Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-09 11:57:17 +08:00
Code Issues Releases Wiki Activity

Merge remote branch 'rg3/master' into ytuser-infoextractor

Browse Source 
Conflicts:
	youtube-dl
This commit is contained in:
Paweł Paprota 2011-01-26 19:27:03 +01:00
commit 6513cc1739
1 changed files with 191 additions and 86 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

277
youtube-dl
View File

@ -4,9 +4,12 @@
# Author: Danny Colligan # Author: Danny Colligan
# Author: Benjamin Johnson # Author: Benjamin Johnson
# Author: Vasyl' Vavrychuk # Author: Vasyl' Vavrychuk
# Author: Witold Baryluk
# License: Public domain code # License: Public domain code
import cookielib import cookielib
import ctypes
import datetime import datetime
import gzip
import htmlentitydefs import htmlentitydefs
import httplib import httplib
import locale import locale
@ -17,11 +20,13 @@ import os.path
import re import re
import socket import socket
import string import string
import StringIO
import subprocess import subprocess
import sys import sys
import time import time
import urllib import urllib
import urllib2 import urllib2
import zlib
# parse_qs was moved from the cgi module to the urlparse module recently. # parse_qs was moved from the cgi module to the urlparse module recently.
try: try:
@ -57,7 +62,7 @@ def preferredencoding():
def htmlentity_transform(matchobj): def htmlentity_transform(matchobj):
"""Transforms an HTML entity to a Unicode character. """Transforms an HTML entity to a Unicode character.
This function receives a match object and is intended to be used with This function receives a match object and is intended to be used with
the re.sub() function. the re.sub() function.
""" """
@ -114,7 +119,7 @@ def sanitize_open(filename, open_mode):
class DownloadError(Exception): class DownloadError(Exception):
"""Download Error exception. """Download Error exception.
This exception may be thrown by FileDownloader objects if they are not This exception may be thrown by FileDownloader objects if they are not
configured to continue on errors. They will contain the appropriate configured to continue on errors. They will contain the appropriate
error message. error message.
@ -160,6 +165,64 @@ class ContentTooShortError(Exception):
self.downloaded = downloaded self.downloaded = downloaded
self.expected = expected self.expected = expected
class YoutubeDLHandler(urllib2.HTTPHandler):
"""Handler for HTTP requests and responses.
This class, when installed with an OpenerDirector, automatically adds
the standard headers to every HTTP request and handles gzipped and
deflated responses from web servers. If compression is to be avoided in
a particular request, the original request in the program code only has
to include the HTTP header "Youtubedl-No-Compression", which will be
removed before making the real request.
Part of this code was copied from:
http://techknack.net/python-urllib2-handlers/
Andrew Rowls, the author of that code, agreed to release it to the
public domain.
"""
@staticmethod
def deflate(data):
try:
return zlib.decompress(data, -zlib.MAX_WBITS)
except zlib.error:
return zlib.decompress(data)
@staticmethod
def addinfourl_wrapper(stream, headers, url, code):
if hasattr(urllib2.addinfourl, 'getcode'):
return urllib2.addinfourl(stream, headers, url, code)
ret = urllib2.addinfourl(stream, headers, url)
ret.code = code
return ret
def http_request(self, req):
for h in std_headers:
if h in req.headers:
del req.headers[h]
req.add_header(h, std_headers[h])
if 'Youtubedl-no-compression' in req.headers:
if 'Accept-encoding' in req.headers:
del req.headers['Accept-encoding']
del req.headers['Youtubedl-no-compression']
return req
def http_response(self, req, resp):
old_resp = resp
# gzip
if resp.headers.get('Content-encoding', '') == 'gzip':
gz = gzip.GzipFile(fileobj=StringIO.StringIO(resp.read()), mode='r')
resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
# deflate
if resp.headers.get('Content-encoding', '') == 'deflate':
gz = StringIO.StringIO(self.deflate(resp.read()))
resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
return resp
class FileDownloader(object): class FileDownloader(object):
"""File Downloader class. """File Downloader class.
@ -208,6 +271,8 @@ class FileDownloader(object):
playliststart: Playlist item to start at. playliststart: Playlist item to start at.
playlistend: Playlist item to end at. playlistend: Playlist item to end at.
logtostderr: Log messages to stderr instead of stdout. logtostderr: Log messages to stderr instead of stdout.
consoletitle: Display progress in console window's titlebar.
nopart: Do not use temporary .part files.
""" """
params = None params = None
@ -225,7 +290,7 @@ class FileDownloader(object):
self._num_downloads = 0 self._num_downloads = 0
self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
self.params = params self.params = params
@staticmethod @staticmethod
def pmkdir(filename): def pmkdir(filename):
"""Create directory components in filename. Similar to Unix "mkdir -p".""" """Create directory components in filename. Similar to Unix "mkdir -p"."""
@ -235,14 +300,7 @@ class FileDownloader(object):
for dir in aggregate: for dir in aggregate:
if not os.path.exists(dir): if not os.path.exists(dir):
os.mkdir(dir) os.mkdir(dir)
@staticmethod
def temp_name(filename):
"""Returns a temporary filename for the given filename."""
if filename == u'-' or (os.path.exists(filename) and not os.path.isfile(filename)):
return filename
return filename + u'.part'
@staticmethod @staticmethod
def format_bytes(bytes): def format_bytes(bytes):
if bytes is None: if bytes is None:
@ -311,12 +369,12 @@ class FileDownloader(object):
"""Add an InfoExtractor object to the end of the list.""" """Add an InfoExtractor object to the end of the list."""
self._ies.append(ie) self._ies.append(ie)
ie.set_downloader(self) ie.set_downloader(self)
def add_post_processor(self, pp): def add_post_processor(self, pp):
"""Add a PostProcessor object to the end of the chain.""" """Add a PostProcessor object to the end of the chain."""
self._pps.append(pp) self._pps.append(pp)
pp.set_downloader(self) pp.set_downloader(self)
def to_screen(self, message, skip_eol=False, ignore_encoding_errors=False): def to_screen(self, message, skip_eol=False, ignore_encoding_errors=False):
"""Print message to stdout if not in quiet mode.""" """Print message to stdout if not in quiet mode."""
try: try:
@ -327,11 +385,22 @@ class FileDownloader(object):
except (UnicodeEncodeError), err: except (UnicodeEncodeError), err:
if not ignore_encoding_errors: if not ignore_encoding_errors:
raise raise
def to_stderr(self, message): def to_stderr(self, message):
"""Print message to stderr.""" """Print message to stderr."""
print >>sys.stderr, message.encode(preferredencoding()) print >>sys.stderr, message.encode(preferredencoding())
def to_cons_title(self, message):
"""Set console/terminal window title to message."""
if not self.params.get('consoletitle', False):
return
if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
# c_wchar_p() might not be necessary if `message` is
# already of type unicode()
ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
elif 'TERM' in os.environ:
sys.stderr.write('\033]0;%s\007' % message.encode(preferredencoding()))
def fixed_template(self): def fixed_template(self):
"""Checks if the output template is fixed.""" """Checks if the output template is fixed."""
return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None) return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None)
@ -361,7 +430,19 @@ class FileDownloader(object):
speed = float(byte_counter) / elapsed speed = float(byte_counter) / elapsed
if speed > rate_limit: if speed > rate_limit:
time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
def temp_name(self, filename):
"""Returns a temporary filename for the given filename."""
if self.params.get('nopart', False) or filename == u'-' or \
(os.path.exists(filename) and not os.path.isfile(filename)):
return filename
return filename + u'.part'
def undo_temp_name(self, filename):
if filename.endswith(u'.part'):
return filename[:-len(u'.part')]
return filename
def try_rename(self, old_filename, new_filename): def try_rename(self, old_filename, new_filename):
try: try:
if old_filename == new_filename: if old_filename == new_filename:
@ -373,40 +454,42 @@ class FileDownloader(object):
def report_destination(self, filename): def report_destination(self, filename):
"""Report destination filename.""" """Report destination filename."""
self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True) self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
def report_progress(self, percent_str, data_len_str, speed_str, eta_str): def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
"""Report download progress.""" """Report download progress."""
if self.params.get('noprogress', False): if self.params.get('noprogress', False):
return return
self.to_screen(u'\r[download] %s of %s at %s ETA %s' % self.to_screen(u'\r[download] %s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True) (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' %
(percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip()))
def report_resuming_byte(self, resume_len): def report_resuming_byte(self, resume_len):
"""Report attempt to resume at given byte.""" """Report attempt to resume at given byte."""
self.to_screen(u'[download] Resuming download at byte %s' % resume_len) self.to_screen(u'[download] Resuming download at byte %s' % resume_len)
def report_retry(self, count, retries): def report_retry(self, count, retries):
"""Report retry in case of HTTP error 5xx""" """Report retry in case of HTTP error 5xx"""
self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries)) self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
def report_file_already_downloaded(self, file_name): def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded.""" """Report file has already been fully downloaded."""
try: try:
self.to_screen(u'[download] %s has already been downloaded' % file_name) self.to_screen(u'[download] %s has already been downloaded' % file_name)
except (UnicodeEncodeError), err: except (UnicodeEncodeError), err:
self.to_screen(u'[download] The file has already been downloaded') self.to_screen(u'[download] The file has already been downloaded')
def report_unable_to_resume(self): def report_unable_to_resume(self):
"""Report it was impossible to resume download.""" """Report it was impossible to resume download."""
self.to_screen(u'[download] Unable to resume') self.to_screen(u'[download] Unable to resume')
def report_finish(self): def report_finish(self):
"""Report download finished.""" """Report download finished."""
if self.params.get('noprogress', False): if self.params.get('noprogress', False):
self.to_screen(u'[download] Download completed') self.to_screen(u'[download] Download completed')
else: else:
self.to_screen(u'') self.to_screen(u'')
def increment_downloads(self): def increment_downloads(self):
"""Increment the ordinal that assigns a number to each file.""" """Increment the ordinal that assigns a number to each file."""
self._num_downloads += 1 self._num_downloads += 1
@ -426,7 +509,7 @@ class FileDownloader(object):
print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace') print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
return return
try: try:
template_dict = dict(info_dict) template_dict = dict(info_dict)
template_dict['epoch'] = unicode(long(time.time())) template_dict['epoch'] = unicode(long(time.time()))
@ -497,7 +580,7 @@ class FileDownloader(object):
info = pp.run(info) info = pp.run(info)
if info is None: if info is None:
break break
def _download_with_rtmpdump(self, filename, url, player_url): def _download_with_rtmpdump(self, filename, url, player_url):
self.report_destination(filename) self.report_destination(filename)
tmpfilename = self.temp_name(filename) tmpfilename = self.temp_name(filename)
@ -532,7 +615,7 @@ class FileDownloader(object):
def _do_download(self, filename, url, player_url): def _do_download(self, filename, url, player_url):
# Check file already present # Check file already present
if self.params.get('continuedl', False) and os.path.isfile(filename): if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False):
self.report_file_already_downloaded(filename) self.report_file_already_downloaded(filename)
return True return True
@ -543,8 +626,11 @@ class FileDownloader(object):
tmpfilename = self.temp_name(filename) tmpfilename = self.temp_name(filename)
stream = None stream = None
open_mode = 'wb' open_mode = 'wb'
basic_request = urllib2.Request(url, None, std_headers)
request = urllib2.Request(url, None, std_headers) # Do not include the Accept-Encoding header
headers = {'Youtubedl-no-compression': 'True'}
basic_request = urllib2.Request(url, None, headers)
request = urllib2.Request(url, None, headers)
# Establish possible resume length # Establish possible resume length
if os.path.isfile(tmpfilename): if os.path.isfile(tmpfilename):
@ -626,6 +712,7 @@ class FileDownloader(object):
if stream is None: if stream is None:
try: try:
(stream, tmpfilename) = sanitize_open(tmpfilename, open_mode) (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
filename = self.undo_temp_name(tmpfilename)
self.report_destination(filename) self.report_destination(filename)
except (OSError, IOError), err: except (OSError, IOError), err:
self.trouble(u'ERROR: unable to open for writing: %s' % str(err)) self.trouble(u'ERROR: unable to open for writing: %s' % str(err))
@ -715,7 +802,7 @@ class InfoExtractor(object):
def set_downloader(self, downloader): def set_downloader(self, downloader):
"""Sets the downloader for this IE.""" """Sets the downloader for this IE."""
self._downloader = downloader self._downloader = downloader
def _real_initialize(self): def _real_initialize(self):
"""Real initialization process. Redefine in subclasses.""" """Real initialization process. Redefine in subclasses."""
pass pass
@ -727,7 +814,7 @@ class InfoExtractor(object):
class YoutubeIE(InfoExtractor): class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com.""" """Information extractor for youtube.com."""
_VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$' _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
_LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' _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' _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' _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
@ -756,31 +843,31 @@ class YoutubeIE(InfoExtractor):
def report_login(self): def report_login(self):
"""Report attempt to log in.""" """Report attempt to log in."""
self._downloader.to_screen(u'[youtube] Logging in') self._downloader.to_screen(u'[youtube] Logging in')
def report_age_confirmation(self): def report_age_confirmation(self):
"""Report attempt to confirm age.""" """Report attempt to confirm age."""
self._downloader.to_screen(u'[youtube] Confirming age') self._downloader.to_screen(u'[youtube] Confirming age')
def report_video_webpage_download(self, video_id): def report_video_webpage_download(self, video_id):
"""Report attempt to download video webpage.""" """Report attempt to download video webpage."""
self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id) self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)
def report_video_info_webpage_download(self, video_id): def report_video_info_webpage_download(self, video_id):
"""Report attempt to download video info webpage.""" """Report attempt to download video info webpage."""
self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id) self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
def report_information_extraction(self, video_id): def report_information_extraction(self, video_id):
"""Report attempt to extract video information.""" """Report attempt to extract video information."""
self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id) self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
def report_unavailable_format(self, video_id, format): def report_unavailable_format(self, video_id, format):
"""Report extracted video URL.""" """Report extracted video URL."""
self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format)) self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
def report_rtmp_download(self): def report_rtmp_download(self):
"""Indicate the download will use the RTMP protocol.""" """Indicate the download will use the RTMP protocol."""
self._downloader.to_screen(u'[youtube] RTMP download detected') self._downloader.to_screen(u'[youtube] RTMP download detected')
def _real_initialize(self): def _real_initialize(self):
if self._downloader is None: if self._downloader is None:
return return
@ -806,7 +893,7 @@ class YoutubeIE(InfoExtractor):
return return
# Set language # Set language
request = urllib2.Request(self._LANG_URL, None, std_headers) request = urllib2.Request(self._LANG_URL)
try: try:
self.report_lang() self.report_lang()
urllib2.urlopen(request).read() urllib2.urlopen(request).read()
@ -826,7 +913,7 @@ class YoutubeIE(InfoExtractor):
'username': username, 'username': username,
'password': password, 'password': password,
} }
request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers) request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form))
try: try:
self.report_login() self.report_login()
login_results = urllib2.urlopen(request).read() login_results = urllib2.urlopen(request).read()
@ -836,13 +923,13 @@ class YoutubeIE(InfoExtractor):
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
return return
# Confirm age # Confirm age
age_form = { age_form = {
'next_url': '/', 'next_url': '/',
'action_confirm': 'Confirm', 'action_confirm': 'Confirm',
} }
request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers) request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form))
try: try:
self.report_age_confirmation() self.report_age_confirmation()
age_results = urllib2.urlopen(request).read() age_results = urllib2.urlopen(request).read()
@ -860,7 +947,7 @@ class YoutubeIE(InfoExtractor):
# Get video webpage # Get video webpage
self.report_video_webpage_download(video_id) 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, None, std_headers) request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
try: try:
video_webpage = urllib2.urlopen(request).read() video_webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@ -879,7 +966,7 @@ class YoutubeIE(InfoExtractor):
for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: 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_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
% (video_id, el_type)) % (video_id, el_type))
request = urllib2.Request(video_info_url, None, std_headers) request = urllib2.Request(video_info_url)
try: try:
video_info_webpage = urllib2.urlopen(request).read() video_info_webpage = urllib2.urlopen(request).read()
video_info = parse_qs(video_info_webpage) video_info = parse_qs(video_info_webpage)
@ -1002,7 +1089,7 @@ class YoutubeIE(InfoExtractor):
'player_url': player_url, 'player_url': player_url,
}) })
except UnavailableVideoError, err: except UnavailableVideoError, err:
self._downloader.trouble(u'ERROR: unable to download video') self._downloader.trouble(u'\nERROR: unable to download video')
class MetacafeIE(InfoExtractor): class MetacafeIE(InfoExtractor):
@ -1028,18 +1115,18 @@ class MetacafeIE(InfoExtractor):
def report_age_confirmation(self): def report_age_confirmation(self):
"""Report attempt to confirm age.""" """Report attempt to confirm age."""
self._downloader.to_screen(u'[metacafe] Confirming age') self._downloader.to_screen(u'[metacafe] Confirming age')
def report_download_webpage(self, video_id): def report_download_webpage(self, video_id):
"""Report webpage download.""" """Report webpage download."""
self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id) self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id): def report_extraction(self, video_id):
"""Report information extraction.""" """Report information extraction."""
self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id) self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id)
def _real_initialize(self): def _real_initialize(self):
# Retrieve disclaimer # Retrieve disclaimer
request = urllib2.Request(self._DISCLAIMER, None, std_headers) request = urllib2.Request(self._DISCLAIMER)
try: try:
self.report_disclaimer() self.report_disclaimer()
disclaimer = urllib2.urlopen(request).read() disclaimer = urllib2.urlopen(request).read()
@ -1052,14 +1139,14 @@ class MetacafeIE(InfoExtractor):
'filters': '0', 'filters': '0',
'submit': "Continue - I'm over 18", 'submit': "Continue - I'm over 18",
} }
request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers) request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form))
try: try:
self.report_age_confirmation() self.report_age_confirmation()
disclaimer = urllib2.urlopen(request).read() disclaimer = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
return return
def _real_extract(self, url): def _real_extract(self, url):
# Extract id and simplified title from URL # Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -1095,7 +1182,7 @@ class MetacafeIE(InfoExtractor):
if mobj is not None: if mobj is not None:
mediaURL = urllib.unquote(mobj.group(1)) mediaURL = urllib.unquote(mobj.group(1))
video_extension = mediaURL[-3:] video_extension = mediaURL[-3:]
# Extract gdaKey if available # Extract gdaKey if available
mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
if mobj is None: if mobj is None:
@ -1147,7 +1234,7 @@ class MetacafeIE(InfoExtractor):
'player_url': None, 'player_url': None,
}) })
except UnavailableVideoError: except UnavailableVideoError:
self._downloader.trouble(u'ERROR: unable to download video') self._downloader.trouble(u'\nERROR: unable to download video')
class DailymotionIE(InfoExtractor): class DailymotionIE(InfoExtractor):
@ -1165,7 +1252,7 @@ class DailymotionIE(InfoExtractor):
def report_download_webpage(self, video_id): def report_download_webpage(self, video_id):
"""Report webpage download.""" """Report webpage download."""
self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id) self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id): def report_extraction(self, video_id):
"""Report information extraction.""" """Report information extraction."""
self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
@ -1216,7 +1303,7 @@ class DailymotionIE(InfoExtractor):
video_title = mobj.group(1).decode('utf-8') video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title) video_title = sanitize_title(video_title)
mobj = re.search(r'(?im)<div class="dmco_html owner">.*?<a class="name" href="/.+?">(.+?)</a>', webpage) mobj = re.search(r'(?im)<Attribute name="owner">(.+?)</Attribute>', webpage)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname') self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return return
@ -1236,7 +1323,7 @@ class DailymotionIE(InfoExtractor):
'player_url': None, 'player_url': None,
}) })
except UnavailableVideoError: except UnavailableVideoError:
self._downloader.trouble(u'ERROR: unable to download video') self._downloader.trouble(u'\nERROR: unable to download video')
class GoogleIE(InfoExtractor): class GoogleIE(InfoExtractor):
"""Information extractor for video.google.com.""" """Information extractor for video.google.com."""
@ -1346,7 +1433,7 @@ class GoogleIE(InfoExtractor):
'player_url': None, 'player_url': None,
}) })
except UnavailableVideoError: except UnavailableVideoError:
self._downloader.trouble(u'ERROR: unable to download video') self._downloader.trouble(u'\nERROR: unable to download video')
class PhotobucketIE(InfoExtractor): class PhotobucketIE(InfoExtractor):
@ -1428,7 +1515,7 @@ class PhotobucketIE(InfoExtractor):
'player_url': None, 'player_url': None,
}) })
except UnavailableVideoError: except UnavailableVideoError:
self._downloader.trouble(u'ERROR: unable to download video') self._downloader.trouble(u'\nERROR: unable to download video')
class YahooIE(InfoExtractor): class YahooIE(InfoExtractor):
@ -1586,7 +1673,7 @@ class YahooIE(InfoExtractor):
'player_url': None, 'player_url': None,
}) })
except UnavailableVideoError: except UnavailableVideoError:
self._downloader.trouble(u'ERROR: unable to download video') self._downloader.trouble(u'\nERROR: unable to download video')
class GenericIE(InfoExtractor): class GenericIE(InfoExtractor):
@ -1687,7 +1774,7 @@ class GenericIE(InfoExtractor):
'player_url': None, 'player_url': None,
}) })
except UnavailableVideoError, err: except UnavailableVideoError, err:
self._downloader.trouble(u'ERROR: unable to download video') self._downloader.trouble(u'\nERROR: unable to download video')
class YoutubeSearchIE(InfoExtractor): class YoutubeSearchIE(InfoExtractor):
@ -1702,7 +1789,7 @@ class YoutubeSearchIE(InfoExtractor):
def __init__(self, youtube_ie, downloader=None): def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
self._youtube_ie = youtube_ie self._youtube_ie = youtube_ie
@staticmethod @staticmethod
def suitable(url): def suitable(url):
return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None) return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)
@ -1714,7 +1801,7 @@ class YoutubeSearchIE(InfoExtractor):
def _real_initialize(self): def _real_initialize(self):
self._youtube_ie.initialize() self._youtube_ie.initialize()
def _real_extract(self, query): def _real_extract(self, query):
mobj = re.match(self._VALID_QUERY, query) mobj = re.match(self._VALID_QUERY, query)
if mobj is None: if mobj is None:
@ -1755,7 +1842,7 @@ class YoutubeSearchIE(InfoExtractor):
while True: while True:
self.report_download_page(query, pagenum) self.report_download_page(query, pagenum)
result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
request = urllib2.Request(result_url, None, std_headers) request = urllib2.Request(result_url)
try: try:
page = urllib2.urlopen(request).read() page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@ -1793,7 +1880,7 @@ class GoogleSearchIE(InfoExtractor):
def __init__(self, google_ie, downloader=None): def __init__(self, google_ie, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
self._google_ie = google_ie self._google_ie = google_ie
@staticmethod @staticmethod
def suitable(url): def suitable(url):
return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None) return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None)
@ -1805,7 +1892,7 @@ class GoogleSearchIE(InfoExtractor):
def _real_initialize(self): def _real_initialize(self):
self._google_ie.initialize() self._google_ie.initialize()
def _real_extract(self, query): def _real_extract(self, query):
mobj = re.match(self._VALID_QUERY, query) mobj = re.match(self._VALID_QUERY, query)
if mobj is None: if mobj is None:
@ -1846,7 +1933,7 @@ class GoogleSearchIE(InfoExtractor):
while True: while True:
self.report_download_page(query, pagenum) self.report_download_page(query, pagenum)
result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
request = urllib2.Request(result_url, None, std_headers) request = urllib2.Request(result_url)
try: try:
page = urllib2.urlopen(request).read() page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@ -1884,7 +1971,7 @@ class YahooSearchIE(InfoExtractor):
def __init__(self, yahoo_ie, downloader=None): def __init__(self, yahoo_ie, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
self._yahoo_ie = yahoo_ie self._yahoo_ie = yahoo_ie
@staticmethod @staticmethod
def suitable(url): def suitable(url):
return (re.match(YahooSearchIE._VALID_QUERY, url) is not None) return (re.match(YahooSearchIE._VALID_QUERY, url) is not None)
@ -1896,7 +1983,7 @@ class YahooSearchIE(InfoExtractor):
def _real_initialize(self): def _real_initialize(self):
self._yahoo_ie.initialize() self._yahoo_ie.initialize()
def _real_extract(self, query): def _real_extract(self, query):
mobj = re.match(self._VALID_QUERY, query) mobj = re.match(self._VALID_QUERY, query)
if mobj is None: if mobj is None:
@ -1937,7 +2024,7 @@ class YahooSearchIE(InfoExtractor):
while True: while True:
self.report_download_page(query, pagenum) self.report_download_page(query, pagenum)
result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
request = urllib2.Request(result_url, None, std_headers) request = urllib2.Request(result_url)
try: try:
page = urllib2.urlopen(request).read() page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@ -1966,7 +2053,7 @@ class YahooSearchIE(InfoExtractor):
class YoutubePlaylistIE(InfoExtractor): class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists.""" """Information Extractor for YouTube playlists."""
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/)([^&]+).*' _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' _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&' _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>' _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
@ -1975,7 +2062,7 @@ class YoutubePlaylistIE(InfoExtractor):
def __init__(self, youtube_ie, downloader=None): def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
self._youtube_ie = youtube_ie self._youtube_ie = youtube_ie
@staticmethod @staticmethod
def suitable(url): def suitable(url):
return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None) return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None)
@ -1986,7 +2073,7 @@ class YoutubePlaylistIE(InfoExtractor):
def _real_initialize(self): def _real_initialize(self):
self._youtube_ie.initialize() self._youtube_ie.initialize()
def _real_extract(self, url): def _real_extract(self, url):
# Extract playlist id # Extract playlist id
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -2001,7 +2088,7 @@ class YoutubePlaylistIE(InfoExtractor):
while True: while True:
self.report_download_page(playlist_id, pagenum) self.report_download_page(playlist_id, pagenum)
request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), None, std_headers) request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum))
try: try:
page = urllib2.urlopen(request).read() page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@ -2040,7 +2127,7 @@ class YoutubeUserIE(InfoExtractor):
def __init__(self, youtube_ie, downloader=None): def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader) InfoExtractor.__init__(self, downloader)
self._youtube_ie = youtube_ie self._youtube_ie = youtube_ie
@staticmethod @staticmethod
def suitable(url): def suitable(url):
return (re.match(YoutubeUserIE._VALID_URL, url) is not None) return (re.match(YoutubeUserIE._VALID_URL, url) is not None)
@ -2051,7 +2138,7 @@ class YoutubeUserIE(InfoExtractor):
def _real_initialize(self): def _real_initialize(self):
self._youtube_ie.initialize() self._youtube_ie.initialize()
def _real_extract(self, url): def _real_extract(self, url):
# Extract username # Extract username
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -2137,7 +2224,7 @@ class DepositFilesIE(InfoExtractor):
# Retrieve file webpage with 'Free download' button pressed # Retrieve file webpage with 'Free download' button pressed
free_download_indication = { 'gateway_result' : '1' } free_download_indication = { 'gateway_result' : '1' }
request = urllib2.Request(url, urllib.urlencode(free_download_indication), std_headers) request = urllib2.Request(url, urllib.urlencode(free_download_indication))
try: try:
self.report_download_webpage(file_id) self.report_download_webpage(file_id)
webpage = urllib2.urlopen(request).read() webpage = urllib2.urlopen(request).read()
@ -2208,7 +2295,7 @@ class PostProcessor(object):
def set_downloader(self, downloader): def set_downloader(self, downloader):
"""Sets the downloader for this PP.""" """Sets the downloader for this PP."""
self._downloader = downloader self._downloader = downloader
def run(self, information): def run(self, information):
"""Run the PostProcessor. """Run the PostProcessor.
@ -2228,7 +2315,7 @@ class PostProcessor(object):
it was called from. it was called from.
""" """
return information # by default, do nothing return information # by default, do nothing
### MAIN PROGRAM ### ### MAIN PROGRAM ###
if __name__ == '__main__': if __name__ == '__main__':
try: try:
@ -2236,20 +2323,26 @@ if __name__ == '__main__':
import getpass import getpass
import optparse import optparse
# Function to update the program file with the latest version from bitbucket.org # Function to update the program file with the latest version from the repository.
def update_self(downloader, filename): def update_self(downloader, filename):
# Note: downloader only used for options # Note: downloader only used for options
if not os.access (filename, os.W_OK): if not os.access(filename, os.W_OK):
sys.exit('ERROR: no write permissions on %s' % filename) sys.exit('ERROR: no write permissions on %s' % filename)
downloader.to_screen('Updating to latest stable version...') downloader.to_screen('Updating to latest stable version...')
latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION' try:
latest_version = urllib.urlopen(latest_url).read().strip() latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION'
prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version latest_version = urllib.urlopen(latest_url).read().strip()
newcontent = urllib.urlopen(prog_url).read() prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
stream = open(filename, 'w') newcontent = urllib.urlopen(prog_url).read()
stream.write(newcontent) except (IOError, OSError), err:
stream.close() sys.exit('ERROR: unable to download latest version')
try:
stream = open(filename, 'w')
stream.write(newcontent)
stream.close()
except (IOError, OSError), err:
sys.exit('ERROR: unable to overwrite current version')
downloader.to_screen('Updated to version %s' % latest_version) downloader.to_screen('Updated to version %s' % latest_version)
# Parse command line # Parse command line
@ -2275,6 +2368,8 @@ if __name__ == '__main__':
dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1) dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
parser.add_option('--playlist-end', parser.add_option('--playlist-end',
dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1) dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
parser.add_option('--dump-user-agent',
action='store_true', dest='dump_user_agent', help='display the current browser identification', default=False)
authentication = optparse.OptionGroup(parser, 'Authentication Options') authentication = optparse.OptionGroup(parser, 'Authentication Options')
authentication.add_option('-u', '--username', authentication.add_option('-u', '--username',
@ -2309,6 +2404,8 @@ if __name__ == '__main__':
action='store_true', dest='getdescription', help='simulate, quiet but print video description', default=False) action='store_true', dest='getdescription', help='simulate, quiet but print video description', default=False)
verbosity.add_option('--no-progress', verbosity.add_option('--no-progress',
action='store_true', dest='noprogress', help='do not print progress bar', default=False) action='store_true', dest='noprogress', help='do not print progress bar', default=False)
verbosity.add_option('--console-title',
action='store_true', dest='consoletitle', help='display progress in console titlebar', default=False)
parser.add_option_group(verbosity) parser.add_option_group(verbosity)
filesystem = optparse.OptionGroup(parser, 'Filesystem Options') filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
@ -2328,6 +2425,8 @@ if __name__ == '__main__':
action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False) action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
filesystem.add_option('--cookies', filesystem.add_option('--cookies',
dest='cookiefile', metavar='FILE', help='file to dump cookie jar to') dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
filesystem.add_option('--no-part',
action='store_true', dest='nopart', help='do not use .part files', default=False)
parser.add_option_group(filesystem) parser.add_option_group(filesystem)
(opts, args) = parser.parse_args() (opts, args) = parser.parse_args()
@ -2343,10 +2442,14 @@ if __name__ == '__main__':
except (IOError, OSError), err: except (IOError, OSError), err:
sys.exit(u'ERROR: unable to open cookie file') sys.exit(u'ERROR: unable to open cookie file')
# Dump user agent
if opts.dump_user_agent:
print std_headers['User-Agent']
sys.exit(0)
# General configuration # General configuration
cookie_processor = urllib2.HTTPCookieProcessor(jar) cookie_processor = urllib2.HTTPCookieProcessor(jar)
urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler())) urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler()))
urllib2.install_opener(urllib2.build_opener(cookie_processor))
socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words) socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
# Batch file verification # Batch file verification
@ -2445,6 +2548,8 @@ if __name__ == '__main__':
'playliststart': opts.playliststart, 'playliststart': opts.playliststart,
'playlistend': opts.playlistend, 'playlistend': opts.playlistend,
'logtostderr': opts.outtmpl == '-', 'logtostderr': opts.outtmpl == '-',
'consoletitle': opts.consoletitle,
'nopart': opts.nopart,
}) })
fd.add_info_extractor(youtube_search_ie) fd.add_info_extractor(youtube_search_ie)
fd.add_info_extractor(youtube_pl_ie) fd.add_info_extractor(youtube_pl_ie)