diff options
Diffstat (limited to 'youtube_dl/InfoExtractors.py')
| -rwxr-xr-x | youtube_dl/InfoExtractors.py | 240 |
1 files changed, 110 insertions, 130 deletions
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>.*)</title>' - EMBED_PAGE_RE = r'http://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)' - SOURCE_RE = r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);' + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).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'<title>(?P<title>.*)</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<videoid>[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\("(?P<source>[^"]+)"\)\);' + 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(), |