sexykarma.py
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 5e38d26630..92f38dcd00 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -316,6 +316,7 @@ from .sbs import SBSIE
from .scivee import SciVeeIE
from .screencast import ScreencastIE
from .servingsys import ServingSysIE
+from .sexykarma import SexyKarmaIE
from .shared import SharedIE
from .sharesix import ShareSixIE
from .sina import SinaIE
diff --git a/youtube_dl/extractor/sexykarma.py b/youtube_dl/extractor/sexykarma.py
new file mode 100644
index 0000000000..cd2668872b
--- /dev/null
+++ b/youtube_dl/extractor/sexykarma.py
@@ -0,0 +1,43 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class SexyKarmaIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?sexykarma\.com/gonewild/video/(?P<id>[a-zA-Z0-9\-]+)(.html)'
+ _TESTS = [{
+ 'url': 'http://www.sexykarma.com/gonewild/video/taking-a-quick-pee-yHI70cOyIHt.html',
+ 'md5': 'b9798e7d1ef1765116a8f516c8091dbd',
+ 'info_dict': {
+ 'id': 'taking-a-quick-pee-yHI70cOyIHt',
+ 'ext': 'mp4',
+ 'title': 'Taking a quick pee.',
+ 'uploader': 'wildginger7',
+ }
+ }, {
+ 'url': 'http://www.sexykarma.com/gonewild/video/pot-pixie-tribute-8Id6EZPbuHf.html',
+ 'md5': 'dd216c68d29b49b12842b9babe762a5d',
+ 'info_dict': {
+ 'id': 'pot-pixie-tribute-8Id6EZPbuHf',
+ 'ext': 'mp4',
+ 'title': 'pot_pixie tribute',
+ 'uploader': 'banffite',
+ }
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ # TODO more code goes here, for example ...
+ webpage = self._download_webpage(url, video_id)
+ title = self._html_search_regex(r'<h2 class="he2"><span>(.*?)</span>', webpage, 'title')
+ uploader = self._html_search_regex(r'class="aupa">\n*(.*?)</a>', webpage, 'uploader')
+ url = self._html_search_regex(r'<p><a href="(.*?)" ?\n*target="_blank"><font color', webpage, 'url')
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'uploader': uploader,
+ 'url': url
+ }
From 1723edb1a589190b8a91af12bd7dadaa50e26549 Mon Sep 17 00:00:00 2001
From: CkuT <s3cu@hotmail.fr>
Date: Wed, 15 Oct 2014 20:17:07 +0200
Subject: [PATCH 2/4] Few improvements
---
youtube_dl/extractor/sexykarma.py | 51 +++++++++++++++++++++++++------
1 file changed, 41 insertions(+), 10 deletions(-)
diff --git a/youtube_dl/extractor/sexykarma.py b/youtube_dl/extractor/sexykarma.py
index cd2668872b..ac7745e74e 100644
--- a/youtube_dl/extractor/sexykarma.py
+++ b/youtube_dl/extractor/sexykarma.py
@@ -2,42 +2,73 @@
from __future__ import unicode_literals
from .common import InfoExtractor
-
+import re
+import datetime
class SexyKarmaIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?sexykarma\.com/gonewild/video/(?P<id>[a-zA-Z0-9\-]+)(.html)'
+ _VALID_URL = r'https?://(?:www\.)?sexykarma\.com/gonewild/video/.+\-(?P<id>[a-zA-Z0-9\-]+)(.html)'
_TESTS = [{
'url': 'http://www.sexykarma.com/gonewild/video/taking-a-quick-pee-yHI70cOyIHt.html',
'md5': 'b9798e7d1ef1765116a8f516c8091dbd',
'info_dict': {
- 'id': 'taking-a-quick-pee-yHI70cOyIHt',
+ 'id': 'yHI70cOyIHt',
'ext': 'mp4',
'title': 'Taking a quick pee.',
- 'uploader': 'wildginger7',
+ 'uploader_id': 'wildginger7',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': int,
+ 'view_count': int,
+ 'upload_date': '20141007',
}
}, {
'url': 'http://www.sexykarma.com/gonewild/video/pot-pixie-tribute-8Id6EZPbuHf.html',
'md5': 'dd216c68d29b49b12842b9babe762a5d',
'info_dict': {
- 'id': 'pot-pixie-tribute-8Id6EZPbuHf',
+ 'id': '8Id6EZPbuHf',
'ext': 'mp4',
'title': 'pot_pixie tribute',
- 'uploader': 'banffite',
+ 'uploader_id': 'banffite',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': int,
+ 'view_count': int,
+ 'upload_date': '20141013',
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
- # TODO more code goes here, for example ...
webpage = self._download_webpage(url, video_id)
+
title = self._html_search_regex(r'<h2 class="he2"><span>(.*?)</span>', webpage, 'title')
- uploader = self._html_search_regex(r'class="aupa">\n*(.*?)</a>', webpage, 'uploader')
+ uploader_id = self._html_search_regex(r'class="aupa">\n*(.*?)</a>', webpage, 'uploader')
url = self._html_search_regex(r'<p><a href="(.*?)" ?\n*target="_blank"><font color', webpage, 'url')
+ thumbnail = self._html_search_regex(r'<div id="player" style="z-index:1;"> <span id="edge"></span> <span id="container"><img[\n ]*src="(.+?)"', webpage, 'thumbnail')
+
+ str_duration = self._html_search_regex(r'<tr>[\n\s]*<td>Time: </td>[\n\s]*<td align="right"><span>(.+)\n*', webpage, 'duration')
+ duration = self._to_seconds(str_duration)
+
+ str_views = self._html_search_regex(r'<tr>[\n\s]*<td>Views: </td>[\n\s]*<td align="right"><span>(.+)</span>', webpage, 'view_count')
+ view_count = int(str_views)
+ # print view_count
+
+ date = self._html_search_regex(r'class="aup">Added: <strong>(.*?)</strong>', webpage, 'date')
+ d = datetime.datetime.strptime(date, '%B %d, %Y')
+ upload_date = d.strftime('%Y%m%d')
return {
'id': video_id,
'title': title,
- 'uploader': uploader,
- 'url': url
+ 'uploader_id': uploader_id,
+ 'url': url,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'view_count': view_count,
+ 'upload_date': upload_date,
}
+
+ def _to_seconds(self, timestr):
+ seconds= 0
+ for part in timestr.split(':'):
+ seconds= seconds*60 + int(part)
+ return seconds
From 7da224c907627b5b0233c7eb4eea733f5f97ae90 Mon Sep 17 00:00:00 2001
From: CkuT <s3cu@hotmail.fr>
Date: Wed, 15 Oct 2014 22:34:35 +0200
Subject: [PATCH 3/4] Add categories
---
youtube_dl/extractor/sexykarma.py | 3 +++
1 file changed, 3 insertions(+)
diff --git a/youtube_dl/extractor/sexykarma.py b/youtube_dl/extractor/sexykarma.py
index ac7745e74e..629499e723 100644
--- a/youtube_dl/extractor/sexykarma.py
+++ b/youtube_dl/extractor/sexykarma.py
@@ -56,6 +56,8 @@ class SexyKarmaIE(InfoExtractor):
d = datetime.datetime.strptime(date, '%B %d, %Y')
upload_date = d.strftime('%Y%m%d')
+ categories = re.findall(r'http://www.sexykarma.com/gonewild/search/video/(?:.+?)"><span>(.*?)</span>', webpage)
+
return {
'id': video_id,
'title': title,
@@ -65,6 +67,7 @@ class SexyKarmaIE(InfoExtractor):
'duration': duration,
'view_count': view_count,
'upload_date': upload_date,
+ 'categories': categories,
}
def _to_seconds(self, timestr):
From 95fa5fb569c9a29d1dfb7da744022373d279fcb7 Mon Sep 17 00:00:00 2001
From: Sergey M <dstftw@gmail.com>
Date: Sun, 19 Oct 2014 00:48:05 +0700
Subject: [PATCH 4/4] [sexykarma] Improve and simplify
---
youtube_dl/extractor/sexykarma.py | 99 ++++++++++++++++++++-----------
1 file changed, 64 insertions(+), 35 deletions(-)
diff --git a/youtube_dl/extractor/sexykarma.py b/youtube_dl/extractor/sexykarma.py
index 629499e723..4a6345758a 100644
--- a/youtube_dl/extractor/sexykarma.py
+++ b/youtube_dl/extractor/sexykarma.py
@@ -1,77 +1,106 @@
# coding: utf-8
from __future__ import unicode_literals
-from .common import InfoExtractor
import re
-import datetime
+
+from .common import InfoExtractor
+from ..utils import (
+ unified_strdate,
+ parse_duration,
+ int_or_none,
+)
+
class SexyKarmaIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?sexykarma\.com/gonewild/video/.+\-(?P<id>[a-zA-Z0-9\-]+)(.html)'
+ _VALID_URL = r'https?://(?:www\.)?sexykarma\.com/gonewild/video/(?P<display_id>[^/]+)-(?P<id>[a-zA-Z0-9]+)\.html'
_TESTS = [{
'url': 'http://www.sexykarma.com/gonewild/video/taking-a-quick-pee-yHI70cOyIHt.html',
'md5': 'b9798e7d1ef1765116a8f516c8091dbd',
'info_dict': {
'id': 'yHI70cOyIHt',
+ 'display_id': 'taking-a-quick-pee',
'ext': 'mp4',
'title': 'Taking a quick pee.',
- 'uploader_id': 'wildginger7',
+ 'description': '',
'thumbnail': 're:^https?://.*\.jpg$',
- 'duration': int,
- 'view_count': int,
+ 'uploader': 'wildginger7',
'upload_date': '20141007',
+ 'duration': 81,
+ 'view_count': int,
+ 'comment_count': int,
+ 'categories': list,
}
}, {
'url': 'http://www.sexykarma.com/gonewild/video/pot-pixie-tribute-8Id6EZPbuHf.html',
'md5': 'dd216c68d29b49b12842b9babe762a5d',
'info_dict': {
'id': '8Id6EZPbuHf',
+ 'display_id': 'pot-pixie-tribute',
'ext': 'mp4',
'title': 'pot_pixie tribute',
- 'uploader_id': 'banffite',
+ 'description': 'tribute',
'thumbnail': 're:^https?://.*\.jpg$',
- 'duration': int,
- 'view_count': int,
+ 'uploader': 'banffite',
'upload_date': '20141013',
+ 'duration': 16,
+ 'view_count': int,
+ 'comment_count': int,
+ 'categories': list,
}
}]
def _real_extract(self, url):
- video_id = self._match_id(url)
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ display_id = mobj.group('display_id')
- webpage = self._download_webpage(url, video_id)
-
- title = self._html_search_regex(r'<h2 class="he2"><span>(.*?)</span>', webpage, 'title')
- uploader_id = self._html_search_regex(r'class="aupa">\n*(.*?)</a>', webpage, 'uploader')
- url = self._html_search_regex(r'<p><a href="(.*?)" ?\n*target="_blank"><font color', webpage, 'url')
- thumbnail = self._html_search_regex(r'<div id="player" style="z-index:1;"> <span id="edge"></span> <span id="container"><img[\n ]*src="(.+?)"', webpage, 'thumbnail')
-
- str_duration = self._html_search_regex(r'<tr>[\n\s]*<td>Time: </td>[\n\s]*<td align="right"><span>(.+)\n*', webpage, 'duration')
- duration = self._to_seconds(str_duration)
+ webpage = self._download_webpage(url, display_id)
- str_views = self._html_search_regex(r'<tr>[\n\s]*<td>Views: </td>[\n\s]*<td align="right"><span>(.+)</span>', webpage, 'view_count')
- view_count = int(str_views)
- # print view_count
+ video_url = self._html_search_regex(
+ r'<p>Save this video to your computer: </p><p><a href="([^"]+)"',
+ webpage, 'url')
- date = self._html_search_regex(r'class="aup">Added: <strong>(.*?)</strong>', webpage, 'date')
- d = datetime.datetime.strptime(date, '%B %d, %Y')
- upload_date = d.strftime('%Y%m%d')
+ title = self._html_search_regex(
+ r'<h2 class="he2"><span>(.*?)</span>',
+ webpage, 'title')
+ description = self._html_search_meta(
+ 'description', webpage, 'description', fatal=False, default='')
+ thumbnail = self._html_search_regex(
+ r'<span id="container"><img\s+src="([^"]+)"',
+ webpage, 'thumbnail', fatal=False)
- categories = re.findall(r'http://www.sexykarma.com/gonewild/search/video/(?:.+?)"><span>(.*?)</span>', webpage)
+ uploader = self._html_search_regex(
+ r'class="aupa">\s*(.*?)</a>',
+ webpage, 'uploader')
+ upload_date = unified_strdate(self._html_search_regex(
+ r'Added: <strong>(.+?)</strong>', webpage, 'upload date', fatal=False))
+
+ duration = parse_duration(self._search_regex(
+ r'<td>Time:\s*</td>\s*<td align="right"><span>\s*(.+?)\s*</span>',
+ webpage, 'duration', fatal=False))
+
+ view_count = int_or_none(self._search_regex(
+ r'<td>Views:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>',
+ webpage, 'view count', fatal=False))
+ comment_count = int_or_none(self._search_regex(
+ r'<td>Comments:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>',
+ webpage, 'comment count', fatal=False))
+
+ categories = self._html_search_meta(
+ 'keywords', webpage, 'categories',
+ fatal=False, default='').split(',')
return {
'id': video_id,
+ 'display_id': display_id,
+ 'url': video_url,
'title': title,
- 'uploader_id': uploader_id,
- 'url': url,
+ 'description': description,
'thumbnail': thumbnail,
+ 'uploader': uploader,
+ 'upload_date': upload_date,
'duration': duration,
'view_count': view_count,
- 'upload_date': upload_date,
+ 'comment_count': comment_count,
'categories': categories,
}
-
- def _to_seconds(self, timestr):
- seconds= 0
- for part in timestr.split(':'):
- seconds= seconds*60 + int(part)
- return seconds