From d90b3854ca9e8602f440cc9439e1cba240192286 Mon Sep 17 00:00:00 2001 From: PeterDing Date: Thu, 28 May 2015 00:37:00 +0800 Subject: [PATCH 1/3] [porn91] Add new extractor for 91porn.com --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/porn91.py | 62 ++++++++++++++++++++++++++++++++ 2 files changed, 63 insertions(+) create mode 100644 youtube_dl/extractor/porn91.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 80c9cb107..d20ad286d 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -400,6 +400,7 @@ 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 index 000000000..af06af2b7 --- /dev/null +++ b/youtube_dl/extractor/porn91.py @@ -0,0 +1,62 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re +import json + +from ..compat import compat_urllib_parse +from .common import InfoExtractor +from ..utils import ExtractorError + + +class Porn91IE(InfoExtractor): + IE_NAME = '91porn' + _VALID_URL = r'(?:https?://)(?:www\.|)91porn\.com/.+?\?viewkey=(?P[\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' + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + 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") + title = re.search( + r'
(.+?)
', + webpage, + re.DOTALL) + assert title + title = title.group(1).replace('\n', '') + + # get real url + n1 = re.search(r'so.addVariable\(\'file\',\'(\d+)\'', webpage) + n2 = re.search(r'so.addVariable\(\'seccode\',\'(.+?)\'', webpage) + n3 = re.search(r'so.addVariable\(\'max_vid\',\'(\d+)\'', webpage) + if not (n1 and n2 and n3): + raise ExtractorError("You are Blocked by Server.") + + url_params = compat_urllib_parse.urlencode({ + 'VID': n1.group(1), + 'mp4': '1', + 'seccode': n2.group(1), + 'max_vid': n3.group(1), + }) + t_url = 'http://91porn.com/getfile.php?' + url_params + info_cn = self._download_webpage(t_url, video_id, "get real video_url") + video_url = re.search(r'file=(http.+?)&', info_cn).group(1) + + info = { + 'id': video_id, + 'title': title, + 'url': video_url, + } + + return info From 703d78bbf5edf73f60447ac273c0d303d28cc340 Mon Sep 17 00:00:00 2001 From: PeterDing Date: Thu, 28 May 2015 01:37:24 +0800 Subject: [PATCH 2/3] [porn91] change re to _search_regex --- youtube_dl/extractor/porn91.py | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) diff --git a/youtube_dl/extractor/porn91.py b/youtube_dl/extractor/porn91.py index af06af2b7..f3a97df64 100644 --- a/youtube_dl/extractor/porn91.py +++ b/youtube_dl/extractor/porn91.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals import re -import json from ..compat import compat_urllib_parse from .common import InfoExtractor @@ -29,30 +28,32 @@ def _real_extract(self, 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") - title = re.search( - r'
(.+?)
', - webpage, - re.DOTALL) + title = self._search_regex( + r'
(?P.+?)</div>', + webpage, 'title', flags=re.DOTALL) assert title - title = title.group(1).replace('\n', '') + title = title.replace('\n', '') # get real url - n1 = re.search(r'so.addVariable\(\'file\',\'(\d+)\'', webpage) - n2 = re.search(r'so.addVariable\(\'seccode\',\'(.+?)\'', webpage) - n3 = re.search(r'so.addVariable\(\'max_vid\',\'(\d+)\'', webpage) + n1 = self._search_regex( + r'so.addVariable\(\'file\',\'(?P<n1>\d+)\'', webpage, 'n1') + n2 = self._search_regex( + r'so.addVariable\(\'seccode\',\'(?P<n2>.+?)\'', webpage, 'n2') + n3 = self._search_regex( + r'so.addVariable\(\'max_vid\',\'(?P<n3>\d+)\'', webpage, 'n3') if not (n1 and n2 and n3): raise ExtractorError("You are Blocked by Server.") - url_params = compat_urllib_parse.urlencode({ - 'VID': n1.group(1), + 'VID': n1, 'mp4': '1', - 'seccode': n2.group(1), - 'max_vid': n3.group(1), + 'seccode': n2, + 'max_vid': n3, }) t_url = 'http://91porn.com/getfile.php?' + url_params info_cn = self._download_webpage(t_url, video_id, "get real video_url") - video_url = re.search(r'file=(http.+?)&', info_cn).group(1) + video_url = self._search_regex(r'file=(?P<url>http.+?)&', info_cn, 'url') + # construct info info = { 'id': video_id, 'title': title, From 806598b94dec1268566ae71d671116060f7971d6 Mon Sep 17 00:00:00 2001 From: PeterDing <dfhayst@gmail.com> Date: Fri, 29 May 2015 08:21:24 +0800 Subject: [PATCH 3/3] [porn91] the one that _search_regex returns not needs to be checked --- youtube_dl/extractor/porn91.py | 3 --- 1 file changed, 3 deletions(-) diff --git a/youtube_dl/extractor/porn91.py b/youtube_dl/extractor/porn91.py index f3a97df64..b62eec92d 100644 --- a/youtube_dl/extractor/porn91.py +++ b/youtube_dl/extractor/porn91.py @@ -31,7 +31,6 @@ def _real_extract(self, url): title = self._search_regex( r'<div id="viewvideo-title">(?P<title>.+?)</div>', webpage, 'title', flags=re.DOTALL) - assert title title = title.replace('\n', '') # get real url @@ -41,8 +40,6 @@ def _real_extract(self, url): r'so.addVariable\(\'seccode\',\'(?P<n2>.+?)\'', webpage, 'n2') n3 = self._search_regex( r'so.addVariable\(\'max_vid\',\'(?P<n3>\d+)\'', webpage, 'n3') - if not (n1 and n2 and n3): - raise ExtractorError("You are Blocked by Server.") url_params = compat_urllib_parse.urlencode({ 'VID': n1, 'mp4': '1',