X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/fa9caede2ef0b8d916bf9c4c7be902d624afc1f0..975f9519f0ae48e780767bf543204c6626a493b0:/youtube_dl/InfoExtractors.py?ds=inline
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
old mode 100644
new mode 100755
index ddb4aa1..672ef9e
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -1,2957 +1,4 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
+# Legacy file for backwards compatibility, use youtube_dl.extractor instead!
-import datetime
-import HTMLParser
-import httplib
-import netrc
-import os
-import re
-import socket
-import time
-import urllib
-import urllib2
-import email.utils
-import xml.etree.ElementTree
-from urlparse import parse_qs
-
-try:
- import cStringIO as StringIO
-except ImportError:
- import StringIO
-
-from utils import *
-
-
-class InfoExtractor(object):
- """Information Extractor class.
-
- Information extractors are the classes that, given a URL, extract
- information from the video (or videos) the URL refers to. This
- information includes the real video URL, the video title and simplified
- title, author and others. The information is stored in a dictionary
- which is then passed to the FileDownloader. The FileDownloader
- processes this information possibly downloading the video to the file
- system, among other possible outcomes. The dictionaries must include
- the following fields:
-
- id: Video identifier.
- url: Final video URL.
- uploader: Nickname of the video uploader.
- title: Literal title.
- ext: Video filename extension.
- format: Video format.
- player_url: SWF Player URL (may be None).
-
- The following fields are optional. Their primary purpose is to allow
- youtube-dl to serve as the backend for a video search function, such
- as the one in youtube2mp3. They are only used when their respective
- forced printing functions are called:
-
- thumbnail: Full URL to a video thumbnail image.
- description: One-line video description.
-
- Subclasses of this one should re-define the _real_initialize() and
- _real_extract() methods and define a _VALID_URL regexp.
- Probably, they should also be added to the list of extractors.
- """
-
- _ready = False
- _downloader = None
-
- def __init__(self, downloader=None):
- """Constructor. Receives an optional downloader."""
- self._ready = False
- self.set_downloader(downloader)
-
- def suitable(self, url):
- """Receives a URL and returns True if suitable for this IE."""
- return re.match(self._VALID_URL, url) is not None
-
- def initialize(self):
- """Initializes an instance (authentication, etc)."""
- if not self._ready:
- self._real_initialize()
- self._ready = True
-
- def extract(self, url):
- """Extracts URL information and returns it in list of dicts."""
- self.initialize()
- return self._real_extract(url)
-
- def set_downloader(self, downloader):
- """Sets the downloader for this IE."""
- self._downloader = downloader
-
- def _real_initialize(self):
- """Real initialization process. Redefine in subclasses."""
- pass
-
- def _real_extract(self, url):
- """Real extraction process. Redefine in subclasses."""
- pass
-
-
-class YoutubeIE(InfoExtractor):
- """Information extractor for youtube.com."""
-
- _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
- _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
- _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
- _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
- _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
- _NETRC_MACHINE = 'youtube'
- # Listed in order of quality
- _available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
- _available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13']
- _video_extensions = {
- '13': '3gp',
- '17': 'mp4',
- '18': 'mp4',
- '22': 'mp4',
- '37': 'mp4',
- '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
- '43': 'webm',
- '44': 'webm',
- '45': 'webm',
- '46': 'webm',
- }
- _video_dimensions = {
- '5': '240x400',
- '6': '???',
- '13': '???',
- '17': '144x176',
- '18': '360x640',
- '22': '720x1280',
- '34': '360x640',
- '35': '480x854',
- '37': '1080x1920',
- '38': '3072x4096',
- '43': '360x640',
- '44': '480x854',
- '45': '720x1280',
- '46': '1080x1920',
- }
- IE_NAME = u'youtube'
-
- def report_lang(self):
- """Report attempt to set language."""
- self._downloader.to_screen(u'[youtube] Setting language')
-
- def report_login(self):
- """Report attempt to log in."""
- self._downloader.to_screen(u'[youtube] Logging in')
-
- def report_age_confirmation(self):
- """Report attempt to confirm age."""
- self._downloader.to_screen(u'[youtube] Confirming age')
-
- def report_video_webpage_download(self, video_id):
- """Report attempt to download video webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)
-
- def report_video_info_webpage_download(self, video_id):
- """Report attempt to download video info webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
-
- def report_video_subtitles_download(self, video_id):
- """Report attempt to download video info webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id)
-
- def report_information_extraction(self, video_id):
- """Report attempt to extract video information."""
- self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
-
- def report_unavailable_format(self, video_id, format):
- """Report extracted video URL."""
- self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
-
- def report_rtmp_download(self):
- """Indicate the download will use the RTMP protocol."""
- self._downloader.to_screen(u'[youtube] RTMP download detected')
-
- def _closed_captions_xml_to_srt(self, xml_string):
- srt = ''
- texts = re.findall(r'([^<]+)', xml_string, re.MULTILINE)
- # TODO parse xml instead of regex
- for n, (start, dur_tag, dur, caption) in enumerate(texts):
- if not dur: dur = '4'
- start = float(start)
- end = start + float(dur)
- start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000)
- end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000)
- caption = unescapeHTML(caption)
- caption = unescapeHTML(caption) # double cycle, intentional
- srt += str(n+1) + '\n'
- srt += start + ' --> ' + end + '\n'
- srt += caption + '\n\n'
- return srt
-
- def _print_formats(self, formats):
- print 'Available formats:'
- for x in formats:
- print '%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???'))
-
- def _real_initialize(self):
- if self._downloader is None:
- return
-
- username = None
- password = None
- downloader_params = self._downloader.params
-
- # Attempt to use provided username and password or .netrc data
- if downloader_params.get('username', None) is not None:
- username = downloader_params['username']
- password = downloader_params['password']
- elif downloader_params.get('usenetrc', False):
- try:
- info = netrc.netrc().authenticators(self._NETRC_MACHINE)
- if info is not None:
- username = info[0]
- password = info[2]
- else:
- raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
- except (IOError, netrc.NetrcParseError), err:
- self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
- return
-
- # Set language
- request = urllib2.Request(self._LANG_URL)
- try:
- self.report_lang()
- urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err))
- return
-
- # No authentication to be performed
- if username is None:
- return
-
- # Log in
- login_form = {
- 'current_form': 'loginForm',
- 'next': '/',
- 'action_login': 'Log In',
- 'username': username,
- 'password': password,
- }
- request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form))
- try:
- self.report_login()
- login_results = urllib2.urlopen(request).read()
- if re.search(r'(?i)]* name="loginForm"', login_results) is not None:
- self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
- return
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
- return
-
- # Confirm age
- age_form = {
- 'next_url': '/',
- 'action_confirm': 'Confirm',
- }
- request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form))
- try:
- self.report_age_confirmation()
- age_results = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
- return
-
- def _real_extract(self, url):
- # Extract original video URL from URL with redirection, like age verification, using next_url parameter
- mobj = re.search(self._NEXT_URL_RE, url)
- if mobj:
- url = 'http://www.youtube.com/' + urllib.unquote(mobj.group(1)).lstrip('/')
-
- # Extract video id from 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(2)
-
- # Get video webpage
- self.report_video_webpage_download(video_id)
- request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
- try:
- video_webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
- return
-
- # Attempt to extract SWF player URL
- mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
- if mobj is not None:
- player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
- else:
- player_url = None
-
- # Get video info
- self.report_video_info_webpage_download(video_id)
- for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
- video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
- % (video_id, el_type))
- request = urllib2.Request(video_info_url)
- try:
- video_info_webpage = urllib2.urlopen(request).read()
- video_info = parse_qs(video_info_webpage)
- if 'token' in video_info:
- break
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
- return
- if 'token' not in video_info:
- if 'reason' in video_info:
- self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0].decode('utf-8'))
- else:
- self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
- return
-
- # Check for "rental" videos
- if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
- self._downloader.trouble(u'ERROR: "rental" videos not supported')
- return
-
- # Start extracting information
- self.report_information_extraction(video_id)
-
- # uploader
- if 'author' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
- return
- video_uploader = urllib.unquote_plus(video_info['author'][0])
-
- # title
- if 'title' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = urllib.unquote_plus(video_info['title'][0])
- video_title = video_title.decode('utf-8')
-
- # thumbnail image
- if 'thumbnail_url' not in video_info:
- self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
- video_thumbnail = ''
- else: # don't panic if we can't find it
- video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
-
- # upload date
- upload_date = u'NA'
- mobj = re.search(r'id="eow-date.*?>(.*?)', video_webpage, re.DOTALL)
- if mobj is not None:
- upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
- format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y']
- for expression in format_expressions:
- try:
- upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
- except:
- pass
-
- # description
- video_description = get_element_by_id("eow-description", video_webpage.decode('utf8'))
- if video_description: video_description = clean_html(video_description)
- else: video_description = ''
-
- # closed captions
- video_subtitles = None
- if self._downloader.params.get('writesubtitles', False):
- try:
- self.report_video_subtitles_download(video_id)
- request = urllib2.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
- try:
- srt_list = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- raise Trouble(u'WARNING: unable to download video subtitles: %s' % str(err))
- srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list)
- srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list)
- if not srt_lang_list:
- raise Trouble(u'WARNING: video has no closed captions')
- if self._downloader.params.get('subtitleslang', False):
- srt_lang = self._downloader.params.get('subtitleslang')
- elif 'en' in srt_lang_list:
- srt_lang = 'en'
- else:
- srt_lang = srt_lang_list.keys()[0]
- if not srt_lang in srt_lang_list:
- raise Trouble(u'WARNING: no closed captions found in the specified language')
- request = urllib2.Request('http://www.youtube.com/api/timedtext?lang=%s&name=%s&v=%s' % (srt_lang, srt_lang_list[srt_lang], video_id))
- try:
- srt_xml = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- raise Trouble(u'WARNING: unable to download video subtitles: %s' % str(err))
- if not srt_xml:
- raise Trouble(u'WARNING: unable to download video subtitles')
- video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8'))
- except Trouble as trouble:
- self._downloader.trouble(trouble[0])
-
- # token
- video_token = urllib.unquote_plus(video_info['token'][0])
-
- # Decide which formats to download
- req_format = self._downloader.params.get('format', None)
-
- if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
- self.report_rtmp_download()
- video_url_list = [(None, video_info['conn'][0])]
- elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1:
- url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
- url_data = [parse_qs(uds) for uds in url_data_strs]
- url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data)
- url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data)
-
- format_limit = self._downloader.params.get('format_limit', None)
- available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
- if format_limit is not None and format_limit in available_formats:
- format_list = available_formats[available_formats.index(format_limit):]
- else:
- format_list = available_formats
- existing_formats = [x for x in format_list if x in url_map]
- if len(existing_formats) == 0:
- self._downloader.trouble(u'ERROR: no known formats available for video')
- return
- if self._downloader.params.get('listformats', None):
- self._print_formats(existing_formats)
- return
- if req_format is None or req_format == 'best':
- video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
- elif req_format == 'worst':
- video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
- elif req_format in ('-1', 'all'):
- video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
- else:
- # Specific formats. We pick the first in a slash-delimeted sequence.
- # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'.
- req_formats = req_format.split('/')
- video_url_list = None
- for rf in req_formats:
- if rf in url_map:
- video_url_list = [(rf, url_map[rf])]
- break
- if video_url_list is None:
- self._downloader.trouble(u'ERROR: requested format not available')
- return
- else:
- self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info')
- return
-
- results = []
- for format_param, video_real_url in video_url_list:
- # Extension
- video_extension = self._video_extensions.get(format_param, 'flv')
-
- results.append({
- 'id': video_id.decode('utf-8'),
- 'url': video_real_url.decode('utf-8'),
- 'uploader': video_uploader.decode('utf-8'),
- 'upload_date': upload_date,
- 'title': video_title,
- 'ext': video_extension.decode('utf-8'),
- 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
- 'thumbnail': video_thumbnail.decode('utf-8'),
- 'description': video_description,
- 'player_url': player_url,
- 'subtitles': video_subtitles
- })
- return results
-
-
-class MetacafeIE(InfoExtractor):
- """Information Extractor for metacafe.com."""
-
- _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
- _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
- _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
- IE_NAME = u'metacafe'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_disclaimer(self):
- """Report disclaimer retrieval."""
- self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')
-
- def report_age_confirmation(self):
- """Report attempt to confirm age."""
- self._downloader.to_screen(u'[metacafe] Confirming age')
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id)
-
- def _real_initialize(self):
- # Retrieve disclaimer
- request = urllib2.Request(self._DISCLAIMER)
- try:
- self.report_disclaimer()
- disclaimer = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
- return
-
- # Confirm age
- disclaimer_form = {
- 'filters': '0',
- 'submit': "Continue - I'm over 18",
- }
- request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form))
- try:
- self.report_age_confirmation()
- disclaimer = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
- return
-
- def _real_extract(self, url):
- # Extract id and simplified title from 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(1)
-
- # Check if video comes from YouTube
- mobj2 = re.match(r'^yt-(.*)$', video_id)
- if mobj2 is not None:
- self._downloader.download(['http://www.youtube.com/watch?v=%s' % mobj2.group(1)])
- return
-
- # Retrieve video webpage to extract further information
- request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)
- try:
- self.report_download_webpage(video_id)
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
- return
-
- # Extract URL, uploader and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
- if mobj is not None:
- mediaURL = urllib.unquote(mobj.group(1))
- video_extension = mediaURL[-3:]
-
- # Extract gdaKey if available
- mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
- if mobj is None:
- video_url = mediaURL
- else:
- gdaKey = mobj.group(1)
- video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
- else:
- mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- vardict = parse_qs(mobj.group(1))
- if 'mediaData' not in vardict:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0])
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mediaURL = mobj.group(1).replace('\\/', '/')
- video_extension = mediaURL[-3:]
- video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2))
-
- mobj = re.search(r'(?im)(.*) - Video', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_title = mobj.group(1).decode('utf-8')
-
- mobj = re.search(r'(?ms)By:\s*(.+?)<', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
- return
- video_uploader = mobj.group(1)
-
- return [{
- 'id': video_id.decode('utf-8'),
- 'url': video_url.decode('utf-8'),
- 'uploader': video_uploader.decode('utf-8'),
- 'upload_date': u'NA',
- 'title': video_title,
- 'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
- }]
-
-
-class DailymotionIE(InfoExtractor):
- """Information Extractor for Dailymotion"""
-
- _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
- IE_NAME = u'dailymotion'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
-
- def _real_extract(self, url):
- # Extract id and simplified title from 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(1)
-
- video_extension = 'flv'
-
- # Retrieve video webpage to extract further information
- request = urllib2.Request(url)
- request.add_header('Cookie', 'family_filter=off')
- try:
- self.report_download_webpage(video_id)
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
- return
-
- # Extract URL, uploader and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- sequence = urllib.unquote(mobj.group(1))
- mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '')
-
- # if needed add http://www.dailymotion.com/ if relative URL
-
- video_url = mediaURL
-
- mobj = re.search(r'', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_title = unescapeHTML(mobj.group('title').decode('utf-8'))
-
- mobj = re.search(r'(?im)[^<]+?]+?>([^<]+?)', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
- return
- video_uploader = mobj.group(1)
-
- return [{
- 'id': video_id.decode('utf-8'),
- 'url': video_url.decode('utf-8'),
- 'uploader': video_uploader.decode('utf-8'),
- 'upload_date': u'NA',
- 'title': video_title,
- 'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
- }]
-
-
-class GoogleIE(InfoExtractor):
- """Information extractor for video.google.com."""
-
- _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
- IE_NAME = u'video.google'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)
-
- def _real_extract(self, url):
- # Extract id from 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(1)
-
- video_extension = 'mp4'
-
- # Retrieve video webpage to extract further information
- request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id)
- try:
- self.report_download_webpage(video_id)
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
- return
-
- # Extract URL, uploader, and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r"download_url:'([^']+)'", webpage)
- if mobj is None:
- video_extension = 'flv'
- mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mediaURL = urllib.unquote(mobj.group(1))
- mediaURL = mediaURL.replace('\\x3d', '\x3d')
- mediaURL = mediaURL.replace('\\x26', '\x26')
-
- video_url = mediaURL
-
- mobj = re.search(r'(.*)', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_title = mobj.group(1).decode('utf-8')
-
- # Extract video description
- mobj = re.search(r'([^<]*)', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video description')
- return
- video_description = mobj.group(1).decode('utf-8')
- if not video_description:
- video_description = 'No description available.'
-
- # Extract video thumbnail
- if self._downloader.params.get('forcethumbnail', False):
- request = urllib2.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id)))
- try:
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
- return
- mobj = re.search(r'![]()
', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
- return
- video_thumbnail = mobj.group(1)
- else: # we need something to pass to process_info
- video_thumbnail = ''
-
- return [{
- 'id': video_id.decode('utf-8'),
- 'url': video_url.decode('utf-8'),
- 'uploader': u'NA',
- 'upload_date': u'NA',
- 'title': video_title,
- 'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
- }]
-
-
-class PhotobucketIE(InfoExtractor):
- """Information extractor for photobucket.com."""
-
- _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
- IE_NAME = u'photobucket'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
-
- def _real_extract(self, url):
- # Extract id from 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(1)
-
- video_extension = 'flv'
-
- # Retrieve video webpage to extract further information
- request = urllib2.Request(url)
- try:
- self.report_download_webpage(video_id)
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
- return
-
- # Extract URL, uploader, and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r'', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mediaURL = urllib.unquote(mobj.group(1))
-
- video_url = mediaURL
-
- mobj = re.search(r'(.*) video by (.*) - Photobucket', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_title = mobj.group(1).decode('utf-8')
-
- video_uploader = mobj.group(2).decode('utf-8')
-
- return [{
- 'id': video_id.decode('utf-8'),
- 'url': video_url.decode('utf-8'),
- 'uploader': video_uploader,
- 'upload_date': u'NA',
- 'title': video_title,
- 'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
- }]
-
-
-class YahooIE(InfoExtractor):
- """Information extractor for video.yahoo.com."""
-
- # _VALID_URL matches all Yahoo! Video URLs
- # _VPAGE_URL matches only the extractable '/watch/' URLs
- _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
- _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
- IE_NAME = u'video.yahoo'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
-
- def _real_extract(self, url, new_video=True):
- # Extract ID from 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(2)
- video_extension = 'flv'
-
- # Rewrite valid but non-extractable URLs as
- # extractable English language /watch/ URLs
- if re.match(self._VPAGE_URL, url) is None:
- request = urllib2.Request(url)
- try:
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
- return
-
- mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Unable to extract id field')
- return
- yahoo_id = mobj.group(1)
-
- mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Unable to extract vid field')
- return
- yahoo_vid = mobj.group(1)
-
- url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
- return self._real_extract(url, new_video=False)
-
- # Retrieve video webpage to extract further information
- request = urllib2.Request(url)
- try:
- self.report_download_webpage(video_id)
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
- return
-
- # Extract uploader and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r'', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = mobj.group(1).decode('utf-8')
-
- mobj = re.search(r'', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video uploader')
- return
- video_uploader = mobj.group(1).decode('utf-8')
-
- # Extract video thumbnail
- mobj = re.search(r'', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
- return
- video_thumbnail = mobj.group(1).decode('utf-8')
-
- # Extract video description
- mobj = re.search(r'', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video description')
- return
- video_description = mobj.group(1).decode('utf-8')
- if not video_description:
- video_description = 'No description available.'
-
- # Extract video height and width
- mobj = re.search(r'', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video height')
- return
- yv_video_height = mobj.group(1)
-
- mobj = re.search(r'', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video width')
- return
- yv_video_width = mobj.group(1)
-
- # Retrieve video playlist to extract media URL
- # I'm not completely sure what all these options are, but we
- # seem to need most of them, otherwise the server sends a 401.
- yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
- yv_bitrate = '700' # according to Wikipedia this is hard-coded
- request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
- '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
- '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
- try:
- self.report_download_webpage(video_id)
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
- return
-
- # Extract media URL from playlist XML
- mobj = re.search(r'[^:]*: (.*?)( \([^\(]*\))?', webpage)
- if mobj is not None:
- video_upload_date = mobj.group(1)
-
- # Vimeo specific: extract request signature and timestamp
- sig = config['request']['signature']
- timestamp = config['request']['timestamp']
-
- # Vimeo specific: extract video codec and quality information
- # TODO bind to format param
- codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')]
- for codec in codecs:
- if codec[0] in config["video"]["files"]:
- video_codec = codec[0]
- video_extension = codec[1]
- if 'hd' in config["video"]["files"][codec[0]]: quality = 'hd'
- else: quality = 'sd'
- break
- else:
- self._downloader.trouble(u'ERROR: no known codec found')
- return
-
- video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
- %(video_id, sig, timestamp, quality, video_codec.upper())
-
- return [{
- 'id': video_id,
- 'url': video_url,
- 'uploader': video_uploader,
- 'upload_date': video_upload_date,
- 'title': video_title,
- 'ext': video_extension,
- 'thumbnail': video_thumbnail,
- 'description': video_description,
- 'player_url': None,
- }]
-
-
-class GenericIE(InfoExtractor):
- """Generic last-resort information extractor."""
-
- _VALID_URL = r'.*'
- IE_NAME = u'generic'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
- self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
-
- def report_following_redirect(self, new_url):
- """Report information extraction."""
- self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url)
-
- def _test_redirect(self, url):
- """Check if it is a redirect, like url shorteners, in case restart chain."""
- class HeadRequest(urllib2.Request):
- def get_method(self):
- return "HEAD"
-
- class HEADRedirectHandler(urllib2.HTTPRedirectHandler):
- """
- Subclass the HTTPRedirectHandler to make it use our
- HeadRequest also on the redirected URL
- """
- def redirect_request(self, req, fp, code, msg, headers, newurl):
- if code in (301, 302, 303, 307):
- newurl = newurl.replace(' ', '%20')
- newheaders = dict((k,v) for k,v in req.headers.items()
- if k.lower() not in ("content-length", "content-type"))
- return HeadRequest(newurl,
- headers=newheaders,
- origin_req_host=req.get_origin_req_host(),
- unverifiable=True)
- else:
- raise urllib2.HTTPError(req.get_full_url(), code, msg, headers, fp)
-
- class HTTPMethodFallback(urllib2.BaseHandler):
- """
- Fallback to GET if HEAD is not allowed (405 HTTP error)
- """
- def http_error_405(self, req, fp, code, msg, headers):
- fp.read()
- fp.close()
-
- newheaders = dict((k,v) for k,v in req.headers.items()
- if k.lower() not in ("content-length", "content-type"))
- return self.parent.open(urllib2.Request(req.get_full_url(),
- headers=newheaders,
- origin_req_host=req.get_origin_req_host(),
- unverifiable=True))
-
- # Build our opener
- opener = urllib2.OpenerDirector()
- for handler in [urllib2.HTTPHandler, urllib2.HTTPDefaultErrorHandler,
- HTTPMethodFallback, HEADRedirectHandler,
- urllib2.HTTPErrorProcessor, urllib2.HTTPSHandler]:
- opener.add_handler(handler())
-
- response = opener.open(HeadRequest(url))
- new_url = response.geturl()
-
- if url == new_url: return False
-
- self.report_following_redirect(new_url)
- self._downloader.download([new_url])
- return True
-
- def _real_extract(self, url):
- if self._test_redirect(url): return
-
- video_id = url.split('/')[-1]
- request = urllib2.Request(url)
- try:
- self.report_download_webpage(video_id)
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
- return
- except ValueError, err:
- # since this is the last-resort InfoExtractor, if
- # this error is thrown, it'll be thrown here
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- self.report_extraction(video_id)
- # Start with something easy: JW Player in SWFObject
- mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
- if mobj is None:
- # Broaden the search a little bit
- mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- # It's possible that one of the regexes
- # matched, but returned an empty group:
- if mobj.group(1) is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- video_url = urllib.unquote(mobj.group(1))
- video_id = os.path.basename(video_url)
-
- # here's a fun little line of code for you:
- video_extension = os.path.splitext(video_id)[1][1:]
- video_id = os.path.splitext(video_id)[0]
-
- # it's tempting to parse this further, but you would
- # have to take into account all the variations like
- # Video Title - Site Name
- # Site Name | Video Title
- # Video Title - Tagline | Site Name
- # and so on and so forth; it's just not practical
- mobj = re.search(r'(.*)', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_title = mobj.group(1).decode('utf-8')
-
- # video uploader is domain name
- mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_uploader = mobj.group(1).decode('utf-8')
-
- return [{
- 'id': video_id.decode('utf-8'),
- 'url': video_url.decode('utf-8'),
- 'uploader': video_uploader,
- 'upload_date': u'NA',
- 'title': video_title,
- 'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
- }]
-
-
-class YoutubeSearchIE(InfoExtractor):
- """Information Extractor for YouTube search queries."""
- _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+'
- _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc'
- _max_youtube_results = 1000
- IE_NAME = u'youtube:search'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_page(self, query, pagenum):
- """Report attempt to download search page with given number."""
- query = query.decode(preferredencoding())
- self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
-
- def _real_extract(self, query):
- mobj = re.match(self._VALID_URL, query)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
- return
-
- prefix, query = query.split(':')
- prefix = prefix[8:]
- query = query.encode('utf-8')
- if prefix == '':
- self._download_n_results(query, 1)
- return
- elif prefix == 'all':
- self._download_n_results(query, self._max_youtube_results)
- return
- else:
- try:
- n = long(prefix)
- if n <= 0:
- self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
- return
- elif n > self._max_youtube_results:
- self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
- n = self._max_youtube_results
- self._download_n_results(query, n)
- return
- except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
-
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
-
- video_ids = []
- pagenum = 0
- limit = n
-
- while (50 * pagenum) < limit:
- self.report_download_page(query, pagenum+1)
- result_url = self._API_URL % (urllib.quote_plus(query), (50*pagenum)+1)
- request = urllib2.Request(result_url)
- try:
- data = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download API page: %s' % str(err))
- return
- api_response = json.loads(data)['data']
-
- new_ids = list(video['id'] for video in api_response['items'])
- video_ids += new_ids
-
- limit = min(n, api_response['totalItems'])
- pagenum += 1
-
- if len(video_ids) > n:
- video_ids = video_ids[:n]
- for id in video_ids:
- self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
- return
-
-
-class GoogleSearchIE(InfoExtractor):
- """Information Extractor for Google Video search queries."""
- _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+'
- _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
- _VIDEO_INDICATOR = r' self._max_google_results:
- self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
- n = self._max_google_results
- self._download_n_results(query, n)
- return
- except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
-
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
-
- video_ids = []
- pagenum = 0
-
- while True:
- self.report_download_page(query, pagenum)
- result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum*10)
- request = urllib2.Request(result_url)
- try:
- 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
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- video_id = mobj.group(1)
- if video_id not in video_ids:
- video_ids.append(video_id)
- if len(video_ids) == n:
- # Specified n videos reached
- for id in video_ids:
- self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id])
- return
-
- if re.search(self._MORE_PAGES_INDICATOR, page) is None:
- for id in video_ids:
- self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id])
- return
-
- pagenum = pagenum + 1
-
-
-class YahooSearchIE(InfoExtractor):
- """Information Extractor for Yahoo! Video search queries."""
- _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+'
- _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
- _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
- _MORE_PAGES_INDICATOR = r'\s*Next'
- _max_yahoo_results = 1000
- IE_NAME = u'video.yahoo:search'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_page(self, query, pagenum):
- """Report attempt to download playlist page with given number."""
- query = query.decode(preferredencoding())
- self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
-
- def _real_extract(self, query):
- mobj = re.match(self._VALID_URL, query)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
- return
-
- prefix, query = query.split(':')
- prefix = prefix[8:]
- query = query.encode('utf-8')
- if prefix == '':
- self._download_n_results(query, 1)
- return
- elif prefix == 'all':
- self._download_n_results(query, self._max_yahoo_results)
- return
- else:
- try:
- n = long(prefix)
- if n <= 0:
- self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
- return
- elif n > self._max_yahoo_results:
- self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
- n = self._max_yahoo_results
- self._download_n_results(query, n)
- return
- except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
-
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
-
- video_ids = []
- already_seen = set()
- pagenum = 1
-
- while True:
- self.report_download_page(query, pagenum)
- result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
- request = urllib2.Request(result_url)
- try:
- 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
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- video_id = mobj.group(1)
- if video_id not in already_seen:
- video_ids.append(video_id)
- already_seen.add(video_id)
- if len(video_ids) == n:
- # Specified n videos reached
- for id in video_ids:
- self._downloader.download(['http://video.yahoo.com/watch/%s' % id])
- return
-
- if re.search(self._MORE_PAGES_INDICATOR, page) is None:
- for id in video_ids:
- self._downloader.download(['http://video.yahoo.com/watch/%s' % id])
- return
-
- pagenum = pagenum + 1
-
-
-class YoutubePlaylistIE(InfoExtractor):
- """Information Extractor for YouTube playlists."""
-
- _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
- _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
- _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&list=(PL)?%s&'
- _MORE_PAGES_INDICATOR = r'yt-uix-pager-next'
- IE_NAME = u'youtube:playlist'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_page(self, playlist_id, pagenum):
- """Report attempt to download playlist page with given number."""
- self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
-
- def _real_extract(self, url):
- # Extract playlist id
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid url: %s' % url)
- return
-
- # Single video case
- if mobj.group(3) is not None:
- self._downloader.download([mobj.group(3)])
- return
-
- # Download playlist pages
- # 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_prefix = 'p'
- playlist_access = 'view_play_list'
- playlist_id = mobj.group(2)
- video_ids = []
- pagenum = 1
-
- while True:
- self.report_download_page(playlist_id, pagenum)
- url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum)
- request = urllib2.Request(url)
- try:
- 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
- ids_in_page = []
- for mobj in re.finditer(self._VIDEO_INDICATOR_TEMPLATE % playlist_id, page):
- if mobj.group(1) not in ids_in_page:
- ids_in_page.append(mobj.group(1))
- video_ids.extend(ids_in_page)
-
- if re.search(self._MORE_PAGES_INDICATOR, page) is None:
- break
- pagenum = pagenum + 1
-
- playliststart = self._downloader.params.get('playliststart', 1) - 1
- playlistend = self._downloader.params.get('playlistend', -1)
- if playlistend == -1:
- video_ids = video_ids[playliststart:]
- else:
- video_ids = video_ids[playliststart:playlistend]
-
- for id in video_ids:
- self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
- return
-
-
-class YoutubeUserIE(InfoExtractor):
- """Information Extractor for YouTube users."""
-
- _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
- _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
- _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=(.+?)[\<&]'
- IE_NAME = u'youtube:user'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_page(self, username, start_index):
- """Report attempt to download user page."""
- 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_extract(self, url):
- # Extract username
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid url: %s' % url)
- return
-
- 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 = []
- pagenum = 0
-
- while True:
- start_index = pagenum * self._GDATA_PAGE_SIZE + 1
- self.report_download_page(username, start_index)
-
- request = urllib2.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index))
-
- try:
- 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
- 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
- playlistend = self._downloader.params.get('playlistend', -1)
-
- if playlistend == -1:
- video_ids = video_ids[playliststart:]
- else:
- video_ids = video_ids[playliststart:playlistend]
-
- self._downloader.to_screen(u"[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._downloader.download(['http://www.youtube.com/watch?v=%s' % video_id])
-
-
-class BlipTVUserIE(InfoExtractor):
- """Information Extractor for blip.tv users."""
-
- _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$'
- _PAGE_SIZE = 12
- IE_NAME = u'blip.tv:user'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_page(self, username, pagenum):
- """Report attempt to download user page."""
- self._downloader.to_screen(u'[%s] user %s: Downloading video ids from page %d' %
- (self.IE_NAME, username, pagenum))
-
- def _real_extract(self, url):
- # Extract username
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid url: %s' % url)
- return
-
- username = mobj.group(1)
-
- page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
-
- request = urllib2.Request(url)
-
- try:
- page = urllib2.urlopen(request).read().decode('utf-8')
- mobj = re.search(r'data-users-id="([^"]+)"', page)
- page_base = page_base % mobj.group(1)
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
- return
-
-
- # Download video ids using BlipTV Ajax calls. Result size per
- # query is limited (currently to 12 videos) so we need to query
- # page by page until there are no video ids - it means we got
- # all of them.
-
- video_ids = []
- pagenum = 1
-
- while True:
- self.report_download_page(username, pagenum)
-
- request = urllib2.Request( page_base + "&page=" + str(pagenum) )
-
- try:
- page = urllib2.urlopen(request).read().decode('utf-8')
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
- return
-
- # Extract video identifiers
- ids_in_page = []
-
- for mobj in re.finditer(r'href="/([^"]+)"', page):
- if mobj.group(1) not in ids_in_page:
- ids_in_page.append(unescapeHTML(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._PAGE_SIZE:
- break
-
- pagenum += 1
-
- all_ids_count = len(video_ids)
- playliststart = self._downloader.params.get('playliststart', 1) - 1
- playlistend = self._downloader.params.get('playlistend', -1)
-
- if playlistend == -1:
- video_ids = video_ids[playliststart:]
- else:
- video_ids = video_ids[playliststart:playlistend]
-
- self._downloader.to_screen(u"[%s] user %s: Collected %d video ids (downloading %d of them)" %
- (self.IE_NAME, username, all_ids_count, len(video_ids)))
-
- for video_id in video_ids:
- self._downloader.download([u'http://blip.tv/'+video_id])
-
-
-class DepositFilesIE(InfoExtractor):
- """Information extractor for depositfiles.com"""
-
- _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
- IE_NAME = u'DepositFiles'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, file_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
-
- def report_extraction(self, file_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
-
- def _real_extract(self, url):
- file_id = url.split('/')[-1]
- # Rebuild url in english locale
- url = 'http://depositfiles.com/en/files/' + file_id
-
- # Retrieve file webpage with 'Free download' button pressed
- free_download_indication = { 'gateway_result' : '1' }
- request = urllib2.Request(url, urllib.urlencode(free_download_indication))
- try:
- self.report_download_webpage(file_id)
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err))
- return
-
- # Search for the real file URL
- mobj = re.search(r'