From 110d4f4c9170c1180cf25fd14976df30744455b7 Mon Sep 17 00:00:00 2001 From: Jeff Crouse Date: Mon, 12 Nov 2012 16:17:55 -0500 Subject: Added Pornotube support (for Laborers of Love) --- youtube_dl/InfoExtractors.py | 81 ++++++++++++++++++++++++++++++++++++++++++++ youtube_dl/__init__.py | 1 + 2 files changed, 82 insertions(+) (limited to 'youtube_dl') diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index cfaef2904..acbd3fcee 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -94,6 +94,8 @@ class InfoExtractor(object): pass + + class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" @@ -3368,3 +3370,82 @@ class GooglePlusIE(InfoExtractor): 'format': u'NA', 'player_url': None, }] + + +class PornotubeIE(InfoExtractor): + """Information extractor for pornotube.com.""" + + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P[0-9]+))?(/m/(?P[0-9]+))(/(?P.+))$' + IE_NAME = u'pornotube' + VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",' + VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' + + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_extract_entry(self, url): + """Report downloading extry""" + self._downloader.to_screen(u'[pornotube] Downloading entry: %s' % url.decode('utf-8')) + + def report_date(self, upload_date): + """Report finding uploaded date""" + self._downloader.to_screen(u'[pornotube] Entry date: %s' % upload_date) + + def report_webpage(self, url): + """Report downloading page""" + self._downloader.to_screen(u'[pornotube] Downloaded page: %s' % url) + + def report_title(self, video_title): + """Report downloading extry""" + self._downloader.to_screen(u'[pornotube] Title: %s' % video_title.decode('utf-8')) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + video_id = mobj.group('videoid').decode('utf-8') + video_title = mobj.group('title').decode('utf-8') + self.report_title(video_title); + + # Get webpage content + try: + webpage = urllib2.urlopen(url).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err) + return + self.report_webpage(url) + + # Get the video URL + result = re.search(self.VIDEO_URL_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video url') + return + video_url = urllib.unquote(result.group('url').decode('utf-8')) + self.report_extract_entry(video_url) + + #Get the uploaded date + result = re.search(self.VIDEO_UPLOADED_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + upload_date = result.group('date').decode('utf-8') + self.report_date(upload_date); + + + info = {'id': video_id, + 'url': video_url, + 'uploader': None, + 'upload_date': upload_date, + 'title': video_title, + 'ext': 'flv', + 'format': 'flv', + 'thumbnail': None, + 'description': None, + 'player_url': None} + + return [info] + + diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 3aa7bde12..3b893c62f 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -361,6 +361,7 @@ def gen_extractors(): YoukuIE(), XNXXIE(), GooglePlusIE(), + PornotubeIE(), GenericIE() ] -- cgit v1.2.3 From fdef722fa1162f93ddd40687447bdf62c16d7fc1 Mon Sep 17 00:00:00 2001 From: Jeff Crouse <jefftimesten@gmail.com> Date: Tue, 13 Nov 2012 13:10:56 -0500 Subject: Added YouPorn infoExtractor --- youtube_dl/InfoExtractors.py | 162 ++++++++++++++++++++++++++++++++++++++++++- youtube_dl/__init__.py | 3 +- 2 files changed, 163 insertions(+), 2 deletions(-) (limited to 'youtube_dl') diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index acbd3fcee..8969160c4 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -15,7 +15,7 @@ import email.utils import xml.etree.ElementTree import random import math -from urlparse import parse_qs +from urlparse import parse_qs, urlparse try: import cStringIO as StringIO @@ -3372,6 +3372,166 @@ class GooglePlusIE(InfoExtractor): }] + +class YouPornIE(InfoExtractor): + """Information extractor for youporn.com.""" + + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)' + IE_NAME = u'youporn' + VIDEO_TITLE_RE = r'videoTitleArea">(?P<title>.*)</h1>' + VIDEO_DATE_RE = r'Date:</b>(?P<date>.*)</li>' + VIDEO_UPLOADER_RE = r'Submitted:</b>(?P<uploader>.*)</li>' + DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>' + LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_id(self, video_id): + """Report finding video ID""" + self._downloader.to_screen(u'[youporn] Video ID: %s' % video_id) + + def report_webpage(self, url): + """Report downloading page""" + self._downloader.to_screen(u'[youporn] Downloaded page: %s' % url) + + def report_title(self, video_title): + """Report dfinding title""" + self._downloader.to_screen(u'[youporn] Title: %s' % video_title) + + def report_uploader(self, uploader): + """Report dfinding title""" + self._downloader.to_screen(u'[youporn] Uploader: %s' % uploader) + + def report_upload_date(self, video_date): + """Report finding date""" + self._downloader.to_screen(u'[youporn] Date: %s' % video_date) + + def _print_formats(self, formats): + """Print all available formats""" + print 'Available formats:' + print u'ext\t\tformat' + print u'---------------------------------' + for format in formats: + print u'%s\t\t%s' % (format['ext'], format['format']) + + def _specific(self, req_format, formats): + for x in formats: + if(x["format"]==req_format): + return x + return None + + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + video_id = mobj.group('videoid').decode('utf-8') + self.report_id(video_id) + + # Get webpage content + try: + webpage = urllib2.urlopen(url).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err) + return + self.report_webpage(url) + + # Get the video URL + result = re.search(self.VIDEO_TITLE_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = result.group('title').decode('utf-8').strip() + self.report_title(video_title) + + # Get the video date + result = re.search(self.VIDEO_DATE_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video date') + return + upload_date = result.group('date').decode('utf-8').strip() + self.report_upload_date(upload_date) + + # Get the video uploader + result = re.search(self.VIDEO_UPLOADER_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract uploader') + return + video_uploader = result.group('uploader').decode('utf-8').strip() + self.report_uploader(video_uploader) + + # Get all of the formats available + result = re.search(self.DOWNLOAD_LIST_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract download list') + return + download_list_html = result.group('download_list').decode('utf-8').strip() + + # Get all of the links from the page + links = re.findall(self.LINK_RE, download_list_html) + if(len(links) == 0): + self._downloader.trouble(u'ERROR: no known formats available for video') + return + + self._downloader.to_screen(u'[youporn] Links found: %d' % len(links)) + + formats = [] + for link in links: + + # A link looks like this: + # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0 + # A path looks like this: + # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4 + video_url = unescapeHTML( link.decode('utf-8') ) + path = urlparse( video_url ).path + extension = os.path.splitext( path )[1][1:] + format = path.split('/')[4].split('_')[:2] + size = format[0] + bitrate = format[1] + format = "-".join( format ) + title = u'%s-%s-%s' % (video_title, size, bitrate) + + formats.append({ + 'id': video_id, + 'url': video_url, + 'uploader': video_uploader, + 'upload_date': upload_date, + 'title': title, + 'ext': extension, + 'format': format, + 'thumbnail': None, + 'description': None, + 'player_url': None + }) + + if self._downloader.params.get('listformats', None): + self._print_formats(results) + return + + req_format = self._downloader.params.get('format', None) + #format_limit = self._downloader.params.get('format_limit', None) + self._downloader.to_screen(u'[youporn] Format: %s' % req_format) + + + if req_format is None or req_format == 'best': + return [formats[0]] + elif req_format == 'worst': + return [formats[-1]] + elif req_format in ('-1', 'all'): + return formats + else: + format = self._specific( req_format, formats ) + if result is None: + self._downloader.trouble(u'ERROR: requested format not available') + return + return [format] + + + + class PornotubeIE(InfoExtractor): """Information extractor for pornotube.com.""" diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 3b893c62f..5a2a55b49 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -362,7 +362,8 @@ def gen_extractors(): XNXXIE(), GooglePlusIE(), PornotubeIE(), - + YouPornIE(), + GenericIE() ] -- cgit v1.2.3 From 5f7ad216333afc541fd28280dd3f8a5e4cf82396 Mon Sep 17 00:00:00 2001 From: Jeff Crouse <jefftimesten@gmail.com> Date: Tue, 13 Nov 2012 17:48:30 -0500 Subject: Strip HTML out of uploader name --- youtube_dl/InfoExtractors.py | 1 + 1 file changed, 1 insertion(+) (limited to 'youtube_dl') diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 8969160c4..15dd15307 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -3461,6 +3461,7 @@ class YouPornIE(InfoExtractor): self._downloader.trouble(u'ERROR: unable to extract uploader') return video_uploader = result.group('uploader').decode('utf-8').strip() + video_uploader = clean_html( video_uploader ) self.report_uploader(video_uploader) # Get all of the formats available -- cgit v1.2.3 From 9a2cf56d512d0a459af652b1262255601b4a86e8 Mon Sep 17 00:00:00 2001 From: Jeff Crouse <jefftimesten@gmail.com> Date: Sat, 15 Dec 2012 23:22:07 -0500 Subject: Fixed a problem with the XNXXIE Regex --- youtube_dl/InfoExtractors.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'youtube_dl') diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 15dd15307..c44fc852c 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -3186,7 +3186,7 @@ class YoukuIE(InfoExtractor): class XNXXIE(InfoExtractor): """Information extractor for xnxx.com""" - _VALID_URL = r'^http://video\.xnxx\.com/video([0-9]+)/(.*)' + _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)' IE_NAME = u'xnxx' VIDEO_URL_RE = r'flv_url=(.*?)&' VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM' @@ -3509,7 +3509,7 @@ class YouPornIE(InfoExtractor): }) if self._downloader.params.get('listformats', None): - self._print_formats(results) + self._print_formats(formats) return req_format = self._downloader.params.get('format', None) -- cgit v1.2.3 From 187da2c093ad1013ea714a464e615de9aa773482 Mon Sep 17 00:00:00 2001 From: Jeff Crouse <jefftimesten@gmail.com> Date: Sun, 16 Dec 2012 00:26:27 -0500 Subject: added YouJizz extractor --- youtube_dl/InfoExtractors.py | 86 +++++++++++++++++++++++++++++++++++++++++++- youtube_dl/__init__.py | 2 +- 2 files changed, 86 insertions(+), 2 deletions(-) (limited to 'youtube_dl') diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index c44fc852c..d30de6943 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -3439,7 +3439,7 @@ class YouPornIE(InfoExtractor): return self.report_webpage(url) - # Get the video URL + # Get the video title result = re.search(self.VIDEO_TITLE_RE, webpage) if result is None: self._downloader.trouble(u'ERROR: unable to extract video title') @@ -3610,3 +3610,87 @@ class PornotubeIE(InfoExtractor): return [info] + + +class YouJizzIE(InfoExtractor): + """Information extractor for youjizz.com.""" + + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/([^.]+).html$' + IE_NAME = u'youjizz' + VIDEO_TITLE_RE = r'<title>(?P<title>.*)' + EMBED_PAGE_RE = r'http://www.youjizz.com/videos/embed/(?P[0-9]+)' + SOURCE_RE = r'so.addVariable\("file",encodeURIComponent\("(?P[^"]+)"\)\);' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_extract_entry(self, url): + """Report downloading extry""" + self._downloader.to_screen(u'[youjizz] Downloading entry: %s' % url.decode('utf-8')) + + def report_webpage(self, url): + """Report downloading page""" + self._downloader.to_screen(u'[youjizz] Downloaded page: %s' % url) + + def report_title(self, video_title): + """Report downloading extry""" + self._downloader.to_screen(u'[youjizz] Title: %s' % video_title.decode('utf-8')) + + def report_embed_page(self, embed_page): + """Report downloading extry""" + self._downloader.to_screen(u'[youjizz] Embed Page: %s' % embed_page.decode('utf-8')) + + def _real_extract(self, url): + # Get webpage content + try: + webpage = urllib2.urlopen(url).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err) + return + self.report_webpage(url) + + # Get the video title + result = re.search(self.VIDEO_TITLE_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = result.group('title').decode('utf-8').strip() + self.report_title(video_title) + + # Get the embed page + result = re.search(self.EMBED_PAGE_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract embed page') + return + + embed_page_url = result.group(0).decode('utf-8').strip() + video_id = result.group('videoid').decode('utf-8') + self.report_embed_page(embed_page_url) + + try: + webpage = urllib2.urlopen(embed_page_url).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video embed page: %s' % err) + return + + # Get the video URL + result = re.search(self.SOURCE_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video url') + return + video_url = result.group('source').decode('utf-8') + self.report_extract_entry(video_url) + + info = {'id': video_id, + 'url': video_url, + 'uploader': None, + 'upload_date': None, + 'title': video_title, + 'ext': 'flv', + 'format': 'flv', + 'thumbnail': None, + 'description': None, + 'player_url': embed_page_url} + + return [info] + diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 5a2a55b49..e99ac2d59 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -363,7 +363,7 @@ def gen_extractors(): GooglePlusIE(), PornotubeIE(), YouPornIE(), - + YouJizzIE(), GenericIE() ] -- cgit v1.2.3 From 991ba7fae38498b1066c7f6821d1d8681ef87f1b Mon Sep 17 00:00:00 2001 From: Jeff Crouse Date: Sat, 5 Jan 2013 15:42:35 -0500 Subject: Added extractors for 3 porn sites --- youtube_dl/InfoExtractors.py | 328 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 328 insertions(+) (limited to 'youtube_dl') diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index e380f62a1..72ad25ad3 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -14,6 +14,10 @@ import email.utils import xml.etree.ElementTree import random import math +import urllib +import urllib2 +import httplib +from urlparse import parse_qs, urlparse from .utils import * @@ -3735,6 +3739,327 @@ class UstreamIE(InfoExtractor): return [info] + +class YouPornIE(InfoExtractor): + """Information extractor for youporn.com.""" + + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P[0-9]+)/(?P[^/]+)' + IE_NAME = u'youporn' + VIDEO_TITLE_RE = r'videoTitleArea">(?P<title>.*)</h1>' + VIDEO_DATE_RE = r'Date:</b>(?P<date>.*)</li>' + VIDEO_UPLOADER_RE = r'Submitted:</b>(?P<uploader>.*)</li>' + DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>' + LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_id(self, video_id): + """Report finding video ID""" + self._downloader.to_screen(u'[youporn] Video ID: %s' % video_id) + + def report_webpage(self, url): + """Report downloading page""" + self._downloader.to_screen(u'[youporn] Downloaded page: %s' % url) + + def report_title(self, video_title): + """Report dfinding title""" + self._downloader.to_screen(u'[youporn] Title: %s' % video_title) + + def report_uploader(self, uploader): + """Report dfinding title""" + self._downloader.to_screen(u'[youporn] Uploader: %s' % uploader) + + def report_upload_date(self, video_date): + """Report finding date""" + self._downloader.to_screen(u'[youporn] Date: %s' % video_date) + + def _print_formats(self, formats): + """Print all available formats""" + print 'Available formats:' + print u'ext\t\tformat' + print u'---------------------------------' + for format in formats: + print u'%s\t\t%s' % (format['ext'], format['format']) + + def _specific(self, req_format, formats): + for x in formats: + if(x["format"]==req_format): + return x + return None + + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + video_id = mobj.group('videoid').decode('utf-8') + self.report_id(video_id) + + # Get webpage content + try: + webpage = urllib2.urlopen(url).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err) + return + self.report_webpage(url) + + # Get the video title + result = re.search(self.VIDEO_TITLE_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = result.group('title').decode('utf-8').strip() + self.report_title(video_title) + + # Get the video date + result = re.search(self.VIDEO_DATE_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video date') + return + upload_date = result.group('date').decode('utf-8').strip() + self.report_upload_date(upload_date) + + # Get the video uploader + result = re.search(self.VIDEO_UPLOADER_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract uploader') + return + video_uploader = result.group('uploader').decode('utf-8').strip() + video_uploader = clean_html( video_uploader ) + self.report_uploader(video_uploader) + + # Get all of the formats available + result = re.search(self.DOWNLOAD_LIST_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract download list') + return + download_list_html = result.group('download_list').decode('utf-8').strip() + + # Get all of the links from the page + links = re.findall(self.LINK_RE, download_list_html) + if(len(links) == 0): + self._downloader.trouble(u'ERROR: no known formats available for video') + return + + self._downloader.to_screen(u'[youporn] Links found: %d' % len(links)) + + formats = [] + for link in links: + + # A link looks like this: + # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0 + # A path looks like this: + # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4 + video_url = unescapeHTML( link.decode('utf-8') ) + path = urlparse( video_url ).path + extension = os.path.splitext( path )[1][1:] + format = path.split('/')[4].split('_')[:2] + size = format[0] + bitrate = format[1] + format = "-".join( format ) + title = u'%s-%s-%s' % (video_title, size, bitrate) + + formats.append({ + 'id': video_id, + 'url': video_url, + 'uploader': video_uploader, + 'upload_date': upload_date, + 'title': title, + 'ext': extension, + 'format': format, + 'thumbnail': None, + 'description': None, + 'player_url': None + }) + + if self._downloader.params.get('listformats', None): + self._print_formats(formats) + return + + req_format = self._downloader.params.get('format', None) + #format_limit = self._downloader.params.get('format_limit', None) + self._downloader.to_screen(u'[youporn] Format: %s' % req_format) + + + if req_format is None or req_format == 'best': + return [formats[0]] + elif req_format == 'worst': + return [formats[-1]] + elif req_format in ('-1', 'all'): + return formats + else: + format = self._specific( req_format, formats ) + if result is None: + self._downloader.trouble(u'ERROR: requested format not available') + return + return [format] + + + +class PornotubeIE(InfoExtractor): + """Information extractor for pornotube.com.""" + + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$' + IE_NAME = u'pornotube' + VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",' + VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' + + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_extract_entry(self, url): + """Report downloading extry""" + self._downloader.to_screen(u'[pornotube] Downloading entry: %s' % url.decode('utf-8')) + + def report_date(self, upload_date): + """Report finding uploaded date""" + self._downloader.to_screen(u'[pornotube] Entry date: %s' % upload_date) + + def report_webpage(self, url): + """Report downloading page""" + self._downloader.to_screen(u'[pornotube] Downloaded page: %s' % url) + + def report_title(self, video_title): + """Report downloading extry""" + self._downloader.to_screen(u'[pornotube] Title: %s' % video_title.decode('utf-8')) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + + video_id = mobj.group('videoid').decode('utf-8') + video_title = mobj.group('title').decode('utf-8') + self.report_title(video_title); + + # Get webpage content + try: + webpage = urllib2.urlopen(url).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err) + return + self.report_webpage(url) + + # Get the video URL + result = re.search(self.VIDEO_URL_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video url') + return + video_url = urllib.unquote(result.group('url').decode('utf-8')) + self.report_extract_entry(video_url) + + #Get the uploaded date + result = re.search(self.VIDEO_UPLOADED_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + upload_date = result.group('date').decode('utf-8') + self.report_date(upload_date); + + + info = {'id': video_id, + 'url': video_url, + 'uploader': None, + 'upload_date': upload_date, + 'title': video_title, + 'ext': 'flv', + 'format': 'flv', + 'thumbnail': None, + 'description': None, + 'player_url': None} + + return [info] + + + +class YouJizzIE(InfoExtractor): + """Information extractor for youjizz.com.""" + + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/([^.]+).html$' + IE_NAME = u'youjizz' + VIDEO_TITLE_RE = r'<title>(?P<title>.*)' + EMBED_PAGE_RE = r'http://www.youjizz.com/videos/embed/(?P[0-9]+)' + SOURCE_RE = r'so.addVariable\("file",encodeURIComponent\("(?P[^"]+)"\)\);' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_extract_entry(self, url): + """Report downloading extry""" + self._downloader.to_screen(u'[youjizz] Downloading entry: %s' % url.decode('utf-8')) + + def report_webpage(self, url): + """Report downloading page""" + self._downloader.to_screen(u'[youjizz] Downloaded page: %s' % url) + + def report_title(self, video_title): + """Report downloading extry""" + self._downloader.to_screen(u'[youjizz] Title: %s' % video_title.decode('utf-8')) + + def report_embed_page(self, embed_page): + """Report downloading extry""" + self._downloader.to_screen(u'[youjizz] Embed Page: %s' % embed_page.decode('utf-8')) + + def _real_extract(self, url): + # Get webpage content + try: + webpage = urllib2.urlopen(url).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err) + return + self.report_webpage(url) + + # Get the video title + result = re.search(self.VIDEO_TITLE_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = result.group('title').decode('utf-8').strip() + self.report_title(video_title) + + # Get the embed page + result = re.search(self.EMBED_PAGE_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract embed page') + return + + embed_page_url = result.group(0).decode('utf-8').strip() + video_id = result.group('videoid').decode('utf-8') + self.report_embed_page(embed_page_url) + + try: + webpage = urllib2.urlopen(embed_page_url).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video embed page: %s' % err) + return + + # Get the video URL + result = re.search(self.SOURCE_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video url') + return + video_url = result.group('source').decode('utf-8') + self.report_extract_entry(video_url) + + info = {'id': video_id, + 'url': video_url, + 'uploader': None, + 'upload_date': None, + 'title': video_title, + 'ext': 'flv', + 'format': 'flv', + 'thumbnail': None, + 'description': None, + 'player_url': embed_page_url} + + return [info] + + def gen_extractors(): """ Return a list of an instance of every supported extractor. The order does matter; the first extractor matched is the one handling the URL. @@ -3768,6 +4093,9 @@ def gen_extractors(): MTVIE(), YoukuIE(), XNXXIE(), + YouJizzIE(), + PornotubeIE(), + YouPornIE(), GooglePlusIE(), ArteTvIE(), NBAIE(), -- cgit v1.2.3 From caec7618a113750eba26d080d4ce0afb2279a448 Mon Sep 17 00:00:00 2001 From: Jeff Crouse Date: Sat, 5 Jan 2013 16:05:23 -0500 Subject: re-fixed XNXX regex problem --- youtube_dl/InfoExtractors.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'youtube_dl') diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 72ad25ad3..905e212b0 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -3294,7 +3294,7 @@ class YoukuIE(InfoExtractor): class XNXXIE(InfoExtractor): """Information extractor for xnxx.com""" - _VALID_URL = r'^http://video\.xnxx\.com/video([0-9]+)/(.*)' + _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)' IE_NAME = u'xnxx' VIDEO_URL_RE = r'flv_url=(.*?)&' VIDEO_TITLE_RE = r'(.*?)\s+-\s+XNXX.COM' -- cgit v1.2.3 From ca6710ee4147a27b64b28b27e681d2b900b437bc Mon Sep 17 00:00:00 2001 From: Jeff Crouse <jefftimesten@gmail.com> Date: Sun, 6 Jan 2013 15:40:50 -0500 Subject: made changes recommended in pull request --- youtube_dl/InfoExtractors.py | 240 ++++++++++++++++++++----------------------- 1 file changed, 110 insertions(+), 130 deletions(-) (limited to 'youtube_dl') diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 905e212b0..7143a229e 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -14,10 +14,6 @@ import email.utils import xml.etree.ElementTree import random import math -import urllib -import urllib2 -import httplib -from urlparse import parse_qs, urlparse from .utils import * @@ -3744,43 +3740,37 @@ class YouPornIE(InfoExtractor): """Information extractor for youporn.com.""" _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)' - IE_NAME = u'youporn' - VIDEO_TITLE_RE = r'videoTitleArea">(?P<title>.*)</h1>' - VIDEO_DATE_RE = r'Date:</b>(?P<date>.*)</li>' - VIDEO_UPLOADER_RE = r'Submitted:</b>(?P<uploader>.*)</li>' - DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>' - LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">' - + def __init__(self, downloader=None): InfoExtractor.__init__(self, downloader) - def report_id(self, video_id): - """Report finding video ID""" - self._downloader.to_screen(u'[youporn] Video ID: %s' % video_id) + # def report_id(self, video_id): + # """Report finding video ID""" + # self._downloader.to_screen(u'[youporn] Video ID: %s' % video_id) - def report_webpage(self, url): - """Report downloading page""" - self._downloader.to_screen(u'[youporn] Downloaded page: %s' % url) + # def report_webpage(self, url): + # """Report downloading page""" + # self._downloader.to_screen(u'[youporn] Downloaded page: %s' % url) - def report_title(self, video_title): - """Report dfinding title""" - self._downloader.to_screen(u'[youporn] Title: %s' % video_title) + # def report_title(self, video_title): + # """Report dfinding title""" + # self._downloader.to_screen(u'[youporn] Title: %s' % video_title) - def report_uploader(self, uploader): - """Report dfinding title""" - self._downloader.to_screen(u'[youporn] Uploader: %s' % uploader) + # def report_uploader(self, uploader): + # """Report dfinding title""" + # self._downloader.to_screen(u'[youporn] Uploader: %s' % uploader) - def report_upload_date(self, video_date): - """Report finding date""" - self._downloader.to_screen(u'[youporn] Date: %s' % video_date) + # def report_upload_date(self, video_date): + # """Report finding date""" + # self._downloader.to_screen(u'[youporn] Date: %s' % video_date) def _print_formats(self, formats): """Print all available formats""" - print 'Available formats:' - print u'ext\t\tformat' - print u'---------------------------------' + print('Available formats:') + print(u'ext\t\tformat') + print(u'---------------------------------') for format in formats: - print u'%s\t\t%s' % (format['ext'], format['format']) + print(u'%s\t\t%s' % (format['ext'], format['format'])) def _specific(self, req_format, formats): for x in formats: @@ -3788,58 +3778,57 @@ class YouPornIE(InfoExtractor): return x return None - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) if mobj is None: self._downloader.trouble(u'ERROR: invalid URL: %s' % url) return - video_id = mobj.group('videoid').decode('utf-8') - self.report_id(video_id) + video_id = mobj.group('videoid') + #self.report_id(video_id) - # Get webpage content - try: - webpage = urllib2.urlopen(url).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err) - return - self.report_webpage(url) + webpage = self._download_webpage(url, video_id) + #self.report_webpage(url) # Get the video title - result = re.search(self.VIDEO_TITLE_RE, webpage) + VIDEO_TITLE_RE = r'videoTitleArea">(?P<title>.*)</h1>' + result = re.search(VIDEO_TITLE_RE, webpage) if result is None: self._downloader.trouble(u'ERROR: unable to extract video title') return - video_title = result.group('title').decode('utf-8').strip() - self.report_title(video_title) + video_title = result.group('title').strip() + #self.report_title(video_title) # Get the video date - result = re.search(self.VIDEO_DATE_RE, webpage) + VIDEO_DATE_RE = r'Date:</b>(?P<date>.*)</li>' + result = re.search(VIDEO_DATE_RE, webpage) if result is None: self._downloader.trouble(u'ERROR: unable to extract video date') return - upload_date = result.group('date').decode('utf-8').strip() - self.report_upload_date(upload_date) + upload_date = result.group('date').strip() + #self.report_upload_date(upload_date) # Get the video uploader - result = re.search(self.VIDEO_UPLOADER_RE, webpage) + VIDEO_UPLOADER_RE = r'Submitted:</b>(?P<uploader>.*)</li>' + result = re.search(VIDEO_UPLOADER_RE, webpage) if result is None: self._downloader.trouble(u'ERROR: unable to extract uploader') return - video_uploader = result.group('uploader').decode('utf-8').strip() + video_uploader = result.group('uploader').strip() video_uploader = clean_html( video_uploader ) - self.report_uploader(video_uploader) + #self.report_uploader(video_uploader) # Get all of the formats available - result = re.search(self.DOWNLOAD_LIST_RE, webpage) + DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>' + result = re.search(DOWNLOAD_LIST_RE, webpage) if result is None: self._downloader.trouble(u'ERROR: unable to extract download list') return - download_list_html = result.group('download_list').decode('utf-8').strip() + download_list_html = result.group('download_list').strip() # Get all of the links from the page - links = re.findall(self.LINK_RE, download_list_html) + LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">' + links = re.findall(LINK_RE, download_list_html) if(len(links) == 0): self._downloader.trouble(u'ERROR: no known formats available for video') return @@ -3853,8 +3842,8 @@ class YouPornIE(InfoExtractor): # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0 # A path looks like this: # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4 - video_url = unescapeHTML( link.decode('utf-8') ) - path = urlparse( video_url ).path + video_url = unescapeHTML( link ) + path = compat_urllib_parse_urlparse( video_url ).path extension = os.path.splitext( path )[1][1:] format = path.split('/')[4].split('_')[:2] size = format[0] @@ -3903,29 +3892,25 @@ class PornotubeIE(InfoExtractor): """Information extractor for pornotube.com.""" _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$' - IE_NAME = u'pornotube' - VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",' - VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' + # def __init__(self, downloader=None): + # InfoExtractor.__init__(self, downloader) - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_extract_entry(self, url): - """Report downloading extry""" - self._downloader.to_screen(u'[pornotube] Downloading entry: %s' % url.decode('utf-8')) + # def report_extract_entry(self, url): + # """Report downloading extry""" + # self._downloader.to_screen(u'[pornotube] Downloading entry: %s' % url.decode('utf-8')) - def report_date(self, upload_date): - """Report finding uploaded date""" - self._downloader.to_screen(u'[pornotube] Entry date: %s' % upload_date) + # def report_date(self, upload_date): + # """Report finding uploaded date""" + # self._downloader.to_screen(u'[pornotube] Entry date: %s' % upload_date) - def report_webpage(self, url): - """Report downloading page""" - self._downloader.to_screen(u'[pornotube] Downloaded page: %s' % url) + # def report_webpage(self, url): + # """Report downloading page""" + # self._downloader.to_screen(u'[pornotube] Downloaded page: %s' % url) - def report_title(self, video_title): - """Report downloading extry""" - self._downloader.to_screen(u'[pornotube] Title: %s' % video_title.decode('utf-8')) + # def report_title(self, video_title): + # """Report downloading extry""" + # self._downloader.to_screen(u'[pornotube] Title: %s' % video_title.decode('utf-8')) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -3933,34 +3918,31 @@ class PornotubeIE(InfoExtractor): self._downloader.trouble(u'ERROR: invalid URL: %s' % url) return - video_id = mobj.group('videoid').decode('utf-8') - video_title = mobj.group('title').decode('utf-8') - self.report_title(video_title); + video_id = mobj.group('videoid') + video_title = mobj.group('title') + #self.report_title(video_title); # Get webpage content - try: - webpage = urllib2.urlopen(url).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err) - return - self.report_webpage(url) + webpage = self._download_webpage(url, video_id) + #self.report_webpage(url) # Get the video URL - result = re.search(self.VIDEO_URL_RE, webpage) + VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",' + result = re.search(VIDEO_URL_RE, webpage) if result is None: self._downloader.trouble(u'ERROR: unable to extract video url') return - video_url = urllib.unquote(result.group('url').decode('utf-8')) - self.report_extract_entry(video_url) + video_url = compat_urllib_parse.unquote(result.group('url')) + #self.report_extract_entry(video_url) #Get the uploaded date - result = re.search(self.VIDEO_UPLOADED_RE, webpage) + VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' + result = re.search(VIDEO_UPLOADED_RE, webpage) if result is None: self._downloader.trouble(u'ERROR: unable to extract video title') return - upload_date = result.group('date').decode('utf-8') - self.report_date(upload_date); - + upload_date = result.group('date') + #self.report_date(upload_date); info = {'id': video_id, 'url': video_url, @@ -3980,71 +3962,69 @@ class PornotubeIE(InfoExtractor): class YouJizzIE(InfoExtractor): """Information extractor for youjizz.com.""" - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/([^.]+).html$' - IE_NAME = u'youjizz' - VIDEO_TITLE_RE = r'<title>(?P<title>.*)' - EMBED_PAGE_RE = r'http://www.youjizz.com/videos/embed/(?P[0-9]+)' - SOURCE_RE = r'so.addVariable\("file",encodeURIComponent\("(?P[^"]+)"\)\);' + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P[^.]+).html$' def __init__(self, downloader=None): InfoExtractor.__init__(self, downloader) - def report_extract_entry(self, url): - """Report downloading extry""" - self._downloader.to_screen(u'[youjizz] Downloading entry: %s' % url.decode('utf-8')) + # def report_extract_entry(self, url): + # """Report downloading extry""" + # self._downloader.to_screen(u'[youjizz] Downloading entry: %s' % url.decode('utf-8')) - def report_webpage(self, url): - """Report downloading page""" - self._downloader.to_screen(u'[youjizz] Downloaded page: %s' % url) + # def report_webpage(self, url): + # """Report downloading page""" + # self._downloader.to_screen(u'[youjizz] Downloaded page: %s' % url) - def report_title(self, video_title): - """Report downloading extry""" - self._downloader.to_screen(u'[youjizz] Title: %s' % video_title.decode('utf-8')) + # def report_title(self, video_title): + # """Report downloading extry""" + # self._downloader.to_screen(u'[youjizz] Title: %s' % video_title.decode('utf-8')) - def report_embed_page(self, embed_page): - """Report downloading extry""" - self._downloader.to_screen(u'[youjizz] Embed Page: %s' % embed_page.decode('utf-8')) + # def report_embed_page(self, embed_page): + # """Report downloading extry""" + # self._downloader.to_screen(u'[youjizz] Embed Page: %s' % embed_page.decode('utf-8')) def _real_extract(self, url): - # Get webpage content - try: - webpage = urllib2.urlopen(url).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err) + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) return - self.report_webpage(url) + + video_id = mobj.group('videoid') + + # Get webpage content + webpage = self._download_webpage(url, video_id) + #self.report_webpage(url) # Get the video title - result = re.search(self.VIDEO_TITLE_RE, webpage) + VIDEO_TITLE_RE = r'(?P<title>.*)' + result = re.search(VIDEO_TITLE_RE, webpage) if result is None: self._downloader.trouble(u'ERROR: unable to extract video title') return - video_title = result.group('title').decode('utf-8').strip() - self.report_title(video_title) + video_title = result.group('title').strip() + #self.report_title(video_title) # Get the embed page - result = re.search(self.EMBED_PAGE_RE, webpage) + EMBED_PAGE_RE = r'http://www.youjizz.com/videos/embed/(?P[0-9]+)' + result = re.search(EMBED_PAGE_RE, webpage) if result is None: self._downloader.trouble(u'ERROR: unable to extract embed page') return - embed_page_url = result.group(0).decode('utf-8').strip() - video_id = result.group('videoid').decode('utf-8') - self.report_embed_page(embed_page_url) + embed_page_url = result.group(0).strip() + video_id = result.group('videoid') + #self.report_embed_page(embed_page_url) - try: - webpage = urllib2.urlopen(embed_page_url).read() - except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self._downloader.trouble(u'ERROR: unable to download video embed page: %s' % err) - return - + webpage = self._download_webpage(embed_page_url, video_id) + # Get the video URL - result = re.search(self.SOURCE_RE, webpage) + SOURCE_RE = r'so.addVariable\("file",encodeURIComponent\("(?P[^"]+)"\)\);' + result = re.search(SOURCE_RE, webpage) if result is None: self._downloader.trouble(u'ERROR: unable to extract video url') return - video_url = result.group('source').decode('utf-8') - self.report_extract_entry(video_url) + video_url = result.group('source') + #self.report_extract_entry(video_url) info = {'id': video_id, 'url': video_url, @@ -4093,9 +4073,9 @@ def gen_extractors(): MTVIE(), YoukuIE(), XNXXIE(), - YouJizzIE(), - PornotubeIE(), - YouPornIE(), + YouJizzIE(), # jefftimesten + PornotubeIE(), # jefftimesten + YouPornIE(), # jefftimesten GooglePlusIE(), ArteTvIE(), NBAIE(), -- cgit v1.2.3 From 18be482a6f0b0d48c4fd8101ba0f0e30ac782d79 Mon Sep 17 00:00:00 2001 From: Jeff Crouse Date: Sun, 6 Jan 2013 15:52:33 -0500 Subject: oops - didn't remove some reminders --- youtube_dl/InfoExtractors.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'youtube_dl') diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 7143a229e..83be8313f 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -4073,9 +4073,9 @@ def gen_extractors(): MTVIE(), YoukuIE(), XNXXIE(), - YouJizzIE(), # jefftimesten - PornotubeIE(), # jefftimesten - YouPornIE(), # jefftimesten + YouJizzIE(), + PornotubeIE(), + YouPornIE(), GooglePlusIE(), ArteTvIE(), NBAIE(), -- cgit v1.2.3