archive
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

made changes recommended in pull request

Browse Source
pull/8/head
Jeff Crouse 12 years ago
parent caec7618a1
commit ca6710ee41
2 changed files with 128 additions and 130 deletions
Show Stats Download Patch File Download Diff File

18
test/tests.json
Unescape Escape View File

@ -35,6 +35,24 @@
"url": "http://www.xvideos.com/video939581/funny_porns_by_s_-1", "url": "http://www.xvideos.com/video939581/funny_porns_by_s_-1",
"file": "939581.flv" "file": "939581.flv"
}, },
{
"name": "YouPorn",
"md5": "fdb230af7a8a52f110b11cdf994877e4",
"url": "http://www.youporn.com/watch/633213/me-and-my-french-girl/",
"file": "633213.mp4"
},
{
"name": "Pornotube",
"md5": "eb55ce998e9464993933df8d9d196f70",
"url": "http://pornotube.com/m/1812947/Intimate-Moments%3A-Masturbation-Sessions",
"file": "1812947.flv"
},
{
"name": "YouJizz",
"md5": "e07263d29b39c3cd2b997b3d3c73ca2d",
"url": "http://www.youjizz.com/videos/daddys-girl--3549881.html",
"file": "3549881.flv"
},
{ {
"name": "Vimeo", "name": "Vimeo",
"md5": "8879b6cc097e987f02484baf890129e5", "md5": "8879b6cc097e987f02484baf890129e5",

236
youtube_dl/InfoExtractors.py
Unescape Escape View File

@ -14,10 +14,6 @@ import email.utils
import xml.etree.ElementTree import xml.etree.ElementTree
import random import random
import math import math
import urllib
import urllib2
import httplib
from urlparse import parse_qs, urlparse
from .utils import * from .utils import *
@ -3744,43 +3740,37 @@ class YouPornIE(InfoExtractor):
"""Information extractor for youporn.com.""" """Information extractor for youporn.com."""
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)' _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): def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
def report_id(self, video_id): # def report_id(self, video_id):
"""Report finding video ID""" # """Report finding video ID"""
self._downloader.to_screen(u'[youporn] Video ID: %s' % video_id) # self._downloader.to_screen(u'[youporn] Video ID: %s' % video_id)
def report_webpage(self, url): # def report_webpage(self, url):
"""Report downloading page""" # """Report downloading page"""
self._downloader.to_screen(u'[youporn] Downloaded page: %s' % url) # self._downloader.to_screen(u'[youporn] Downloaded page: %s' % url)
def report_title(self, video_title): # def report_title(self, video_title):
"""Report dfinding title""" # """Report dfinding title"""
self._downloader.to_screen(u'[youporn] Title: %s' % video_title) # self._downloader.to_screen(u'[youporn] Title: %s' % video_title)
def report_uploader(self, uploader): # def report_uploader(self, uploader):
"""Report dfinding title""" # """Report dfinding title"""
self._downloader.to_screen(u'[youporn] Uploader: %s' % uploader) # self._downloader.to_screen(u'[youporn] Uploader: %s' % uploader)
def report_upload_date(self, video_date): # def report_upload_date(self, video_date):
"""Report finding date""" # """Report finding date"""
self._downloader.to_screen(u'[youporn] Date: %s' % video_date) # self._downloader.to_screen(u'[youporn] Date: %s' % video_date)
def _print_formats(self, formats): def _print_formats(self, formats):
"""Print all available formats""" """Print all available formats"""
print 'Available formats:' print('Available formats:')
print u'ext\t\tformat' print(u'ext\t\tformat')
print u'---------------------------------' print(u'---------------------------------')
for format in formats: 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): def _specific(self, req_format, formats):
for x in formats: for x in formats:
@ -3788,58 +3778,57 @@ class YouPornIE(InfoExtractor):
return x return x
return None return None
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url) self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return return
video_id = mobj.group('videoid').decode('utf-8') video_id = mobj.group('videoid')
self.report_id(video_id) #self.report_id(video_id)
# Get webpage content webpage = self._download_webpage(url, video_id)
try: #self.report_webpage(url)
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 # 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: if result is None:
self._downloader.trouble(u'ERROR: unable to extract video title') self._downloader.trouble(u'ERROR: unable to extract video title')
return return
video_title = result.group('title').decode('utf-8').strip() video_title = result.group('title').strip()
self.report_title(video_title) #self.report_title(video_title)
# Get the video date # 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: if result is None:
self._downloader.trouble(u'ERROR: unable to extract video date') self._downloader.trouble(u'ERROR: unable to extract video date')
return return
upload_date = result.group('date').decode('utf-8').strip() upload_date = result.group('date').strip()
self.report_upload_date(upload_date) #self.report_upload_date(upload_date)
# Get the video uploader # 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: if result is None:
self._downloader.trouble(u'ERROR: unable to extract uploader') self._downloader.trouble(u'ERROR: unable to extract uploader')
return return
video_uploader = result.group('uploader').decode('utf-8').strip() video_uploader = result.group('uploader').strip()
video_uploader = clean_html( video_uploader ) video_uploader = clean_html( video_uploader )
self.report_uploader(video_uploader) #self.report_uploader(video_uploader)
# Get all of the formats available # 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: if result is None:
self._downloader.trouble(u'ERROR: unable to extract download list') self._downloader.trouble(u'ERROR: unable to extract download list')
return 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 # 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): if(len(links) == 0):
self._downloader.trouble(u'ERROR: no known formats available for video') self._downloader.trouble(u'ERROR: no known formats available for video')
return 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 # 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: # A path looks like this:
# /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4 # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
video_url = unescapeHTML( link.decode('utf-8') ) video_url = unescapeHTML( link )
path = urlparse( video_url ).path path = compat_urllib_parse_urlparse( video_url ).path
extension = os.path.splitext( path )[1][1:] extension = os.path.splitext( path )[1][1:]
format = path.split('/')[4].split('_')[:2] format = path.split('/')[4].split('_')[:2]
size = format[0] size = format[0]
@ -3903,29 +3892,25 @@ class PornotubeIE(InfoExtractor):
"""Information extractor for pornotube.com.""" """Information extractor for pornotube.com."""
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$' _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
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): # def report_extract_entry(self, url):
InfoExtractor.__init__(self, downloader) # """Report downloading extry"""
# self._downloader.to_screen(u'[pornotube] Downloading entry: %s' % url.decode('utf-8'))
def report_extract_entry(self, url): # def report_date(self, upload_date):
"""Report downloading extry""" # """Report finding uploaded date"""
self._downloader.to_screen(u'[pornotube] Downloading entry: %s' % url.decode('utf-8')) # 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): # def report_webpage(self, url):
"""Report downloading page""" # """Report downloading page"""
self._downloader.to_screen(u'[pornotube] Downloaded page: %s' % url) # self._downloader.to_screen(u'[pornotube] Downloaded page: %s' % url)
def report_title(self, video_title): # def report_title(self, video_title):
"""Report downloading extry""" # """Report downloading extry"""
self._downloader.to_screen(u'[pornotube] Title: %s' % video_title.decode('utf-8')) # self._downloader.to_screen(u'[pornotube] Title: %s' % video_title.decode('utf-8'))
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -3933,34 +3918,31 @@ class PornotubeIE(InfoExtractor):
self._downloader.trouble(u'ERROR: invalid URL: %s' % url) self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return return
video_id = mobj.group('videoid').decode('utf-8') video_id = mobj.group('videoid')
video_title = mobj.group('title').decode('utf-8') video_title = mobj.group('title')
self.report_title(video_title); #self.report_title(video_title);
# Get webpage content # Get webpage content
try: webpage = self._download_webpage(url, video_id)
webpage = urllib2.urlopen(url).read() #self.report_webpage(url)
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 # 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: if result is None:
self._downloader.trouble(u'ERROR: unable to extract video url') self._downloader.trouble(u'ERROR: unable to extract video url')
return return
video_url = urllib.unquote(result.group('url').decode('utf-8')) video_url = compat_urllib_parse.unquote(result.group('url'))
self.report_extract_entry(video_url) #self.report_extract_entry(video_url)
#Get the uploaded date #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: if result is None:
self._downloader.trouble(u'ERROR: unable to extract video title') self._downloader.trouble(u'ERROR: unable to extract video title')
return return
upload_date = result.group('date').decode('utf-8') upload_date = result.group('date')
self.report_date(upload_date); #self.report_date(upload_date);
info = {'id': video_id, info = {'id': video_id,
'url': video_url, 'url': video_url,
@ -3980,71 +3962,69 @@ class PornotubeIE(InfoExtractor):
class YouJizzIE(InfoExtractor): class YouJizzIE(InfoExtractor):
"""Information extractor for youjizz.com.""" """Information extractor for youjizz.com."""
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/([^.]+).html$' _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
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\("(?P<source>[^"]+)"\)\);'
def __init__(self, downloader=None): def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
def report_extract_entry(self, url): # def report_extract_entry(self, url):
"""Report downloading extry""" # """Report downloading extry"""
self._downloader.to_screen(u'[youjizz] Downloading entry: %s' % url.decode('utf-8')) # self._downloader.to_screen(u'[youjizz] Downloading entry: %s' % url.decode('utf-8'))
def report_webpage(self, url): # def report_webpage(self, url):
"""Report downloading page""" # """Report downloading page"""
self._downloader.to_screen(u'[youjizz] Downloaded page: %s' % url) # self._downloader.to_screen(u'[youjizz] Downloaded page: %s' % url)
def report_title(self, video_title): # def report_title(self, video_title):
"""Report downloading extry""" # """Report downloading extry"""
self._downloader.to_screen(u'[youjizz] Title: %s' % video_title.decode('utf-8')) # self._downloader.to_screen(u'[youjizz] Title: %s' % video_title.decode('utf-8'))
def report_embed_page(self, embed_page): # def report_embed_page(self, embed_page):
"""Report downloading extry""" # """Report downloading extry"""
self._downloader.to_screen(u'[youjizz] Embed Page: %s' % embed_page.decode('utf-8')) # self._downloader.to_screen(u'[youjizz] Embed Page: %s' % embed_page.decode('utf-8'))
def _real_extract(self, url): def _real_extract(self, url):
# Get webpage content mobj = re.match(self._VALID_URL, url)
try: if mobj is None:
webpage = urllib2.urlopen(url).read() self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err)
return 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 # 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: if result is None:
self._downloader.trouble(u'ERROR: unable to extract video title') self._downloader.trouble(u'ERROR: unable to extract video title')
return return
video_title = result.group('title').decode('utf-8').strip() video_title = result.group('title').strip()
self.report_title(video_title) #self.report_title(video_title)
# Get the embed page # 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: if result is None:
self._downloader.trouble(u'ERROR: unable to extract embed page') self._downloader.trouble(u'ERROR: unable to extract embed page')
return return
embed_page_url = result.group(0).decode('utf-8').strip() embed_page_url = result.group(0).strip()
video_id = result.group('videoid').decode('utf-8') video_id = result.group('videoid')
self.report_embed_page(embed_page_url) #self.report_embed_page(embed_page_url)
try: webpage = self._download_webpage(embed_page_url, video_id)
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 # 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: if result is None:
self._downloader.trouble(u'ERROR: unable to extract video url') self._downloader.trouble(u'ERROR: unable to extract video url')
return return
video_url = result.group('source').decode('utf-8') video_url = result.group('source')
self.report_extract_entry(video_url) #self.report_extract_entry(video_url)
info = {'id': video_id, info = {'id': video_id,
'url': video_url, 'url': video_url,
@ -4093,9 +4073,9 @@ def gen_extractors():
MTVIE(), MTVIE(),
YoukuIE(), YoukuIE(),
XNXXIE(), XNXXIE(),
YouJizzIE(), YouJizzIE(), # jefftimesten
PornotubeIE(), PornotubeIE(), # jefftimesten
YouPornIE(), YouPornIE(), # jefftimesten
GooglePlusIE(), GooglePlusIE(),
ArteTvIE(), ArteTvIE(),
NBAIE(), NBAIE(),

Write Preview
Loading…
Cancel
Save