From: Jeff Crouse Date: Sat, 5 Jan 2013 20:42:35 +0000 (-0500) Subject: Added extractors for 3 porn sites X-Git-Url: http://git.bitcoin.ninja/index.cgi?p=youtube-dl;a=commitdiff_plain;h=991ba7fae38498b1066c7f6821d1d8681ef87f1b Added extractors for 3 porn sites --- diff --git a/LATEST_VERSION b/LATEST_VERSION old mode 100644 new mode 100755 index d070c6ea3..275de03d9 --- a/LATEST_VERSION +++ b/LATEST_VERSION @@ -1 +1 @@ -2012.10.09 +9999.99.99 \ No newline at end of file diff --git a/README.md b/README.md old mode 100644 new mode 100755 index 4b0de1b88..b3cd9a38c --- a/README.md +++ b/README.md @@ -30,7 +30,7 @@ which means you can modify it, redistribute it or use it however you like. --list-extractors List all supported extractors and the URLs they would handle - Video Selection: +## Video Selection: --playlist-start NUMBER playlist video to start at (default is 1) --playlist-end NUMBER playlist video to end at (default is last) --match-title REGEX download only matching titles (regex or caseless @@ -39,7 +39,7 @@ which means you can modify it, redistribute it or use it however you like. caseless sub-string) --max-downloads NUMBER Abort after downloading NUMBER files - Filesystem Options: +## Filesystem Options: -t, --title use title in file name --id use video ID in file name -l, --literal [deprecated] alias of --title @@ -70,7 +70,7 @@ which means you can modify it, redistribute it or use it however you like. --write-description write video description to a .description file --write-info-json write video metadata to a .info.json file - Verbosity / Simulation Options: +## Verbosity / Simulation Options: -q, --quiet activates quiet mode -s, --simulate do not download the video and do not write anything to disk @@ -85,7 +85,7 @@ which means you can modify it, redistribute it or use it however you like. --console-title display progress in console titlebar -v, --verbose print various debugging information - Video Format Options: +## Video Format Options: -f, --format FORMAT video format code --all-formats download all available video formats --prefer-free-formats prefer free video formats unless a specific one is @@ -97,12 +97,12 @@ which means you can modify it, redistribute it or use it however you like. --srt-lang LANG language of the closed captions to download (optional) use IETF language tags like 'en' - Authentication Options: +## Authentication Options: -u, --username USERNAME account username -p, --password PASSWORD account password -n, --netrc use .netrc authentication data - Post-processing Options: +## Post-processing Options: -x, --extract-audio convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe) --audio-format FORMAT "best", "aac", "vorbis", "mp3", "m4a", or "wav"; @@ -172,7 +172,7 @@ youtube requires an additional signature since September 2012 which is not suppo The error File "youtube-dl", line 2 - SyntaxError: Non-ASCII character '“' ... + SyntaxError: Non-ASCII character '\x93' ... means you're using an outdated version of Python. Please update to Python 2.6 or 2.7. diff --git a/youtube-dl b/youtube-dl index 6ba864a14..e6f05c173 100755 Binary files a/youtube-dl and b/youtube-dl differ 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(),