commit 14638e291511c3305b70dce64e9bd97686e9da93
parent 1910077ed77a270fea8e368c3815b23cee254f85
Author: Yen Chi Hsuan <yan12125@gmail.com>
Date: Fri, 29 Apr 2016 18:17:08 +0800
[sexykarma] Rename to WatchIndianPornIE and fix extraction
Diffstat:
3 files changed, 91 insertions(+), 122 deletions(-)
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
@@ -657,7 +657,6 @@ from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE
from .senateisvp import SenateISVPIE
from .servingsys import ServingSysIE
from .sexu import SexuIE
-from .sexykarma import SexyKarmaIE
from .shahid import ShahidIE
from .shared import SharedIE
from .sharesix import ShareSixIE
@@ -918,6 +917,7 @@ from .vulture import VultureIE
from .walla import WallaIE
from .washingtonpost import WashingtonPostIE
from .wat import WatIE
+from .watchindianporn import WatchIndianPornIE
from .wdr import (
WDRIE,
WDRMobileIE,
diff --git a/youtube_dl/extractor/sexykarma.py b/youtube_dl/extractor/sexykarma.py
@@ -1,121 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
- unified_strdate,
- parse_duration,
- int_or_none,
-)
-
-
-class SexyKarmaIE(InfoExtractor):
- IE_DESC = 'Sexy Karma and Watch Indian Porn'
- _VALID_URL = r'https?://(?:www\.)?(?:sexykarma\.com|watchindianporn\.net)/(?:[^/]+/)*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.',
- 'thumbnail': 're:^https?://.*\.jpg$',
- 'uploader': 'wildginger7',
- 'upload_date': '20141008',
- 'duration': 22,
- 'view_count': int,
- 'comment_count': int,
- 'categories': list,
- 'age_limit': 18,
- }
- }, {
- 'url': 'http://www.sexykarma.com/gonewild/video/pot-pixie-tribute-8Id6EZPbuHf.html',
- 'md5': 'dd216c68d29b49b12842b9babe762a5d',
- 'info_dict': {
- 'id': '8Id6EZPbuHf',
- 'display_id': 'pot-pixie-tribute',
- 'ext': 'mp4',
- 'title': 'pot_pixie tribute',
- 'thumbnail': 're:^https?://.*\.jpg$',
- 'uploader': 'banffite',
- 'upload_date': '20141013',
- 'duration': 16,
- 'view_count': int,
- 'comment_count': int,
- 'categories': list,
- 'age_limit': 18,
- }
- }, {
- 'url': 'http://www.watchindianporn.net/video/desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number-dW2mtctxJfs.html',
- 'md5': '9afb80675550406ed9a63ac2819ef69d',
- 'info_dict': {
- 'id': 'dW2mtctxJfs',
- 'display_id': 'desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number',
- 'ext': 'mp4',
- 'title': 'Desi dancer namrata stripping completely nude and dancing on a hot number',
- 'thumbnail': 're:^https?://.*\.jpg$',
- 'uploader': 'Don',
- 'upload_date': '20140213',
- 'duration': 83,
- 'view_count': int,
- 'comment_count': int,
- 'categories': list,
- 'age_limit': 18,
- }
- }]
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
- display_id = mobj.group('display_id')
-
- webpage = self._download_webpage(url, display_id)
-
- video_url = self._html_search_regex(
- r"url: escape\('([^']+)'\)", webpage, 'url')
-
- title = self._html_search_regex(
- r'<h2 class="he2"><span>(.*?)</span>',
- webpage, 'title')
- thumbnail = self._html_search_regex(
- r'<span id="container"><img\s+src="([^"]+)"',
- webpage, 'thumbnail', fatal=False)
-
- 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 = re.findall(
- r'<a href="[^"]+/search/video/desi"><span>([^<]+)</span></a>',
- webpage)
-
- return {
- 'id': video_id,
- 'display_id': display_id,
- 'url': video_url,
- 'title': title,
- 'thumbnail': thumbnail,
- 'uploader': uploader,
- 'upload_date': upload_date,
- 'duration': duration,
- 'view_count': view_count,
- 'comment_count': comment_count,
- 'categories': categories,
- 'age_limit': 18,
- }
diff --git a/youtube_dl/extractor/watchindianporn.py b/youtube_dl/extractor/watchindianporn.py
@@ -0,0 +1,90 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ unified_strdate,
+ parse_duration,
+ int_or_none,
+)
+
+
+class WatchIndianPornIE(InfoExtractor):
+ IE_DESC = 'Watch Indian Porn'
+ _VALID_URL = r'https?://(?:www\.)?watchindianporn\.net/(?:[^/]+/)*video/(?P<display_id>[^/]+)-(?P<id>[a-zA-Z0-9]+)\.html'
+ _TEST = {
+ 'url': 'http://www.watchindianporn.net/video/hot-milf-from-kerala-shows-off-her-gorgeous-large-breasts-on-camera-RZa2avywNPa.html',
+ 'md5': '249589a164dde236ec65832bfce17440',
+ 'info_dict': {
+ 'id': 'RZa2avywNPa',
+ 'display_id': 'hot-milf-from-kerala-shows-off-her-gorgeous-large-breasts-on-camera',
+ 'ext': 'mp4',
+ 'title': 'Hot milf from kerala shows off her gorgeous large breasts on camera',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'uploader': 'LoveJay',
+ 'upload_date': '20160428',
+ 'duration': 226,
+ 'view_count': int,
+ 'comment_count': int,
+ 'categories': list,
+ 'age_limit': 18,
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ display_id = mobj.group('display_id')
+
+ webpage = self._download_webpage(url, display_id)
+
+ video_url = self._html_search_regex(
+ r"url: escape\('([^']+)'\)", webpage, 'url')
+
+ title = self._html_search_regex(
+ r'<h2 class="he2"><span>(.*?)</span>',
+ webpage, 'title')
+ thumbnail = self._html_search_regex(
+ r'<span id="container"><img\s+src="([^"]+)"',
+ webpage, 'thumbnail', fatal=False)
+
+ 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 = re.findall(
+ r'<a href="[^"]+/search/video/desi"><span>([^<]+)</span></a>',
+ webpage)
+
+ return {
+ 'id': video_id,
+ 'display_id': display_id,
+ 'url': video_url,
+ 'http_headers': {
+ 'Referer': url,
+ },
+ 'title': title,
+ 'thumbnail': thumbnail,
+ 'uploader': uploader,
+ 'upload_date': upload_date,
+ 'duration': duration,
+ 'view_count': view_count,
+ 'comment_count': comment_count,
+ 'categories': categories,
+ 'age_limit': 18,
+ }
