X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube-dl;h=1ae68b2b5d017c3d530eb986cb48f50c3b368234;hb=2c8d32de33dd6618659cd1fe98dcdf09fde1ecaf;hp=e980f41f8bb5ebce31c5553455b4c2112430b866;hpb=9e0dd8692ea16d62564c6b05c6fdc3f2e0b2f02d;p=youtube-dl.git
diff --git a/youtube-dl b/youtube-dl
index e980f41f8..1ae68b2b5 100755
--- a/youtube-dl
+++ b/youtube-dl
@@ -1,16 +1,21 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
-# Author: Ricardo Garcia Gonzalez
-# Author: Danny Colligan
-# Author: Benjamin Johnson
-# Author: Vasyl' Vavrychuk
-# Author: Witold Baryluk
-# Author: PaweÅ Paprota
-# License: Public domain code
+
+__author__ = (
+ 'Ricardo Garcia Gonzalez',
+ 'Danny Colligan',
+ 'Benjamin Johnson',
+ 'Vasyl\' Vavrychuk',
+ 'Witold Baryluk',
+ 'PaweÅ Paprota',
+ 'Gergely Imreh',
+ )
+
+__license__ = 'Public Domain'
+__version__ = '2011.08.24-phihag'
+
import cookielib
-import ctypes
import datetime
-import email.utils
import gzip
import htmlentitydefs
import httplib
@@ -22,22 +27,39 @@ import os.path
import re
import socket
import string
-import StringIO
import subprocess
import sys
import time
import urllib
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:
+ import StringIO
+
# parse_qs was moved from the cgi module to the urlparse module recently.
try:
from urlparse import parse_qs
except ImportError:
from cgi import parse_qs
+try:
+ import lxml.etree
+except ImportError:
+ pass # Handled below
+
std_headers = {
- 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.12) Gecko/20101028 Firefox/3.6.12',
+ 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv: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',
@@ -46,6 +68,119 @@ std_headers = {
simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
+try:
+ import json
+except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson):
+ import re
+ class json(object):
+ @staticmethod
+ def loads(s):
+ s = s.decode('UTF-8')
+ def raiseError(msg, i):
+ raise ValueError(msg + ' at position ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]))
+ def skipSpace(i, expectMore=True):
+ while i < len(s) and s[i] in ' \t\r\n':
+ i += 1
+ if expectMore:
+ if i >= len(s):
+ raiseError('Premature end', i)
+ return i
+ def decodeEscape(match):
+ esc = match.group(1)
+ _STATIC = {
+ '"': '"',
+ '\\': '\\',
+ '/': '/',
+ 'b': unichr(0x8),
+ 'f': unichr(0xc),
+ 'n': '\n',
+ 'r': '\r',
+ 't': '\t',
+ }
+ if esc in _STATIC:
+ return _STATIC[esc]
+ if esc[0] == 'u':
+ if len(esc) == 1+4:
+ return unichr(int(esc[1:5], 16))
+ if len(esc) == 5+6 and esc[5:7] == '\\u':
+ hi = int(esc[1:5], 16)
+ low = int(esc[7:11], 16)
+ return unichr((hi - 0xd800) * 0x400 + low - 0xdc00 + 0x10000)
+ raise ValueError('Unknown escape ' + str(esc))
+ def parseString(i):
+ i += 1
+ e = i
+ while True:
+ e = s.index('"', e)
+ bslashes = 0
+ while s[e-bslashes-1] == '\\':
+ bslashes += 1
+ if bslashes % 2 == 1:
+ e += 1
+ continue
+ break
+ rexp = re.compile(r'\\(u[dD][89aAbB][0-9a-fA-F]{2}\\u[0-9a-fA-F]{4}|u[0-9a-fA-F]{4}|.|$)')
+ stri = rexp.sub(decodeEscape, s[i:e])
+ return (e+1,stri)
+ def parseObj(i):
+ i += 1
+ res = {}
+ i = skipSpace(i)
+ if s[i] == '}': # Empty dictionary
+ return (i+1,res)
+ while True:
+ if s[i] != '"':
+ raiseError('Expected a string object key', i)
+ i,key = parseString(i)
+ i = skipSpace(i)
+ if i >= len(s) or s[i] != ':':
+ raiseError('Expected a colon', i)
+ i,val = parse(i+1)
+ res[key] = val
+ i = skipSpace(i)
+ if s[i] == '}':
+ return (i+1, res)
+ if s[i] != ',':
+ raiseError('Expected comma or closing curly brace', i)
+ i = skipSpace(i+1)
+ def parseArray(i):
+ res = []
+ i = skipSpace(i+1)
+ if s[i] == ']': # Empty array
+ return (i+1,res)
+ while True:
+ i,val = parse(i)
+ res.append(val)
+ i = skipSpace(i) # Raise exception if premature end
+ if s[i] == ']':
+ return (i+1, res)
+ if s[i] != ',':
+ raiseError('Expected a comma or closing bracket', i)
+ i = skipSpace(i+1)
+ def parseDiscrete(i):
+ for k,v in {'true': True, 'false': False, 'null': None}.items():
+ if s.startswith(k, i):
+ return (i+len(k), v)
+ raiseError('Not a boolean (or null)', i)
+ def parseNumber(i):
+ mobj = re.match('^(-?(0|[1-9][0-9]*)(\.[0-9]*)?([eE][+-]?[0-9]+)?)', s[i:])
+ if mobj is None:
+ raiseError('Not a number', i)
+ nums = mobj.group(1)
+ if '.' in nums or 'e' in nums or 'E' in nums:
+ return (i+len(nums), float(nums))
+ return (i+len(nums), int(nums))
+ CHARMAP = {'{': parseObj, '[': parseArray, '"': parseString, 't': parseDiscrete, 'f': parseDiscrete, 'n': parseDiscrete}
+ def parse(i):
+ i = skipSpace(i)
+ i,res = CHARMAP.get(s[i], parseNumber)(i)
+ i = skipSpace(i, False)
+ return (i,res)
+ i,res = parse(0)
+ if i < len(s):
+ raise ValueError('Extra data at end of input (index ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]) + ')')
+ return res
+
def preferredencoding():
"""Get preferred encoding.
@@ -285,6 +420,8 @@ class FileDownloader(object):
consoletitle: Display progress in console window's titlebar.
nopart: Do not use temporary .part files.
updatetime: Use the Last-modified header to set output file timestamps.
+ writedescription: Write the video description to a .description file
+ writeinfojson: Write the video description to a .info.json file
"""
params = None
@@ -480,6 +617,14 @@ class FileDownloader(object):
except:
pass
+ def report_writedescription(self, descfn):
+ """ Report that the description file is being written """
+ self.to_screen(u'[info] Writing video description to: %s' % descfn, ignore_encoding_errors=True)
+
+ def report_writeinfojson(self, infofn):
+ """ Report that the metadata file has been written """
+ self.to_screen(u'[info] Video description metadata as JSON to: %s' % infofn, ignore_encoding_errors=True)
+
def report_destination(self, filename):
"""Report destination filename."""
self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
@@ -566,6 +711,37 @@ class FileDownloader(object):
self.trouble(u'ERROR: unable to create directories: %s' % str(err))
return
+ if self.params.get('writedescription', False):
+ try:
+ descfn = filename + '.description'
+ self.report_writedescription(descfn)
+ 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
+
+ if self.params.get('writeinfojson', False):
+ infofn = filename + '.info.json'
+ self.report_writeinfojson(infofn)
+ try:
+ json.dump
+ except (NameError,AttributeError):
+ 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:
+ 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
+
try:
success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None))
except (OSError, IOError), err:
@@ -705,7 +881,7 @@ class FileDownloader(object):
else:
# Examine the reported length
if (content_length is not None and
- (resume_len - 100 < long(content_length) < resume_len + 100)):
+ (resume_len - 100 < long(content_length) < resume_len + 100)):
# The file had already been fully downloaded.
# Explanation to the above condition: in issue #175 it was revealed that
# YouTube sometimes adds or removes a few bytes from the end of the file,
@@ -857,7 +1033,7 @@ class InfoExtractor(object):
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
- _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed)/)|(?:(?: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'
@@ -1055,10 +1231,10 @@ class YoutubeIE(InfoExtractor):
# upload date
upload_date = u'NA'
- mobj = re.search(r'id="eow-date".*?>(.*?)', video_webpage, re.DOTALL)
+ 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']
+ 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')
@@ -1066,11 +1242,19 @@ class YoutubeIE(InfoExtractor):
pass
# description
- video_description = 'No description available.'
- if self._downloader.params.get('forcedescription', False):
- mobj = re.search(r'', video_webpage)
- if mobj is not None:
- video_description = mobj.group(1)
+ try:
+ lxml.etree
+ except NameError:
+ video_description = u'No description available.'
+ if self._downloader.params.get('forcedescription', False) or self._downloader.params.get('writedescription', False):
+ mobj = re.search(r'', video_webpage)
+ if mobj is not None:
+ video_description = mobj.group(1).decode('utf-8')
+ else:
+ 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])
@@ -1078,8 +1262,15 @@ class YoutubeIE(InfoExtractor):
# Decide which formats to download
req_format = self._downloader.params.get('format', None)
- if 'fmt_url_map' in video_info:
- 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):]
@@ -1099,13 +1290,8 @@ 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:
@@ -1115,7 +1301,6 @@ 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({
@@ -1128,7 +1313,7 @@ class YoutubeIE(InfoExtractor):
'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.decode('utf-8'),
+ 'description': video_description,
'player_url': player_url,
})
except UnavailableVideoError, err:
@@ -1682,8 +1867,8 @@ class YahooIE(InfoExtractor):
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')
+ '&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()
@@ -2096,8 +2281,8 @@ class YahooSearchIE(InfoExtractor):
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
- _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/|p/)([^&]+).*'
- _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
+ _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists|artist)\?.*?(p|a)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([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 = r'/watch\?v=(.+?)&'
_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*'
_youtube_ie = None
@@ -2124,14 +2309,26 @@ class YoutubePlaylistIE(InfoExtractor):
self._downloader.trouble(u'ERROR: invalid url: %s' % url)
return
+ # Single video case
+ if mobj.group(3) is not None:
+ self._youtube_ie.extract(mobj.group(3))
+ return
+
# Download playlist pages
- playlist_id = mobj.group(1)
+ # prefix is 'p' as default for playlists but there are other types that need extra care
+ playlist_prefix = mobj.group(1)
+ if playlist_prefix == 'a':
+ playlist_access = 'artist'
+ else:
+ playlist_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)
- request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum))
+ request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum))
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@@ -2240,9 +2437,9 @@ class YoutubeUserIE(InfoExtractor):
video_ids = video_ids[playliststart:]
else:
video_ids = video_ids[playliststart:playlistend]
-
+
self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" %
- (username, all_ids_count, len(video_ids)))
+ (username, all_ids_count, len(video_ids)))
for video_id in video_ids:
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id)
@@ -2327,6 +2524,301 @@ class DepositFilesIE(InfoExtractor):
except UnavailableVideoError, err:
self._downloader.trouble(u'ERROR: unable to download file')
+class FacebookIE(InfoExtractor):
+ """Information Extractor for Facebook"""
+
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook.com/video/video.php\?(?:.*?)v=(?P\d+)(?:.*)'
+ _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
+ _NETRC_MACHINE = 'facebook'
+ _available_formats = ['highqual', 'lowqual']
+ _video_extensions = {
+ 'highqual': 'mp4',
+ 'lowqual': 'mp4',
+ }
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(FacebookIE._VALID_URL, url) is not None)
+
+ def _reporter(self, message):
+ """Add header and report message."""
+ self._downloader.to_screen(u'[facebook] %s' % message)
+
+ def report_login(self):
+ """Report attempt to log in."""
+ self._reporter(u'Logging in')
+
+ def report_video_webpage_download(self, video_id):
+ """Report attempt to download video webpage."""
+ self._reporter(u'%s: Downloading video webpage' % video_id)
+
+ def report_information_extraction(self, video_id):
+ """Report attempt to extract video information."""
+ self._reporter(u'%s: Extracting video information' % video_id)
+
+ def _parse_page(self, video_webpage):
+ """Extract video information from page"""
+ # General data
+ data = {'title': r'class="video_title datawrap">(.*?)',
+ 'description': r'(.*?)
',
+ 'owner': r'\("video_owner_name", "(.*?)"\)',
+ 'upload_date': r'data-date="(.*?)"',
+ 'thumbnail': r'\("thumb_url", "(?P.*?)"\)',
+ }
+ video_info = {}
+ for piece in data.keys():
+ mobj = re.search(data[piece], video_webpage)
+ if mobj is not None:
+ video_info[piece] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape"))
+
+ # Video urls
+ video_urls = {}
+ for fmt in self._available_formats:
+ mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage)
+ if mobj is not None:
+ # URL is in a Javascript segment inside an escaped Unicode format within
+ # the generally utf-8 page
+ video_urls[fmt] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape"))
+ video_info['video_urls'] = video_urls
+
+ return video_info
+
+ def _real_initialize(self):
+ if self._downloader is None:
+ return
+
+ useremail = 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:
+ useremail = 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:
+ useremail = 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
+
+ if useremail is None:
+ return
+
+ # Log in
+ login_form = {
+ 'email': useremail,
+ 'pass': password,
+ 'login': 'Log+In'
+ }
+ request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form))
+ try:
+ self.report_login()
+ login_results = urllib2.urlopen(request).read()
+ if re.search(r'