X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube-dl;h=67e1a0ffd75c7f2be68f9b92f63a987bf6c4ccf4;hb=2b70537d7b102969839557b221a29b6bd3c670af;hp=762bfc3ef55deb645181ef65535dec1e513c8a5a;hpb=5623100e43b12413790c4017eafb3412e29e517f;p=youtube-dl diff --git a/youtube-dl b/youtube-dl index 762bfc3ef..67e1a0ffd 100755 --- a/youtube-dl +++ b/youtube-dl @@ -9,12 +9,8 @@ # Author: Gergely Imreh # Author: Philipp Hagemeister # License: Public domain code -from __future__ import with_statement -import contextlib import cookielib -import ctypes import datetime -import email.utils import gzip import htmlentitydefs import httplib @@ -34,6 +30,13 @@ import urllib2 import warnings import zlib +if os.name == 'nt': + import ctypes + +try: + import email.utils +except ImportError: # Python 2.4 + import email.Utils try: import cStringIO as StringIO except ImportError: @@ -47,11 +50,11 @@ except ImportError: try: import lxml.etree -except ImportError: # Python < 2.6 +except ImportError: pass # Handled below std_headers = { - 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:2.0b11) Gecko/20100101 Firefox/4.0b11', + 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1', 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 'Accept-Encoding': 'gzip, deflate', @@ -62,7 +65,7 @@ simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode try: import json -except ImportError: # Python <2.5, use trivialjson (https://github.com/phihag/trivialjson): +except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson): import re class json(object): @staticmethod @@ -707,8 +710,11 @@ class FileDownloader(object): try: descfn = filename + '.description' self.report_writedescription(descfn) - with contextlib.closing(open(descfn, 'wb')) as descfile: + descfile = open(descfn, 'wb') + try: descfile.write(info_dict['description'].encode('utf-8')) + finally: + descfile.close() except (OSError, IOError): self.trouble(u'ERROR: Cannot write description file: %s' % str(descfn)) return @@ -722,8 +728,11 @@ class FileDownloader(object): self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.') return try: - with contextlib.closing(open(infofn, 'wb')) as infof: + infof = open(infofn, 'wb') + try: json.dump(info_dict, infof) + finally: + infof.close() except (OSError, IOError): self.trouble(u'ERROR: Cannot write metadata to JSON file: %s' % str(infofn)) return @@ -1019,7 +1028,7 @@ class InfoExtractor(object): class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" - _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$' + _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$' _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' @@ -1233,7 +1242,6 @@ class YoutubeIE(InfoExtractor): except NameError: video_description = u'No description available.' if self._downloader.params.get('forcedescription', False) or self._downloader.params.get('writedescription', False): - warnings.warn(u'You are using an old Python version, install Python 2.6+ or lxml. Falling back to old video description extractor.') mobj = re.search(r'', video_webpage) if mobj is not None: video_description = mobj.group(1).decode('utf-8') @@ -1241,6 +1249,7 @@ class YoutubeIE(InfoExtractor): html_parser = lxml.etree.HTMLParser(encoding='utf-8') vwebpage_doc = lxml.etree.parse(StringIO.StringIO(video_webpage), html_parser) video_description = u''.join(vwebpage_doc.xpath('id("eow-description")//text()')) + # TODO use another parser # token video_token = urllib.unquote_plus(video_info['token'][0]) @@ -1248,8 +1257,15 @@ class YoutubeIE(InfoExtractor): # Decide which formats to download req_format = self._downloader.params.get('format', None) - if 'fmt_url_map' in video_info and len(video_info['fmt_url_map']) >= 1 and ',' in video_info['fmt_url_map'][0]: - url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(',')) + 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) if format_limit is not None and format_limit in self._available_formats: format_list = self._available_formats[self._available_formats.index(format_limit):] @@ -1269,13 +1285,8 @@ class YoutubeIE(InfoExtractor): self._downloader.trouble(u'ERROR: requested format not available') return video_url_list = [(req_format, url_map[req_format])] # Specific format - - elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): - self.report_rtmp_download() - video_url_list = [(None, video_info['conn'][0])] - else: - self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info') + self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info') return for format_param, video_real_url in video_url_list: @@ -1285,7 +1296,6 @@ class YoutubeIE(InfoExtractor): # Extension video_extension = self._video_extensions.get(format_param, 'flv') - # Find the video URL in fmt_url_map or conn paramters try: # Process video information self._downloader.process_info({ @@ -2710,7 +2720,6 @@ class FacebookIE(InfoExtractor): # Extension video_extension = self._video_extensions.get(format_param, 'mp4') - # Find the video URL in fmt_url_map or conn paramters try: # Process video information self._downloader.process_info({ @@ -2732,7 +2741,7 @@ class FacebookIE(InfoExtractor): class BlipTVIE(InfoExtractor): """Information extractor for blip.tv""" - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip.tv(/.+)$' + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$' _URL_EXT = r'^.*\.([a-z0-9]+)$' @staticmethod @@ -2754,7 +2763,11 @@ class BlipTVIE(InfoExtractor): self._downloader.trouble(u'ERROR: invalid URL: %s' % url) return - json_url = url + ('&' if '?' in url else '?') + 'skin=json&version=2&no_wrap=1' + if '?' in url: + cchar = '&' + else: + cchar = '?' + json_url = url + cchar + 'skin=json&version=2&no_wrap=1' request = urllib2.Request(json_url) self.report_extraction(mobj.group(1)) try: @@ -2764,7 +2777,10 @@ class BlipTVIE(InfoExtractor): return try: json_data = json.loads(json_code) - data = json_data['Post'] if 'Post' in json_data else json_data + if 'Post' in json_data: + data = json_data['Post'] + else: + data = json_data upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d') video_url = data['media']['url'] @@ -2958,7 +2974,7 @@ if __name__ == '__main__': # Parse command line parser = optparse.OptionParser( usage='Usage: %prog [options] url...', - version='2011.07.09-phihag', + version='2011.08.04-phihag', conflict_handler='resolve', )