X-Git-Url: https://git.jankratochvil.net/?a=blobdiff_plain;f=youtube_dl%2F__init__.py;h=4c9c237d91d0086077e54d763117c508460eda75;hb=09fbc6c952ddb42ff042c2911576102dc8e78e23;hp=8fc320cbf73890aff89de3a9f93aaa823007335e;hpb=e33e3045c6d3a4e6a8489074548e392e4f748615;p=youtube-dl.git
diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py
index 8fc320c..4c9c237 100755
--- a/youtube_dl/__init__.py
+++ b/youtube_dl/__init__.py
@@ -1,7 +1,7 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
-__author__ = (
+__authors__ = (
'Ricardo Garcia Gonzalez',
'Danny Colligan',
'Benjamin Johnson',
@@ -14,10 +14,11 @@ __author__ = (
'Sören Schulze',
'Kevin Ngo',
'Ori Avtalion',
+ 'shizeeg',
)
__license__ = 'Public Domain'
-__version__ = '2011.10.19'
+__version__ = '2012.01.08b'
UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
@@ -79,8 +80,6 @@ std_headers = {
'Accept-Language': 'en-us,en;q=0.5',
}
-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):
@@ -260,14 +259,14 @@ def sanitize_open(filename, open_mode):
import msvcrt
msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
return (sys.stdout, filename)
- stream = open(filename, open_mode)
+ stream = open(_encodeFilename(filename), open_mode)
return (stream, filename)
except (IOError, OSError), err:
# In case of error, try to remove win32 forbidden chars
filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
# An exception here should be caught in the caller
- stream = open(filename, open_mode)
+ stream = open(_encodeFilename(filename), open_mode)
return (stream, filename)
@@ -280,7 +279,40 @@ def timeconvert(timestr):
return timestamp
def _simplify_title(title):
- return re.sub(ur'[^\w\d_\-]+', u'_', title)
+ expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE)
+ return expr.sub(u'_', title).strip(u'_')
+
+def _orderedSet(iterable):
+ """ Remove all duplicates from the input iterable """
+ res = []
+ for el in iterable:
+ if el not in res:
+ res.append(el)
+ return res
+
+def _unescapeHTML(s):
+ """
+ @param s a string (of type unicode)
+ """
+ assert type(s) == type(u'')
+
+ htmlParser = HTMLParser.HTMLParser()
+ return htmlParser.unescape(s)
+
+def _encodeFilename(s):
+ """
+ @param s The name of the file (of type unicode)
+ """
+
+ assert type(s) == type(u'')
+
+ if sys.platform == 'win32' and sys.getwindowsversion().major >= 5:
+ # Pass u'' directly to use Unicode APIs on Windows 2000 and up
+ # (Detecting Windows NT 4 is tricky because 'major >= 4' would
+ # match Windows 9x series as well. Besides, NT 4 is obsolete.)
+ return s
+ else:
+ return s.encode(sys.getfilesystemencoding(), 'ignore')
class DownloadError(Exception):
"""Download Error exception.
@@ -309,6 +341,10 @@ class PostProcessingError(Exception):
"""
pass
+class MaxDownloadsReached(Exception):
+ """ --max-downloads limit has been reached. """
+ pass
+
class UnavailableVideoError(Exception):
"""Unavailable Format exception.
@@ -542,16 +578,17 @@ class FileDownloader(object):
self._pps.append(pp)
pp.set_downloader(self)
- def to_screen(self, message, skip_eol=False, ignore_encoding_errors=False):
+ def to_screen(self, message, skip_eol=False):
"""Print message to stdout if not in quiet mode."""
- try:
- if not self.params.get('quiet', False):
- terminator = [u'\n', u''][skip_eol]
- print >>self._screen_file, (u'%s%s' % (message, terminator)).encode(preferredencoding()),
+ assert type(message) == type(u'')
+ if not self.params.get('quiet', False):
+ terminator = [u'\n', u''][skip_eol]
+ output = message + terminator
+
+ if 'b' not in self._screen_file.mode or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr
+ output = output.encode(preferredencoding(), 'ignore')
+ self._screen_file.write(output)
self._screen_file.flush()
- except (UnicodeEncodeError), err:
- if not ignore_encoding_errors:
- raise
def to_stderr(self, message):
"""Print message to stderr."""
@@ -601,7 +638,7 @@ class FileDownloader(object):
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)):
+ (os.path.exists(_encodeFilename(filename)) and not os.path.isfile(_encodeFilename(filename))):
return filename
return filename + u'.part'
@@ -614,7 +651,7 @@ class FileDownloader(object):
try:
if old_filename == new_filename:
return
- os.rename(old_filename, new_filename)
+ os.rename(_encodeFilename(old_filename), _encodeFilename(new_filename))
except (IOError, OSError), err:
self.trouble(u'ERROR: unable to rename file')
@@ -622,7 +659,7 @@ class FileDownloader(object):
"""Try to set the last-modified time of the given file."""
if last_modified_hdr is None:
return
- if not os.path.isfile(filename):
+ if not os.path.isfile(_encodeFilename(filename)):
return
timestr = last_modified_hdr
if timestr is None:
@@ -638,15 +675,15 @@ class FileDownloader(object):
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)
+ self.to_screen(u'[info] Writing video description to: ' + descfn)
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)
+ self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn)
def report_destination(self, filename):
"""Report destination filename."""
- self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
+ self.to_screen(u'[download] Destination: ' + filename)
def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
"""Report download progress."""
@@ -699,8 +736,31 @@ class FileDownloader(object):
self.trouble(u'ERROR: invalid system charset or erroneous output template')
return None
+ def _match_entry(self, info_dict):
+ """ Returns None iff the file should be downloaded """
+
+ title = info_dict['title']
+ matchtitle = self.params.get('matchtitle', False)
+ if matchtitle and not re.search(matchtitle, title, re.IGNORECASE):
+ return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"'
+ rejecttitle = self.params.get('rejecttitle', False)
+ if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE):
+ return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
+ return None
+
def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
+
+ reason = self._match_entry(info_dict)
+ if reason is not None:
+ self.to_screen(u'[download] ' + reason)
+ return
+
+ max_downloads = self.params.get('max_downloads')
+ if max_downloads is not None:
+ if self._num_downloads > int(max_downloads):
+ raise MaxDownloadsReached()
+
filename = self.prepare_filename(info_dict)
# Forced printings
@@ -724,23 +784,9 @@ class FileDownloader(object):
if filename is None:
return
- matchtitle=self.params.get('matchtitle',False)
- rejecttitle=self.params.get('rejecttitle',False)
- title=info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
- if matchtitle and not re.search(matchtitle, title, re.IGNORECASE):
- self.to_screen(u'[download] "%s" title did not match pattern "%s"' % (title, matchtitle))
- return
- if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE):
- self.to_screen(u'[download] "%s" title matched reject pattern "%s"' % (title, rejecttitle))
- return
-
- if self.params.get('nooverwrites', False) and os.path.exists(filename):
- self.to_stderr(u'WARNING: file exists and will be skipped')
- return
-
try:
- dn = os.path.dirname(filename)
- if dn != '' and not os.path.exists(dn):
+ dn = os.path.dirname(_encodeFilename(filename))
+ if dn != '' and not os.path.exists(dn): # dn is already encoded
os.makedirs(dn)
except (OSError, IOError), err:
self.trouble(u'ERROR: unable to create directory ' + unicode(err))
@@ -748,9 +794,9 @@ class FileDownloader(object):
if self.params.get('writedescription', False):
try:
- descfn = filename + '.description'
+ descfn = filename + u'.description'
self.report_writedescription(descfn)
- descfile = open(descfn, 'wb')
+ descfile = open(_encodeFilename(descfn), 'wb')
try:
descfile.write(info_dict['description'].encode('utf-8'))
finally:
@@ -760,7 +806,7 @@ class FileDownloader(object):
return
if self.params.get('writeinfojson', False):
- infofn = filename + '.info.json'
+ infofn = filename + u'.info.json'
self.report_writeinfojson(infofn)
try:
json.dump
@@ -768,7 +814,7 @@ 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:
- infof = open(infofn, 'wb')
+ infof = open(_encodeFilename(infofn), 'wb')
try:
json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',))
json.dump(json_info_dict, infof)
@@ -779,16 +825,19 @@ class FileDownloader(object):
return
if not self.params.get('skip_download', False):
- try:
- success = self._do_download(filename, info_dict)
- except (OSError, IOError), err:
- raise UnavailableVideoError
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.trouble(u'ERROR: unable to download video data: %s' % str(err))
- return
- except (ContentTooShortError, ), err:
- self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
- return
+ if self.params.get('nooverwrites', False) and os.path.exists(_encodeFilename(filename)):
+ success = True
+ else:
+ try:
+ success = self._do_download(filename, info_dict)
+ except (OSError, IOError), err:
+ raise UnavailableVideoError
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self.trouble(u'ERROR: unable to download video data: %s' % str(err))
+ return
+ except (ContentTooShortError, ), err:
+ self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
+ return
if success:
try:
@@ -849,11 +898,11 @@ class FileDownloader(object):
basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
while retval == 2 or retval == 1:
- prevsize = os.path.getsize(tmpfilename)
+ prevsize = os.path.getsize(_encodeFilename(tmpfilename))
self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
time.sleep(5.0) # This seems to be needed
retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
- cursize = os.path.getsize(tmpfilename)
+ cursize = os.path.getsize(_encodeFilename(tmpfilename))
if prevsize == cursize and retval == 1:
break
# Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
@@ -862,7 +911,7 @@ class FileDownloader(object):
retval = 0
break
if retval == 0:
- self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename))
+ self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(_encodeFilename(tmpfilename)))
self.try_rename(tmpfilename, filename)
return True
else:
@@ -874,7 +923,7 @@ class FileDownloader(object):
player_url = info_dict.get('player_url', None)
# Check file already present
- if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False):
+ if self.params.get('continuedl', False) and os.path.isfile(_encodeFilename(filename)) and not self.params.get('nopart', False):
self.report_file_already_downloaded(filename)
return True
@@ -891,8 +940,8 @@ class FileDownloader(object):
request = urllib2.Request(url, None, headers)
# Establish possible resume length
- if os.path.isfile(tmpfilename):
- resume_len = os.path.getsize(tmpfilename)
+ if os.path.isfile(_encodeFilename(tmpfilename)):
+ resume_len = os.path.getsize(_encodeFilename(tmpfilename))
else:
resume_len = 0
@@ -1096,6 +1145,7 @@ class YoutubeIE(InfoExtractor):
_NETRC_MACHINE = 'youtube'
# Listed in order of quality
_available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
+ _available_formats_prefer_free = ['38', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13']
_video_extensions = {
'13': '3gp',
'17': 'mp4',
@@ -1293,8 +1343,7 @@ class YoutubeIE(InfoExtractor):
video_title = sanitize_title(video_title)
# simplified title
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
- simple_title = simple_title.strip(ur'_')
+ simple_title = _simplify_title(video_title)
# thumbnail image
if 'thumbnail_url' not in video_info:
@@ -1346,10 +1395,11 @@ class YoutubeIE(InfoExtractor):
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):]
+ 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 = self._available_formats
+ 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')
@@ -1575,7 +1625,6 @@ class DailymotionIE(InfoExtractor):
self._downloader.increment_downloads()
video_id = mobj.group(1)
- simple_title = mobj.group(2).decode('utf-8')
video_extension = 'flv'
# Retrieve video webpage to extract further information
@@ -1605,12 +1654,13 @@ class DailymotionIE(InfoExtractor):
video_url = mediaURL
- mobj = re.search(r'(?im)
Dailymotion\s*-\s*(.+)\s*-\s*[^<]+?', webpage)
+ mobj = re.search(r'', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract title')
return
- video_title = mobj.group(1).decode('utf-8')
+ video_title = _unescapeHTML(mobj.group('title').decode('utf-8'))
video_title = sanitize_title(video_title)
+ simple_title = _simplify_title(video_title)
mobj = re.search(r'(?im)[^<]+?]+?>([^<]+?)', webpage)
if mobj is None:
@@ -1695,7 +1745,7 @@ class GoogleIE(InfoExtractor):
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = _simplify_title(video_title)
# Extract video description
mobj = re.search(r'([^<]*)', webpage)
@@ -1794,7 +1844,7 @@ class PhotobucketIE(InfoExtractor):
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = _simplify_title(vide_title)
video_uploader = mobj.group(2).decode('utf-8')
@@ -1888,7 +1938,7 @@ class YahooIE(InfoExtractor):
self._downloader.trouble(u'ERROR: unable to extract video title')
return
video_title = mobj.group(1).decode('utf-8')
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = _simplify_title(video_title)
mobj = re.search(r'', webpage)
if mobj is None:
@@ -2016,7 +2066,7 @@ class VimeoIE(InfoExtractor):
self._downloader.trouble(u'ERROR: unable to extract video title')
return
video_title = mobj.group(1).decode('utf-8')
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = _simplify_title(video_title)
# Extract uploader
mobj = re.search(r'http://vimeo.com/(.*?)', webpage)
@@ -2160,7 +2210,7 @@ class GenericIE(InfoExtractor):
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = _simplify_title(video_title)
# video uploader is domain name
mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
@@ -2609,7 +2659,7 @@ class YoutubeUserIE(InfoExtractor):
else:
video_ids = video_ids[playliststart:playlistend]
- self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" %
+ self._downloader.to_screen(u"[youtube] user %s: Collected %d video ids (downloading %d of them)" %
(username, all_ids_count, len(video_ids)))
for video_id in video_ids:
@@ -2830,9 +2880,7 @@ class FacebookIE(InfoExtractor):
video_title = video_title.decode('utf-8')
video_title = sanitize_title(video_title)
- # simplified title
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
- simple_title = simple_title.strip(ur'_')
+ simple_title = _simplify_title(video_title)
# thumbnail image
if 'thumbnail' not in video_info:
@@ -2923,11 +2971,6 @@ class BlipTVIE(InfoExtractor):
"""Report information extraction."""
self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title))
- def _simplify_title(self, title):
- res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
- res = res.strip(ur'_')
- return res
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
@@ -2947,13 +2990,14 @@ class BlipTVIE(InfoExtractor):
if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
basename = url.split('/')[-1]
title,ext = os.path.splitext(basename)
+ title = title.decode('UTF-8')
ext = ext.replace('.', '')
self.report_direct_download(title)
info = {
'id': title,
'url': url,
'title': title,
- 'stitle': self._simplify_title(title),
+ 'stitle': _simplify_title(title),
'ext': ext,
'urlhandle': urlh
}
@@ -2987,7 +3031,7 @@ class BlipTVIE(InfoExtractor):
'uploader': data['display_name'],
'upload_date': upload_date,
'title': data['title'],
- 'stitle': self._simplify_title(data['title']),
+ 'stitle': _simplify_title(data['title']),
'ext': ext,
'format': data['media']['mimeType'],
'thumbnail': data['thumbnailUrl'],
@@ -3030,10 +3074,6 @@ class MyVideoIE(InfoExtractor):
return
video_id = mobj.group(1)
- simple_title = mobj.group(2).decode('utf-8')
- # should actually not be necessary
- simple_title = sanitize_title(simple_title)
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', simple_title)
# Get video webpage
request = urllib2.Request('http://www.myvideo.de/watch/%s' % video_id)
@@ -3060,6 +3100,8 @@ class MyVideoIE(InfoExtractor):
video_title = mobj.group(1)
video_title = sanitize_title(video_title)
+ simple_title = _simplify_title(video_title)
+
try:
self._downloader.process_info({
'id': video_id,
@@ -3093,11 +3135,6 @@ class ComedyCentralIE(InfoExtractor):
def report_player_url(self, episode_id):
self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id)
- def _simplify_title(self, title):
- res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
- res = res.strip(ur'_')
- return res
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
@@ -3106,9 +3143,9 @@ class ComedyCentralIE(InfoExtractor):
if mobj.group('shortname'):
if mobj.group('shortname') in ('tds', 'thedailyshow'):
- url = 'http://www.thedailyshow.com/full-episodes/'
+ url = u'http://www.thedailyshow.com/full-episodes/'
else:
- url = 'http://www.colbertnation.com/full-episodes/'
+ url = u'http://www.colbertnation.com/full-episodes/'
mobj = re.match(self._VALID_URL, url)
assert mobj is not None
@@ -3137,7 +3174,7 @@ class ComedyCentralIE(InfoExtractor):
return
epTitle = mobj.group('episode')
- mMovieParams = re.findall('', html)
+ mMovieParams = re.findall('(?:/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P[^&]+)(&video=(?P