Merge branch 'master' into vimeo

This commit is contained in:
Rogério Brito 2011-02-04 03:51:16 -02:00
commit 58b53721af
2 changed files with 69 additions and 30 deletions

View File

@ -1 +1 @@
2010.12.09 2011.01.30

View File

@ -5,6 +5,7 @@
# Author: Benjamin Johnson # Author: Benjamin Johnson
# Author: Vasyl' Vavrychuk # Author: Vasyl' Vavrychuk
# Author: Witold Baryluk # Author: Witold Baryluk
# Author: Paweł Paprota
# License: Public domain code # License: Public domain code
import cookielib import cookielib
import ctypes import ctypes
@ -36,7 +37,7 @@ except ImportError:
from cgi import parse_qs from cgi import parse_qs
std_headers = { std_headers = {
'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.12) Gecko/20101028 Firefox/3.6.12', 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:2.0b10) Gecko/20100101 Firefox/4.0b10',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate', 'Accept-Encoding': 'gzip, deflate',
@ -2207,8 +2208,8 @@ class YahooSearchIE(InfoExtractor):
class YoutubePlaylistIE(InfoExtractor): class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists.""" """Information Extractor for YouTube playlists."""
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/|p/)([^&]+).*' _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists|artist)\?.*?(p|a)=|user/.*?/user/|p/)([^&]+).*'
_TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en' _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&' _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>' _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
_youtube_ie = None _youtube_ie = None
@ -2236,13 +2237,19 @@ class YoutubePlaylistIE(InfoExtractor):
return return
# Download playlist pages # Download playlist pages
playlist_id = mobj.group(1) # prefix is 'p' as default for playlists but there are other types that need extra care
playlist_prefix = mobj.group(1)
if playlist_prefix == 'a':
playlist_access = 'artist'
else:
playlist_access = 'view_play_list'
playlist_id = mobj.group(2)
video_ids = [] video_ids = []
pagenum = 1 pagenum = 1
while True: while True:
self.report_download_page(playlist_id, pagenum) self.report_download_page(playlist_id, pagenum)
request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum)) request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum))
try: try:
page = urllib2.urlopen(request).read() page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@ -2271,9 +2278,11 @@ class YoutubePlaylistIE(InfoExtractor):
class YoutubeUserIE(InfoExtractor): class YoutubeUserIE(InfoExtractor):
"""Information Extractor for YouTube users.""" """Information Extractor for YouTube users."""
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/user/(.*)' _VALID_URL = r'(?:(?:(?:http://)?(?:\w+\.)?youtube.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
_TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s' _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
_VIDEO_INDICATOR = r'http://gdata.youtube.com/feeds/api/videos/(.*)' # XXX Fix this. _GDATA_PAGE_SIZE = 50
_GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
_youtube_ie = None _youtube_ie = None
def __init__(self, youtube_ie, downloader=None): def __init__(self, youtube_ie, downloader=None):
@ -2284,9 +2293,10 @@ class YoutubeUserIE(InfoExtractor):
def suitable(url): def suitable(url):
return (re.match(YoutubeUserIE._VALID_URL, url) is not None) return (re.match(YoutubeUserIE._VALID_URL, url) is not None)
def report_download_page(self, username): def report_download_page(self, username, start_index):
"""Report attempt to download user page.""" """Report attempt to download user page."""
self._downloader.to_screen(u'[youtube] user %s: Downloading page ' % (username)) self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
(username, start_index, start_index + self._GDATA_PAGE_SIZE))
def _real_initialize(self): def _real_initialize(self):
self._youtube_ie.initialize() self._youtube_ie.initialize()
@ -2298,34 +2308,63 @@ class YoutubeUserIE(InfoExtractor):
self._downloader.trouble(u'ERROR: invalid url: %s' % url) self._downloader.trouble(u'ERROR: invalid url: %s' % url)
return return
# Download user page
username = mobj.group(1) username = mobj.group(1)
# Download video ids using YouTube Data API. Result size per
# query is limited (currently to 50 videos) so we need to query
# page by page until there are no video ids - it means we got
# all of them.
video_ids = [] video_ids = []
pagenum = 1 pagenum = 0
self.report_download_page(username) while True:
request = urllib2.Request(self._TEMPLATE_URL % (username)) start_index = pagenum * self._GDATA_PAGE_SIZE + 1
try: self.report_download_page(username, start_index)
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
return
# Extract video identifiers request = urllib2.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index))
ids_in_page = []
for mobj in re.finditer(self._VIDEO_INDICATOR, page): try:
if mobj.group(1) not in ids_in_page: page = urllib2.urlopen(request).read()
ids_in_page.append(mobj.group(1)) except (urllib2.URLError, httplib.HTTPException, socket.error), err:
video_ids.extend(ids_in_page) self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
return
# Extract video identifiers
ids_in_page = []
for mobj in re.finditer(self._VIDEO_INDICATOR, page):
if mobj.group(1) not in ids_in_page:
ids_in_page.append(mobj.group(1))
video_ids.extend(ids_in_page)
# A little optimization - if current page is not
# "full", ie. does not contain PAGE_SIZE video ids then
# we can assume that this page is the last one - there
# are no more ids on further pages - no need to query
# again.
if len(ids_in_page) < self._GDATA_PAGE_SIZE:
break
pagenum += 1
all_ids_count = len(video_ids)
playliststart = self._downloader.params.get('playliststart', 1) - 1 playliststart = self._downloader.params.get('playliststart', 1) - 1
playlistend = self._downloader.params.get('playlistend', -1) playlistend = self._downloader.params.get('playlistend', -1)
video_ids = video_ids[playliststart:playlistend]
for id in video_ids: if playlistend == -1:
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) video_ids = video_ids[playliststart:]
return else:
video_ids = video_ids[playliststart:playlistend]
self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" %
(username, all_ids_count, len(video_ids)))
for video_id in video_ids:
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id)
class DepositFilesIE(InfoExtractor): class DepositFilesIE(InfoExtractor):
"""Information extractor for depositfiles.com""" """Information extractor for depositfiles.com"""
@ -2484,7 +2523,7 @@ if __name__ == '__main__':
# Parse command line # Parse command line
parser = optparse.OptionParser( parser = optparse.OptionParser(
usage='Usage: %prog [options] url...', usage='Usage: %prog [options] url...',
version='2010.12.09', version='2011.01.30',
conflict_handler='resolve', conflict_handler='resolve',
) )