X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/65cc51b0a1ddf217bc2026332532e0f8019c158a..e2ab891fc9c2fba13be7528d0964f7bca6319bdb:/youtube_dl/InfoExtractors.py diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py old mode 100644 new mode 100755 index 5ebe64b..672ef9e --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -1,3568 +1,4 @@ -#!/usr/bin/env python -# -*- coding: utf-8 -*- +# Legacy file for backwards compatibility, use youtube_dl.extractor instead! -from __future__ import absolute_import - -import datetime -import netrc -import os -import re -import socket -import time -import email.utils -import xml.etree.ElementTree -import random -import math - -from .utils import * - - -class InfoExtractor(object): - """Information Extractor class. - - Information extractors are the classes that, given a URL, extract - information about the video (or videos) the URL refers to. This - information includes the real video URL, the video 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, unescaped. - upload_date: Video upload date (YYYYMMDD). - title: Video title, unescaped. - ext: Video filename extension. - - The following fields are optional: - - format: The video format, defaults to ext (used for --get-format) - thumbnail: Full URL to a video thumbnail image. - description: One-line video description. - player_url: SWF Player URL (used for rtmpdump). - subtitles: The .srt file contents. - urlhandle: [internal] The urlHandle to be used to download the file, - like returned by urllib.request.urlopen - - The fields should all be Unicode strings. - - 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. - - _real_extract() must return a *list* of information dictionaries as - described above. - - Finally, the _WORKING attribute should be set to False for broken IEs - in order to warn the users and skip the tests. - """ - - _ready = False - _downloader = None - _WORKING = True - - 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 working(self): - """Getter method for _WORKING.""" - return self._WORKING - - 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?://)? # http(s):// (optional) - (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/| - tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains - (?:.*?\#/)? # handle anchor (#/) redirect urls - (?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs - (?: # the various things that can precede the ID: - (?:(?:v|embed|e)/) # v/ or embed/ or e/ - |(?: # or the v= param in all its forms - (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) - (?:\?|\#!?) # the params delimiter ? or # or #! - (?:.+&)? # any other preceding param (like /?s=tuff&v=xxxx) - v= - ) - )? # optional -> youtube.com/xxxx is OK - )? # all until now is optional -> you can pass the naked ID - ([0-9A-Za-z_-]+) # here is it! the YouTube video ID - (?(1).+)? # if we found the ID, everything can follow - $""" - _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 suitable(self, url): - """Receives a URL and returns True if suitable for this IE.""" - return re.match(self._VALID_URL, url, re.VERBOSE) is not None - - 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) as err: - self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err)) - return - - # Set language - request = compat_urllib_request.Request(self._LANG_URL) - try: - self.report_lang() - compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.to_stderr(u'WARNING: unable to set language: %s' % compat_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 = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form)) - try: - self.report_login() - login_results = compat_urllib_request.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 (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err)) - return - - # Confirm age - age_form = { - 'next_url': '/', - 'action_confirm': 'Confirm', - } - request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form)) - try: - self.report_age_confirmation() - age_results = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_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/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/') - - # Extract video id from URL - mobj = re.match(self._VALID_URL, url, re.VERBOSE) - 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 = compat_urllib_request.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id) - try: - video_webpage_bytes = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) - return - - video_webpage = video_webpage_bytes.decode('utf-8', 'ignore') - - # 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 = compat_urllib_request.Request(video_info_url) - try: - video_info_webpage_bytes = compat_urllib_request.urlopen(request).read() - video_info_webpage = video_info_webpage_bytes.decode('utf-8', 'ignore') - video_info = compat_parse_qs(video_info_webpage) - if 'token' in video_info: - break - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_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]) - 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 = compat_urllib_parse.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 = compat_urllib_parse.unquote_plus(video_info['title'][0]) - - # 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 = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0]) - - # upload date - upload_date = None - 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) - 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 = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id) - try: - srt_list = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise Trouble(u'WARNING: unable to download video subtitles: %s' % compat_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 = compat_urllib_request.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 = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise Trouble(u'WARNING: unable to download video subtitles: %s' % compat_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]) - - if 'length_seconds' not in video_info: - self._downloader.trouble(u'WARNING: unable to extract video duration') - video_duration = '' - else: - video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0]) - - # token - video_token = compat_urllib_parse.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 = [compat_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] + '&signature=' + ud['sig'][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') - - video_format = '{0} - {1}'.format(format_param if format_param else video_extension, - self._video_dimensions.get(format_param, '???')) - - results.append({ - 'id': video_id, - 'url': video_real_url, - 'uploader': video_uploader, - 'upload_date': upload_date, - 'title': video_title, - 'ext': video_extension, - 'format': video_format, - 'thumbnail': video_thumbnail, - 'description': video_description, - 'player_url': player_url, - 'subtitles': video_subtitles, - 'duration': video_duration - }) - 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 = compat_urllib_request.Request(self._DISCLAIMER) - try: - self.report_disclaimer() - disclaimer = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % compat_str(err)) - return - - # Confirm age - disclaimer_form = { - 'filters': '0', - 'submit': "Continue - I'm over 18", - } - request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form)) - try: - self.report_age_confirmation() - disclaimer = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_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 = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id) - try: - self.report_download_webpage(video_id) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_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 = compat_urllib_parse.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 = compat_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'submitter=(.*?);', 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': None, - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - }] - - -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).split('_')[0].split('?')[0] - - video_extension = 'mp4' - - # Retrieve video webpage to extract further information - request = compat_urllib_request.Request(url) - request.add_header('Cookie', 'family_filter=off') - try: - self.report_download_webpage(video_id) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err)) - return - - # Extract URL, uploader and title from webpage - self.report_extraction(video_id) - mobj = re.search(r'\s*var flashvars = (.*)', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return - flashvars = compat_urllib_parse.unquote(mobj.group(1)) - - for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']: - if key in flashvars: - max_quality = key - self._downloader.to_screen(u'[dailymotion] Using %s' % key) - break - else: - self._downloader.trouble(u'ERROR: unable to extract video URL') - return - - mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video URL') - return - - video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/') - - # TODO: support choosing qualities - - 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')) - - video_uploader = None - mobj = re.search(r'(?im)[^<]+?]+?>([^<]+?)', webpage) - if mobj is None: - # lookin for official user - mobj_official = re.search(r'', webpage) - if mobj_official is None: - self._downloader.trouble(u'WARNING: unable to extract uploader nickname') - else: - video_uploader = mobj_official.group(1) - else: - video_uploader = mobj.group(1) - - video_upload_date = None - mobj = re.search(r'
([0-9]{2})-([0-9]{2})-([0-9]{4})
', webpage) - if mobj is not None: - video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1) - - return [{ - 'id': video_id.decode('utf-8'), - 'url': video_url.decode('utf-8'), - 'uploader': video_uploader.decode('utf-8'), - 'upload_date': video_upload_date, - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - }] - - -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 = compat_urllib_request.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id) - try: - self.report_download_webpage(video_id) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_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 = compat_urllib_parse.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 = compat_urllib_request.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id))) - try: - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_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': None, - 'upload_date': None, - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - }] - - -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 = compat_urllib_request.Request(url) - try: - self.report_download_webpage(video_id) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_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 = compat_urllib_parse.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': None, - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - }] - - -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 = compat_urllib_request.Request(url) - try: - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_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 = compat_urllib_request.Request(url) - try: - self.report_download_webpage(video_id) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_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 = compat_urllib_request.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 = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_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 - # First consider quality, then codecs, then take everything - # TODO bind to format param - codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')] - files = { 'hd': [], 'sd': [], 'other': []} - for codec_name, codec_extension in codecs: - if codec_name in config["video"]["files"]: - if 'hd' in config["video"]["files"][codec_name]: - files['hd'].append((codec_name, codec_extension, 'hd')) - elif 'sd' in config["video"]["files"][codec_name]: - files['sd'].append((codec_name, codec_extension, 'sd')) - else: - files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0])) - - for quality in ('hd', 'sd', 'other'): - if len(files[quality]) > 0: - video_quality = files[quality][0][2] - video_codec = files[quality][0][0] - video_extension = files[quality][0][1] - self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality)) - 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, video_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, - }] - - -class ArteTvIE(InfoExtractor): - """arte.tv information extractor.""" - - _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*' - _LIVE_URL = r'index-[0-9]+\.html$' - - IE_NAME = u'arte.tv' - - def __init__(self, downloader=None): - InfoExtractor.__init__(self, downloader) - - def report_download_webpage(self, video_id): - """Report webpage download.""" - self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id) - - def report_extraction(self, video_id): - """Report information extraction.""" - self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id) - - def fetch_webpage(self, url): - self._downloader.increment_downloads() - request = compat_urllib_request.Request(url) - try: - self.report_download_webpage(url) - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) - return - except ValueError as err: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return - return webpage - - def grep_webpage(self, url, regex, regexFlags, matchTuples): - page = self.fetch_webpage(url) - mobj = re.search(regex, page, regexFlags) - info = {} - - if mobj is None: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) - return - - for (i, key, err) in matchTuples: - if mobj.group(i) is None: - self._downloader.trouble(err) - return - else: - info[key] = mobj.group(i) - - return info - - def extractLiveStream(self, url): - video_lang = url.split('/')[-4] - info = self.grep_webpage( - url, - r'src="(.*?/videothek_js.*?\.js)', - 0, - [ - (1, 'url', u'ERROR: Invalid URL: %s' % url) - ] - ) - http_host = url.split('/')[2] - next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url'))) - info = self.grep_webpage( - next_url, - r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' + - '(http://.*?\.swf).*?' + - '(rtmp://.*?)\'', - re.DOTALL, - [ - (1, 'path', u'ERROR: could not extract video path: %s' % url), - (2, 'player', u'ERROR: could not extract video player: %s' % url), - (3, 'url', u'ERROR: could not extract video url: %s' % url) - ] - ) - video_url = u'%s/%s' % (info.get('url'), info.get('path')) - - def extractPlus7Stream(self, url): - video_lang = url.split('/')[-3] - info = self.grep_webpage( - url, - r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)', - 0, - [ - (1, 'url', u'ERROR: Invalid URL: %s' % url) - ] - ) - next_url = compat_urllib_parse.unquote(info.get('url')) - info = self.grep_webpage( - next_url, - r'