From 51065d3efdbd2267e555d329808d8ca9e39bae6a Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 27 Nov 2012 20:26:56 +0100 Subject: [PATCH] Prepare strings for Python 2.5-3 transition --- test/test_utils.py | 77 ++-- youtube_dl/FileDownloader.py | 103 +++--- youtube_dl/InfoExtractors.py | 687 +++++++++++++++++------------------ youtube_dl/PostProcessor.py | 15 +- youtube_dl/__init__.py | 68 ++-- youtube_dl/__main__.py | 1 - youtube_dl/utils.py | 21 +- 7 files changed, 490 insertions(+), 482 deletions(-) diff --git a/test/test_utils.py b/test/test_utils.py index a3a23fbb4..b8fc13aef 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -1,15 +1,22 @@ -# -*- coding: utf-8 -*- - # Various small unit tests +import sys import unittest +# Allow direct execution +import os +sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + #from youtube_dl.utils import htmlentity_transform from youtube_dl.utils import timeconvert from youtube_dl.utils import sanitize_filename from youtube_dl.utils import unescapeHTML from youtube_dl.utils import orderedSet +if sys.version < (3,0): + _compat_str = lambda b: b.decode('unicode-escape') +else: + _compat_str = lambda s: s class TestUtil(unittest.TestCase): def test_timeconvert(self): @@ -17,56 +24,59 @@ class TestUtil(unittest.TestCase): self.assertTrue(timeconvert('bougrg') is None) def test_sanitize_filename(self): - self.assertEqual(sanitize_filename(u'abc'), u'abc') - self.assertEqual(sanitize_filename(u'abc_d-e'), u'abc_d-e') + self.assertEqual(sanitize_filename('abc'), 'abc') + self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e') - self.assertEqual(sanitize_filename(u'123'), u'123') + self.assertEqual(sanitize_filename('123'), '123') - self.assertEqual(u'abc_de', sanitize_filename(u'abc/de')) - self.assertFalse(u'/' in sanitize_filename(u'abc/de///')) + self.assertEqual('abc_de', sanitize_filename('abc/de')) + self.assertFalse('/' in sanitize_filename('abc/de///')) - self.assertEqual(u'abc_de', sanitize_filename(u'abc/<>\\*|de')) - self.assertEqual(u'xxx', sanitize_filename(u'xxx/<>\\*|')) - self.assertEqual(u'yes no', sanitize_filename(u'yes? no')) - self.assertEqual(u'this - that', sanitize_filename(u'this: that')) + self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de')) + self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|')) + self.assertEqual('yes no', sanitize_filename('yes? no')) + self.assertEqual('this - that', sanitize_filename('this: that')) - self.assertEqual(sanitize_filename(u'AT&T'), u'AT&T') - self.assertEqual(sanitize_filename(u'ä'), u'ä') - self.assertEqual(sanitize_filename(u'кириллица'), u'кириллица') + self.assertEqual(sanitize_filename('AT&T'), 'AT&T') + aumlaut = _compat_str('\xe4') + self.assertEqual(sanitize_filename(aumlaut), aumlaut) + tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430') + self.assertEqual(sanitize_filename(tests), tests) - forbidden = u'"\0\\/' + forbidden = '"\0\\/' for fc in forbidden: for fbc in forbidden: self.assertTrue(fbc not in sanitize_filename(fc)) def test_sanitize_filename_restricted(self): - self.assertEqual(sanitize_filename(u'abc', restricted=True), u'abc') - self.assertEqual(sanitize_filename(u'abc_d-e', restricted=True), u'abc_d-e') + self.assertEqual(sanitize_filename('abc', restricted=True), 'abc') + self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e') - self.assertEqual(sanitize_filename(u'123', restricted=True), u'123') + self.assertEqual(sanitize_filename('123', restricted=True), '123') - self.assertEqual(u'abc_de', sanitize_filename(u'abc/de', restricted=True)) - self.assertFalse(u'/' in sanitize_filename(u'abc/de///', restricted=True)) + self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True)) + self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True)) - self.assertEqual(u'abc_de', sanitize_filename(u'abc/<>\\*|de', restricted=True)) - self.assertEqual(u'xxx', sanitize_filename(u'xxx/<>\\*|', restricted=True)) - self.assertEqual(u'yes_no', sanitize_filename(u'yes? no', restricted=True)) - self.assertEqual(u'this_-_that', sanitize_filename(u'this: that', restricted=True)) + self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True)) + self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True)) + self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True)) + self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True)) - self.assertEqual(sanitize_filename(u'aäb中国的c', restricted=True), u'a_b_c') - self.assertTrue(sanitize_filename(u'ö', restricted=True) != u'') # No empty filename + tests =_compat_str('a\xe4b\u4e2d\u56fd\u7684c') + self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c') + self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '') # No empty filename - forbidden = u'"\0\\/&!: \'\t\n' + forbidden = '"\0\\/&!: \'\t\n' for fc in forbidden: for fbc in forbidden: self.assertTrue(fbc not in sanitize_filename(fc, restricted=True)) # Handle a common case more neatly - self.assertEqual(sanitize_filename(u'大声带 - Song', restricted=True), u'Song') - self.assertEqual(sanitize_filename(u'总统: Speech', restricted=True), u'Speech') + self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song') + self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech') # .. but make sure the file name is never empty - self.assertTrue(sanitize_filename(u'-', restricted=True) != u'') - self.assertTrue(sanitize_filename(u':', restricted=True) != u'') + self.assertTrue(sanitize_filename('-', restricted=True) != '') + self.assertTrue(sanitize_filename(':', restricted=True) != '') def test_ordered_set(self): self.assertEqual(orderedSet([1,1,2,3,4,4,5,6,7,3,5]), [1,2,3,4,5,6,7]) @@ -76,4 +86,7 @@ class TestUtil(unittest.TestCase): self.assertEqual(orderedSet([135,1,1,1]), [135,1]) def test_unescape_html(self): - self.assertEqual(unescapeHTML(u"%20;"), u"%20;") + self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;')) + +if __name__ == '__main__': + unittest.main() diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 5a7af2a7a..17f946e71 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -1,5 +1,4 @@ #!/usr/bin/env python -# -*- coding: utf-8 -*- import httplib import math @@ -97,7 +96,7 @@ class FileDownloader(object): self.params = params if '%(stitle)s' in self.params['outtmpl']: - self.to_stderr(u'WARNING: %(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.') + self.to_stderr(u('WARNING: %(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.')) @staticmethod def format_bytes(bytes): @@ -175,9 +174,9 @@ class FileDownloader(object): def to_screen(self, message, skip_eol=False): """Print message to stdout if not in quiet mode.""" - assert type(message) == type(u'') + assert type(message) == type(u('')) if not self.params.get('quiet', False): - terminator = [u'\n', u''][skip_eol] + 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') @@ -186,8 +185,8 @@ class FileDownloader(object): def to_stderr(self, message): """Print message to stderr.""" - assert type(message) == type(u'') - sys.stderr.write((message + u'\n').encode(preferredencoding())) + assert type(message) == type(u('')) + sys.stderr.write((message + u('\n')).encode(preferredencoding())) def to_cons_title(self, message): """Set console/terminal window title to message.""" @@ -232,14 +231,14 @@ 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 \ + if self.params.get('nopart', False) or filename == u('-') or \ (os.path.exists(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))): return filename - return filename + u'.part' + return filename + u('.part') def undo_temp_name(self, filename): - if filename.endswith(u'.part'): - return filename[:-len(u'.part')] + if filename.endswith(u('.part')): + return filename[:-len(u('.part'))] return filename def try_rename(self, old_filename, new_filename): @@ -249,7 +248,7 @@ class FileDownloader(object): os.rename(encodeFilename(old_filename), encodeFilename(new_filename)) except (IOError, OSError): _, err, _ = sys.exc_info() - self.trouble(u'ERROR: unable to rename file') + self.trouble(u('ERROR: unable to rename file')) def try_utime(self, filename, last_modified_hdr): """Try to set the last-modified time of the given file.""" @@ -271,55 +270,55 @@ 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: ' + descfn) + self.to_screen(u('[info] Writing video description to: ') + descfn) def report_writesubtitles(self, srtfn): """ Report that the subtitles file is being written """ - self.to_screen(u'[info] Writing video subtitles to: ' + srtfn) + self.to_screen(u('[info] Writing video subtitles to: ') + srtfn) def report_writeinfojson(self, infofn): """ Report that the metadata file has been written """ - self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn) + 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: ' + filename) + self.to_screen(u('[download] Destination: ') + filename) def report_progress(self, percent_str, data_len_str, speed_str, eta_str): """Report download progress.""" if self.params.get('noprogress', False): 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) - self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' % + 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): """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): """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): """Report file has already been fully downloaded.""" 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, _ = sys.exc_info() - 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): """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): """Report download finished.""" if self.params.get('noprogress', False): - self.to_screen(u'[download] Download completed') + self.to_screen(u('[download] Download completed')) else: - self.to_screen(u'') + self.to_screen(u('')) def increment_downloads(self): """Increment the ordinal that assigns a number to each file.""" @@ -330,14 +329,14 @@ class FileDownloader(object): try: template_dict = dict(info_dict) template_dict['epoch'] = int(time.time()) - template_dict['autonumber'] = u'%05d' % self._num_downloads + template_dict['autonumber'] = u('%05d') % self._num_downloads template_dict = dict((k, sanitize_filename(u(v), self.params.get('restrictfilenames'))) for k,v in template_dict.items()) filename = self.params['outtmpl'] % template_dict return filename except (ValueError, KeyError): _, err, _ = sys.exc_info() - self.trouble(u'ERROR: invalid system charset or erroneous output template') + self.trouble(u('ERROR: invalid system charset or erroneous output template')) return None def _match_entry(self, info_dict): @@ -348,12 +347,12 @@ class FileDownloader(object): if matchtitle: matchtitle = matchtitle.decode('utf8') if not re.search(matchtitle, title, re.IGNORECASE): - return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"' + return u('[download] "') + title + '" title did not match pattern "' + matchtitle + '"' rejecttitle = self.params.get('rejecttitle', False) if rejecttitle: rejecttitle = rejecttitle.decode('utf8') if re.search(rejecttitle, title, re.IGNORECASE): - return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"' + return u('"') + title + '" title matched reject pattern "' + rejecttitle + '"' return None def process_info(self, info_dict): @@ -364,7 +363,7 @@ class FileDownloader(object): reason = self._match_entry(info_dict) if reason is not None: - self.to_screen(u'[download] ' + reason) + self.to_screen(u('[download] ') + reason) return max_downloads = self.params.get('max_downloads') @@ -401,12 +400,12 @@ class FileDownloader(object): os.makedirs(dn) except (OSError, IOError): _, err, _ = sys.exc_info() - self.trouble(u'ERROR: unable to create directory ' + u(err)) + self.trouble(u('ERROR: unable to create directory ') + u(err)) return if self.params.get('writedescription', False): try: - descfn = filename + u'.description' + descfn = filename + u('.description') self.report_writedescription(descfn) descfile = open(encodeFilename(descfn), 'wb') try: @@ -414,14 +413,14 @@ class FileDownloader(object): finally: descfile.close() except (OSError, IOError): - self.trouble(u'ERROR: Cannot write description file ' + descfn) + self.trouble(u('ERROR: Cannot write description file ') + descfn) return if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']: # subtitles download errors are already managed as troubles in relevant IE # that way it will silently go on when used with unsupporting IE try: - srtfn = filename.rsplit('.', 1)[0] + u'.srt' + srtfn = filename.rsplit('.', 1)[0] + u('.srt') self.report_writesubtitles(srtfn) srtfile = open(encodeFilename(srtfn), 'wb') try: @@ -429,16 +428,16 @@ class FileDownloader(object): finally: srtfile.close() except (OSError, IOError): - self.trouble(u'ERROR: Cannot write subtitles file ' + descfn) + self.trouble(u('ERROR: Cannot write subtitles file ') + descfn) return if self.params.get('writeinfojson', False): - infofn = filename + u'.info.json' + infofn = filename + u('.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.') + 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(encodeFilename(infofn), 'wb') @@ -448,7 +447,7 @@ class FileDownloader(object): finally: infof.close() except (OSError, IOError): - self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn) + self.trouble(u('ERROR: Cannot write metadata to JSON file ') + infofn) return if not self.params.get('skip_download', False): @@ -462,11 +461,11 @@ class FileDownloader(object): raise UnavailableVideoError except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - self.trouble(u'ERROR: unable to download video data: %s' % str(err)) + self.trouble(u('ERROR: unable to download video data: %s') % str(err)) return except (ContentTooShortError, ): _, err, _ = sys.exc_info() - self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) + self.trouble(u('ERROR: content too short (expected %s bytes and served %s)') % (err.expected, err.downloaded)) return if success: @@ -474,7 +473,7 @@ class FileDownloader(object): self.post_process(filename, info_dict) except (PostProcessingError): _, err, _ = sys.exc_info() - self.trouble(u'ERROR: postprocessing: %s' % str(err)) + self.trouble(u('ERROR: postprocessing: %s') % str(err)) return def download(self, url_list): @@ -500,13 +499,13 @@ class FileDownloader(object): self.increment_downloads() self.process_info(video) except UnavailableVideoError: - self.trouble(u'\nERROR: unable to download video') + self.trouble(u('\nERROR: unable to download video')) # Suitable InfoExtractor had been found; go to next URL break if not suitable_found: - self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url) + self.trouble(u('ERROR: no suitable InfoExtractor: %s') % url) return self._download_retcode @@ -527,7 +526,7 @@ class FileDownloader(object): try: subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT) except (OSError, IOError): - self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run') + self.trouble(u('ERROR: RTMP download detected but "rtmpdump" could not be run')) return False # Download using rtmpdump. rtmpdump returns exit code 2 when @@ -541,11 +540,11 @@ class FileDownloader(object): shell_quote = lambda args: ' '.join(map(pipes.quote, args)) except ImportError: shell_quote = repr - self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(args)) + self.to_screen(u('[debug] rtmpdump command line: ') + shell_quote(args)) retval = subprocess.call(args) while retval == 2 or retval == 1: prevsize = os.path.getsize(encodeFilename(tmpfilename)) - self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True) + 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(encodeFilename(tmpfilename)) @@ -553,15 +552,15 @@ class FileDownloader(object): break # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those if prevsize == cursize and retval == 2 and cursize > 1024: - self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.') + self.to_screen(u('\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.')) retval = 0 break if retval == 0: - self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(encodeFilename(tmpfilename))) + self.to_screen(u('\r[rtmpdump] %s bytes') % os.path.getsize(encodeFilename(tmpfilename))) self.try_rename(tmpfilename, filename) return True else: - self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval) + self.trouble(u('\nERROR: rtmpdump exited with code %d') % retval) return False def _do_download(self, filename, info_dict): @@ -649,7 +648,7 @@ class FileDownloader(object): self.report_retry(count, retries) if count > retries: - self.trouble(u'ERROR: giving up after %s retries' % retries) + self.trouble(u('ERROR: giving up after %s retries') % retries) return False data_len = data.info().get('Content-length', None) @@ -677,13 +676,13 @@ class FileDownloader(object): self.report_destination(filename) except (OSError, IOError): _, err, _ = sys.exc_info() - self.trouble(u'ERROR: unable to open for writing: %s' % str(err)) + self.trouble(u('ERROR: unable to open for writing: %s') % str(err)) return False try: stream.write(data_block) except (IOError, OSError): _, err, _ = sys.exc_info() - self.trouble(u'\nERROR: unable to write data: %s' % str(err)) + self.trouble(u('\nERROR: unable to write data: %s') % str(err)) return False if not self.params.get('noresizebuffer', False): block_size = self.best_block_size(after - before, len(data_block)) @@ -701,7 +700,7 @@ class FileDownloader(object): self.slow_down(start, byte_counter - resume_len) if stream is None: - self.trouble(u'\nERROR: Did not get any data blocks') + self.trouble(u('\nERROR: Did not get any data blocks')) return False stream.close() self.report_finish() diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 5fa2be342..2f9096057 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -1,5 +1,4 @@ #!/usr/bin/env python -# -*- coding: utf-8 -*- import datetime import HTMLParser @@ -153,7 +152,7 @@ class YoutubeIE(InfoExtractor): '45': '720x1280', '46': '1080x1920', } - IE_NAME = u'youtube' + IE_NAME = u('youtube') def suitable(self, url): """Receives a URL and returns True if suitable for this IE.""" @@ -161,39 +160,39 @@ class YoutubeIE(InfoExtractor): def report_lang(self): """Report attempt to set language.""" - self._downloader.to_screen(u'[youtube] Setting 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') + 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') + 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) + 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) + 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) + 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) + 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)) + 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') + self._downloader.to_screen(u('[youtube] RTMP download detected')) def _closed_captions_xml_to_srt(self, xml_string): srt = '' @@ -239,7 +238,7 @@ class YoutubeIE(InfoExtractor): raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) except (IOError, netrc.NetrcParseError): _, err, _ = sys.exc_info() - self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % u(err)) + self._downloader.to_stderr(u('WARNING: parsing .netrc: %s') % u(err)) return # Set language @@ -249,7 +248,7 @@ class YoutubeIE(InfoExtractor): urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - self._downloader.to_stderr(u'WARNING: unable to set language: %s' % u(err)) + self._downloader.to_stderr(u('WARNING: unable to set language: %s') % u(err)) return # No authentication to be performed @@ -269,11 +268,11 @@ class YoutubeIE(InfoExtractor): self.report_login() login_results = urllib2.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') + self._downloader.to_stderr(u('WARNING: unable to log in: bad username or password')) return except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - self._downloader.to_stderr(u'WARNING: unable to log in: %s' % u(err)) + self._downloader.to_stderr(u('WARNING: unable to log in: %s') % u(err)) return # Confirm age @@ -287,7 +286,7 @@ class YoutubeIE(InfoExtractor): age_results = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - self._downloader.trouble(u'ERROR: unable to confirm age: %s' % u(err)) + self._downloader.trouble(u('ERROR: unable to confirm age: %s') % u(err)) return def _real_extract(self, url): @@ -299,7 +298,7 @@ class YoutubeIE(InfoExtractor): # 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) + self._downloader.trouble(u('ERROR: invalid URL: %s') % url) return video_id = mobj.group(2) @@ -310,7 +309,7 @@ class YoutubeIE(InfoExtractor): video_webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err)) + self._downloader.trouble(u('ERROR: unable to download video webpage: %s') % u(err)) return # Attempt to extract SWF player URL @@ -333,18 +332,18 @@ class YoutubeIE(InfoExtractor): break except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % u(err)) + self._downloader.trouble(u('ERROR: unable to download video info webpage: %s') % u(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].decode('utf-8')) + self._downloader.trouble(u('ERROR: YouTube said: %s') % video_info['reason'][0].decode('utf-8')) else: - self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason') + 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') + self._downloader.trouble(u('ERROR: "rental" videos not supported')) return # Start extracting information @@ -352,26 +351,26 @@ class YoutubeIE(InfoExtractor): # uploader if 'author' not in video_info: - self._downloader.trouble(u'ERROR: unable to extract uploader nickname') + self._downloader.trouble(u('ERROR: unable to extract uploader nickname')) return video_uploader = urllib.unquote_plus(video_info['author'][0]) # title if 'title' not in video_info: - self._downloader.trouble(u'ERROR: unable to extract video title') + self._downloader.trouble(u('ERROR: unable to extract video title')) return video_title = urllib.unquote_plus(video_info['title'][0]) video_title = video_title.decode('utf-8') # thumbnail image if 'thumbnail_url' not in video_info: - self._downloader.trouble(u'WARNING: unable to extract video thumbnail') + self._downloader.trouble(u('WARNING: unable to extract video thumbnail')) video_thumbnail = '' else: # don't panic if we can't find it video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0]) # upload date - upload_date = u'NA' + upload_date = u('NA') 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()) @@ -397,11 +396,11 @@ class YoutubeIE(InfoExtractor): srt_list = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - raise Trouble(u'WARNING: unable to download video subtitles: %s' % u(err)) + raise Trouble(u('WARNING: unable to download video subtitles: %s') % u(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') + 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: @@ -409,22 +408,22 @@ class YoutubeIE(InfoExtractor): 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') + raise Trouble(u('WARNING: no closed captions found in the specified language')) request = urllib2.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 = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - raise Trouble(u'WARNING: unable to download video subtitles: %s' % u(err)) + raise Trouble(u('WARNING: unable to download video subtitles: %s') % u(err)) if not srt_xml: - raise Trouble(u'WARNING: unable to download video subtitles') + raise Trouble(u('WARNING: unable to download video subtitles')) video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8')) except Trouble: _, trouble, _ = sys.exc_info() self._downloader.trouble(trouble[0]) if 'length_seconds' not in video_info: - self._downloader.trouble(u'WARNING: unable to extract video duration') + self._downloader.trouble(u('WARNING: unable to extract video duration')) video_duration = '' else: video_duration = urllib.unquote_plus(video_info['length_seconds'][0]) @@ -452,7 +451,7 @@ class YoutubeIE(InfoExtractor): 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') + self._downloader.trouble(u('ERROR: no known formats available for video')) return if self._downloader.params.get('listformats', None): self._print_formats(existing_formats) @@ -473,10 +472,10 @@ class YoutubeIE(InfoExtractor): video_url_list = [(rf, url_map[rf])] break if video_url_list is None: - self._downloader.trouble(u'ERROR: requested format not available') + 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') + self._downloader.trouble(u('ERROR: no conn or url_encoded_fmt_stream_map information found in video info')) return results = [] @@ -491,7 +490,7 @@ class YoutubeIE(InfoExtractor): 'upload_date': upload_date, 'title': video_title, 'ext': video_extension.decode('utf-8'), - 'format': (format_param is None and u'NA' or format_param.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, 'player_url': player_url, @@ -507,26 +506,26 @@ class MetacafeIE(InfoExtractor): _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' + 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') + 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') + 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) + 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) + self._downloader.to_screen(u('[metacafe] %s: Extracting information') % video_id) def _real_initialize(self): # Retrieve disclaimer @@ -536,7 +535,7 @@ class MetacafeIE(InfoExtractor): disclaimer = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % u(err)) + self._downloader.trouble(u('ERROR: unable to retrieve disclaimer: %s') % u(err)) return # Confirm age @@ -550,14 +549,14 @@ class MetacafeIE(InfoExtractor): disclaimer = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - self._downloader.trouble(u'ERROR: unable to confirm age: %s' % u(err)) + self._downloader.trouble(u('ERROR: unable to confirm age: %s') % u(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) + self._downloader.trouble(u('ERROR: invalid URL: %s') % url) return video_id = mobj.group(1) @@ -575,7 +574,7 @@ class MetacafeIE(InfoExtractor): webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % u(err)) + self._downloader.trouble(u('ERROR: unable retrieve video webpage: %s') % u(err)) return # Extract URL, uploader and title from webpage @@ -595,15 +594,15 @@ class MetacafeIE(InfoExtractor): else: mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') + self._downloader.trouble(u('ERROR: unable to extract media URL')) return vardict = parse_qs(mobj.group(1)) if 'mediaData' not in vardict: - self._downloader.trouble(u'ERROR: unable to extract media URL') + 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') + self._downloader.trouble(u('ERROR: unable to extract media URL')) return mediaURL = mobj.group(1).replace('\\/', '/') video_extension = mediaURL[-3:] @@ -611,13 +610,13 @@ class MetacafeIE(InfoExtractor): mobj = re.search(r'(?im)(.*) - Video', webpage) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') + 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') + self._downloader.trouble(u('ERROR: unable to extract uploader nickname')) return video_uploader = mobj.group(1) @@ -625,10 +624,10 @@ class MetacafeIE(InfoExtractor): 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), 'uploader': video_uploader.decode('utf-8'), - 'upload_date': u'NA', + 'upload_date': u('NA'), 'title': video_title, 'ext': video_extension.decode('utf-8'), - 'format': u'NA', + 'format': u('NA'), 'player_url': None, }] @@ -637,24 +636,24 @@ class DailymotionIE(InfoExtractor): """Information Extractor for Dailymotion""" _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)' - IE_NAME = u'dailymotion' + 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) + 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) + 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) + self._downloader.trouble(u('ERROR: invalid URL: %s') % url) return video_id = mobj.group(1).split('_')[0].split('?')[0] @@ -669,29 +668,29 @@ class DailymotionIE(InfoExtractor): webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % u(err)) + self._downloader.trouble(u('ERROR: unable retrieve video webpage: %s') % u(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') + self._downloader.trouble(u('ERROR: unable to extract media URL')) return flashvars = urllib.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) + self._downloader.to_screen(u('[dailymotion] Using %s') % key) break else: - self._downloader.trouble(u'ERROR: unable to extract video URL') + 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') + self._downloader.trouble(u('ERROR: unable to extract video URL')) return video_url = urllib.unquote(mobj.group(1)).replace('\\/', '/') @@ -700,23 +699,23 @@ class DailymotionIE(InfoExtractor): mobj = re.search(r'', webpage) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') + self._downloader.trouble(u('ERROR: unable to extract title')) return video_title = unescapeHTML(mobj.group('title').decode('utf-8')) - video_uploader = u'NA' + video_uploader = u('NA') 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') + 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 = u'NA' + video_upload_date = u('NA') 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) @@ -728,7 +727,7 @@ class DailymotionIE(InfoExtractor): 'upload_date': video_upload_date, 'title': video_title, 'ext': video_extension.decode('utf-8'), - 'format': u'NA', + 'format': u('NA'), 'player_url': None, }] @@ -737,24 +736,24 @@ 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' + 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) + 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) + 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) + self._downloader.trouble(u('ERROR: Invalid URL: %s') % url) return video_id = mobj.group(1) @@ -768,7 +767,7 @@ class GoogleIE(InfoExtractor): webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err)) + self._downloader.trouble(u('ERROR: Unable to retrieve video webpage: %s') % u(err)) return # Extract URL, uploader, and title from webpage @@ -778,7 +777,7 @@ class GoogleIE(InfoExtractor): 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') + self._downloader.trouble(u('ERROR: unable to extract media URL')) return mediaURL = urllib.unquote(mobj.group(1)) mediaURL = mediaURL.replace('\\x3d', '\x3d') @@ -788,14 +787,14 @@ class GoogleIE(InfoExtractor): mobj = re.search(r'(.*)', webpage) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') + 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') + self._downloader.trouble(u('ERROR: unable to extract video description')) return video_description = mobj.group(1).decode('utf-8') if not video_description: @@ -808,11 +807,11 @@ class GoogleIE(InfoExtractor): webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err)) + self._downloader.trouble(u('ERROR: Unable to retrieve video webpage: %s') % u(err)) return mobj = re.search(r'', webpage) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video thumbnail') + 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 @@ -821,11 +820,11 @@ class GoogleIE(InfoExtractor): return [{ 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), - 'uploader': u'NA', - 'upload_date': u'NA', + 'uploader': u('NA'), + 'upload_date': u('NA'), 'title': video_title, 'ext': video_extension.decode('utf-8'), - 'format': u'NA', + 'format': u('NA'), 'player_url': None, }] @@ -834,24 +833,24 @@ class PhotobucketIE(InfoExtractor): """Information extractor for photobucket.com.""" _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' - IE_NAME = u'photobucket' + 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) + 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) + 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) + self._downloader.trouble(u('ERROR: Invalid URL: %s') % url) return video_id = mobj.group(1) @@ -865,14 +864,14 @@ class PhotobucketIE(InfoExtractor): webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err)) + self._downloader.trouble(u('ERROR: Unable to retrieve video webpage: %s') % u(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') + self._downloader.trouble(u('ERROR: unable to extract media URL')) return mediaURL = urllib.unquote(mobj.group(1)) @@ -880,7 +879,7 @@ class PhotobucketIE(InfoExtractor): mobj = re.search(r'(.*) video by (.*) - Photobucket', webpage) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract title') + self._downloader.trouble(u('ERROR: unable to extract title')) return video_title = mobj.group(1).decode('utf-8') @@ -890,10 +889,10 @@ class PhotobucketIE(InfoExtractor): 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), 'uploader': video_uploader, - 'upload_date': u'NA', + 'upload_date': u('NA'), 'title': video_title, 'ext': video_extension.decode('utf-8'), - 'format': u'NA', + 'format': u('NA'), 'player_url': None, }] @@ -905,24 +904,24 @@ class YahooIE(InfoExtractor): # _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' + 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) + 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) + 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) + self._downloader.trouble(u('ERROR: Invalid URL: %s') % url) return video_id = mobj.group(2) @@ -936,18 +935,18 @@ class YahooIE(InfoExtractor): webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err)) + self._downloader.trouble(u('ERROR: Unable to retrieve video webpage: %s') % u(err)) return mobj = re.search(r'\("id", "([0-9]+)"\);', webpage) if mobj is None: - self._downloader.trouble(u'ERROR: Unable to extract id field') + 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') + self._downloader.trouble(u('ERROR: Unable to extract vid field')) return yahoo_vid = mobj.group(1) @@ -961,34 +960,34 @@ class YahooIE(InfoExtractor): webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err)) + self._downloader.trouble(u('ERROR: Unable to retrieve video webpage: %s') % u(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') + 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') + 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') + 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') + self._downloader.trouble(u('ERROR: unable to extract video description')) return video_description = mobj.group(1).decode('utf-8') if not video_description: @@ -997,13 +996,13 @@ class YahooIE(InfoExtractor): # Extract video height and width mobj = re.search(r'', webpage) if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract video height') + 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') + self._downloader.trouble(u('ERROR: unable to extract video width')) return yv_video_width = mobj.group(1) @@ -1020,13 +1019,13 @@ class YahooIE(InfoExtractor): webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err)) + self._downloader.trouble(u('ERROR: Unable to retrieve video webpage: %s') % u(err)) return # Extract media URL from playlist XML mobj = re.search(r'[^:]*: (.*?)( \([^\(]*\))?', webpage) if mobj is not None: video_upload_date = mobj.group(1) @@ -1138,10 +1137,10 @@ class VimeoIE(InfoExtractor): 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)) + 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') + 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=" \ @@ -1166,18 +1165,18 @@ class ArteTvIE(InfoExtractor): _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*' _LIVE_URL = r'index-[0-9]+\.html$' - IE_NAME = u'arte.tv' + 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) + 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) + self._downloader.to_screen(u('[arte.tv] %s: Extracting information') % video_id) def fetch_webpage(self, url): self._downloader.increment_downloads() @@ -1187,11 +1186,11 @@ class ArteTvIE(InfoExtractor): webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error): _, err, _ = sys.exc_info() - self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + self._downloader.trouble(u('ERROR: Unable to retrieve video webpage: %s') % str(err)) return except ValueError: _, err, _ = sys.exc_info() - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + self._downloader.trouble(u('ERROR: Invalid URL: %s') % url) return return webpage @@ -1201,7 +1200,7 @@ class ArteTvIE(InfoExtractor): info = {} if mobj is None: - self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + self._downloader.trouble(u('ERROR: Invalid URL: %s') % url) return for (i, key, err) in matchTuples: @@ -1220,7 +1219,7 @@ class ArteTvIE(InfoExtractor): r'src="(.*?/videothek_js.*?\.js)', 0, [ - (1, 'url', u'ERROR: Invalid URL: %s' % url) + (1, 'url', u('ERROR: Invalid URL: %s') % url) ] ) http_host = url.split('/')[2] @@ -1232,12 +1231,12 @@ class ArteTvIE(InfoExtractor): '(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) + (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')) + video_url = u('%s/%s') % (info.get('url'), info.get('path')) def extractPlus7Stream(self, url): video_lang = url.split('/')[-3] @@ -1246,7 +1245,7 @@ class ArteTvIE(InfoExtractor): r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)', 0, [ - (1, 'url', u'ERROR: Invalid URL: %s' % url) + (1, 'url', u('ERROR: Invalid URL: %s') % url) ] ) next_url = urllib.unquote(info.get('url')) @@ -1255,7 +1254,7 @@ class ArteTvIE(InfoExtractor): r'