From d90b3854ca9e8602f440cc9439e1cba240192286 Mon Sep 17 00:00:00 2001 From: PeterDing Date: Thu, 28 May 2015 00:37:00 +0800 Subject: [PATCH 1/8] [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 80c9cb1075..d20ad286d1 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 0000000000..af06af2b70 --- /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 2/8] [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 af06af2b70..f3a97df64a 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 3/8] [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 f3a97df64a..b62eec92d6 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', From 9ff811c5cddbf3481fdcd44e97cf3683a925b33f Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan <yan12125@gmail.com> Date: Sat, 30 May 2015 23:35:55 +0800 Subject: [PATCH 4/8] [porn91] PEP8 --- youtube_dl/extractor/porn91.py | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/porn91.py b/youtube_dl/extractor/porn91.py index b62eec92d6..cdf308f3d7 100644 --- a/youtube_dl/extractor/porn91.py +++ b/youtube_dl/extractor/porn91.py @@ -5,7 +5,6 @@ from ..compat import compat_urllib_parse from .common import InfoExtractor -from ..utils import ExtractorError class Porn91IE(InfoExtractor): @@ -13,13 +12,13 @@ class Porn91IE(InfoExtractor): _VALID_URL = r'(?:https?://)(?:www\.|)91porn\.com/.+?\?viewkey=(?P<id>[\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' - } + '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): From 1c2223875664f99325b73fe7765677db9b87e105 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan <yan12125@gmail.com> Date: Sun, 31 May 2015 00:03:19 +0800 Subject: [PATCH 5/8] [porn91] Simplify --- youtube_dl/extractor/porn91.py | 38 ++++++++++++++-------------------- 1 file changed, 16 insertions(+), 22 deletions(-) diff --git a/youtube_dl/extractor/porn91.py b/youtube_dl/extractor/porn91.py index cdf308f3d7..377ca2c773 100644 --- a/youtube_dl/extractor/porn91.py +++ b/youtube_dl/extractor/porn91.py @@ -1,8 +1,6 @@ # encoding: utf-8 from __future__ import unicode_literals -import re - from ..compat import compat_urllib_parse from .common import InfoExtractor @@ -22,38 +20,34 @@ class Porn91IE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(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 = self._search_regex( - r'<div id="viewvideo-title">(?P<title>.+?)</div>', - webpage, 'title', flags=re.DOTALL) + r'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title') title = title.replace('\n', '') # get real url - 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') + file_id = self._search_regex( + r'so.addVariable\(\'file\',\'(\d+)\'', webpage, 'file id') + sec_code = self._search_regex( + r'so.addVariable\(\'seccode\',\'([^\']+)\'', webpage, 'sec code') + max_vid = self._search_regex( + r'so.addVariable\(\'max_vid\',\'(\d+)\'', webpage, 'max vid') url_params = compat_urllib_parse.urlencode({ - 'VID': n1, + 'VID': file_id, 'mp4': '1', - 'seccode': n2, - 'max_vid': n3, + 'seccode': sec_code, + 'max_vid': max_vid, }) - t_url = 'http://91porn.com/getfile.php?' + url_params - info_cn = self._download_webpage(t_url, video_id, "get real video_url") - video_url = self._search_regex(r'file=(?P<url>http.+?)&', info_cn, 'url') + info_cn = self._download_webpage( + 'http://91porn.com/getfile.php?' + url_params, video_id, + "get real video url") + video_url = self._search_regex(r'file=([^&]+)&', info_cn, 'url') - # construct info - info = { + return { 'id': video_id, 'title': title, 'url': video_url, } - - return info From a80601f8d9789e27c0a916e63d7192c3f398d5d5 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan <yan12125@gmail.com> Date: Sun, 31 May 2015 00:20:37 +0800 Subject: [PATCH 6/8] [porn91] Extract more info --- youtube_dl/extractor/porn91.py | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/porn91.py b/youtube_dl/extractor/porn91.py index 377ca2c773..ea1efc71b2 100644 --- a/youtube_dl/extractor/porn91.py +++ b/youtube_dl/extractor/porn91.py @@ -3,6 +3,10 @@ from ..compat import compat_urllib_parse from .common import InfoExtractor +from ..utils import ( + parse_duration, + int_or_none, +) class Porn91IE(InfoExtractor): @@ -15,7 +19,8 @@ class Porn91IE(InfoExtractor): 'info_dict': { 'id': '7e42283b4f5ab36da134', 'title': '18岁大一漂亮学妹，水嫩性感，再爽一次！', - 'ext': 'mp4' + 'ext': 'mp4', + 'duration': 431, } } @@ -46,8 +51,16 @@ def _real_extract(self, url): "get real video url") video_url = self._search_regex(r'file=([^&]+)&', info_cn, 'url') + duration = parse_duration(self._search_regex( + r'时长:\s*</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False)) + + comment_count = int_or_none(self._search_regex( + r'留言:\s*</span>\s*(\d+)', webpage, 'comment count', fatal=False)) + return { 'id': video_id, 'title': title, 'url': video_url, + 'duration': duration, + 'comment_count': comment_count, } From d05a1dbe7013d6314ec477b50d864726e509a872 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan <yan12125@gmail.com> Date: Sun, 31 May 2015 00:26:12 +0800 Subject: [PATCH 7/8] [porn91] Catch daily limit error --- youtube_dl/extractor/porn91.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/youtube_dl/extractor/porn91.py b/youtube_dl/extractor/porn91.py index ea1efc71b2..c119c7e94a 100644 --- a/youtube_dl/extractor/porn91.py +++ b/youtube_dl/extractor/porn91.py @@ -6,6 +6,7 @@ from ..utils import ( parse_duration, int_or_none, + ExtractorError, ) @@ -29,6 +30,10 @@ 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") + + if '作为游客，你每天只可观看10个视频' in webpage: + raise ExtractorError('91 Porn says: Daily limit 10 videos exceeded', expected=True) + title = self._search_regex( r'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title') title = title.replace('\n', '') From a2d971309b75c79f3f688a0c381707d828cb1026 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan <yan12125@gmail.com> Date: Sun, 31 May 2015 00:31:18 +0800 Subject: [PATCH 8/8] [porn91] Use single quotes --- youtube_dl/extractor/porn91.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/porn91.py b/youtube_dl/extractor/porn91.py index c119c7e94a..72d1b27186 100644 --- a/youtube_dl/extractor/porn91.py +++ b/youtube_dl/extractor/porn91.py @@ -29,7 +29,7 @@ def _real_extract(self, url): video_id = self._match_id(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") + webpage = self._download_webpage(url, video_id, 'get HTML content') if '作为游客，你每天只可观看10个视频' in webpage: raise ExtractorError('91 Porn says: Daily limit 10 videos exceeded', expected=True) @@ -53,7 +53,7 @@ def _real_extract(self, url): }) info_cn = self._download_webpage( 'http://91porn.com/getfile.php?' + url_params, video_id, - "get real video url") + 'get real video url') video_url = self._search_regex(r'file=([^&]+)&', info_cn, 'url') duration = parse_duration(self._search_regex(