Remove mentions of unicode

This commit is contained in:
Philipp Hagemeister 2012-11-27 19:02:37 +01:00
parent b514df2034
commit dd109dee8e
3 changed files with 64 additions and 65 deletions

View File

@ -330,7 +330,7 @@ def prepare_filename(self, info_dict):
template_dict['epoch'] = int(time.time()) 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(compat_str(v), self.params.get('restrictfilenames'))) for k,v in template_dict.items()) 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 filename = self.params['outtmpl'] % template_dict
return filename return filename
except (ValueError, KeyError), err: except (ValueError, KeyError), err:
@ -397,7 +397,7 @@ def process_info(self, info_dict):
if dn != '' and not os.path.exists(dn): # dn is already encoded if dn != '' and not os.path.exists(dn): # dn is already encoded
os.makedirs(dn) os.makedirs(dn)
except (OSError, IOError), err: except (OSError, IOError), err:
self.trouble(u'ERROR: unable to create directory ' + unicode(err)) self.trouble(u'ERROR: unable to create directory ' + u(err))
return return
if self.params.get('writedescription', False): if self.params.get('writedescription', False):

View File

@ -238,7 +238,7 @@ def _real_initialize(self):
else: else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError), err: except (IOError, netrc.NetrcParseError), err:
self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err)) self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % u(err))
return return
# Set language # Set language
@ -247,7 +247,7 @@ def _real_initialize(self):
self.report_lang() self.report_lang()
urllib2.urlopen(request).read() urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.to_stderr(u'WARNING: unable to set language: %s' % compat_str(err)) self._downloader.to_stderr(u'WARNING: unable to set language: %s' % u(err))
return return
# No authentication to be performed # No authentication to be performed
@ -270,7 +270,7 @@ def _real_initialize(self):
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 return
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' % compat_str(err)) self._downloader.to_stderr(u'WARNING: unable to log in: %s' % u(err))
return return
# Confirm age # Confirm age
@ -283,7 +283,7 @@ def _real_initialize(self):
self.report_age_confirmation() self.report_age_confirmation()
age_results = urllib2.urlopen(request).read() age_results = 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' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to confirm age: %s' % u(err))
return return
def _real_extract(self, url): def _real_extract(self, url):
@ -305,7 +305,7 @@ def _real_extract(self, url):
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:
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
return return
# Attempt to extract SWF player URL # Attempt to extract SWF player URL
@ -327,7 +327,7 @@ def _real_extract(self, url):
if 'token' in video_info: if 'token' in video_info:
break break
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % u(err))
return return
if 'token' not in video_info: if 'token' not in video_info:
if 'reason' in video_info: if 'reason' in video_info:
@ -390,7 +390,7 @@ def _real_extract(self, url):
try: try:
srt_list = urllib2.urlopen(request).read() srt_list = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
raise Trouble(u'WARNING: unable to download video subtitles: %s' % compat_str(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 = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list)
srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list) srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list)
if not srt_lang_list: if not srt_lang_list:
@ -407,7 +407,7 @@ def _real_extract(self, url):
try: try:
srt_xml = urllib2.urlopen(request).read() srt_xml = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
raise Trouble(u'WARNING: unable to download video subtitles: %s' % compat_str(err)) raise Trouble(u'WARNING: unable to download video subtitles: %s' % u(err))
if not srt_xml: 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')) video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8'))
@ -526,7 +526,7 @@ def _real_initialize(self):
self.report_disclaimer() self.report_disclaimer()
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 retrieve disclaimer: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % u(err))
return return
# Confirm age # Confirm age
@ -539,7 +539,7 @@ def _real_initialize(self):
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' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to confirm age: %s' % u(err))
return return
def _real_extract(self, url): def _real_extract(self, url):
@ -563,7 +563,7 @@ def _real_extract(self, url):
self.report_download_webpage(video_id) self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read() webpage = 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 retrieve video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % u(err))
return return
# Extract URL, uploader and title from webpage # Extract URL, uploader and title from webpage
@ -656,7 +656,7 @@ def _real_extract(self, url):
self.report_download_webpage(video_id) self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read() webpage = 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 retrieve video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % u(err))
return return
# Extract URL, uploader and title from webpage # Extract URL, uploader and title from webpage
@ -754,7 +754,7 @@ def _real_extract(self, url):
self.report_download_webpage(video_id) self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read() webpage = 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 retrieve video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return return
# Extract URL, uploader, and title from webpage # Extract URL, uploader, and title from webpage
@ -793,7 +793,7 @@ def _real_extract(self, url):
try: try:
webpage = urllib2.urlopen(request).read() webpage = 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 retrieve video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return return
mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage) mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage)
if mobj is None: if mobj is None:
@ -849,7 +849,7 @@ def _real_extract(self, url):
self.report_download_webpage(video_id) self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read() webpage = 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 retrieve video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return return
# Extract URL, uploader, and title from webpage # Extract URL, uploader, and title from webpage
@ -919,7 +919,7 @@ def _real_extract(self, url, new_video=True):
try: try:
webpage = urllib2.urlopen(request).read() webpage = 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 retrieve video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return return
mobj = re.search(r'\("id", "([0-9]+)"\);', webpage) mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
@ -943,7 +943,7 @@ def _real_extract(self, url, new_video=True):
self.report_download_webpage(video_id) self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read() webpage = 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 retrieve video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return return
# Extract uploader and title from webpage # Extract uploader and title from webpage
@ -1001,7 +1001,7 @@ def _real_extract(self, url, new_video=True):
self.report_download_webpage(video_id) self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read() webpage = 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 retrieve video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return return
# Extract media URL from playlist XML # Extract media URL from playlist XML
@ -1059,7 +1059,7 @@ def _real_extract(self, url, new_video=True):
self.report_download_webpage(video_id) self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read() webpage = 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 retrieve video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return return
# Now we begin extracting as much information as we can from what we # Now we begin extracting as much information as we can from what we
@ -1362,7 +1362,7 @@ def _real_extract(self, url):
self.report_download_webpage(video_id) self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read() webpage = 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 retrieve video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return return
except ValueError, err: except ValueError, err:
# since this is the last-resort InfoExtractor, if # since this is the last-resort InfoExtractor, if
@ -1483,7 +1483,7 @@ def _download_n_results(self, query, n):
try: try:
data = urllib2.urlopen(request).read() data = 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 download API page: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download API page: %s' % u(err))
return return
api_response = json.loads(data)['data'] api_response = json.loads(data)['data']
@ -1560,7 +1560,7 @@ def _download_n_results(self, query, n):
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:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
return return
# Extract video identifiers # Extract video identifiers
@ -1643,7 +1643,7 @@ def _download_n_results(self, query, n):
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:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
return return
# Extract video identifiers # Extract video identifiers
@ -1713,7 +1713,7 @@ def _real_extract(self, 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:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
return return
# Extract video identifiers # Extract video identifiers
@ -1770,7 +1770,7 @@ def _real_extract(self, 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:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
return return
# Extract video identifiers # Extract video identifiers
@ -1833,7 +1833,7 @@ def _real_extract(self, 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:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
return return
# Extract video identifiers # Extract video identifiers
@ -1905,7 +1905,7 @@ def _real_extract(self, url):
mobj = re.search(r'data-users-id="([^"]+)"', page) mobj = re.search(r'data-users-id="([^"]+)"', page)
page_base = page_base % mobj.group(1) page_base = page_base % mobj.group(1)
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
return return
@ -1993,7 +1993,7 @@ def _real_extract(self, url):
self.report_download_webpage(file_id) self.report_download_webpage(file_id)
webpage = urllib2.urlopen(request).read() webpage = 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 retrieve file webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % u(err))
return return
# Search for the real file URL # Search for the real file URL
@ -2110,7 +2110,7 @@ def _real_initialize(self):
else: else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError), err: except (IOError, netrc.NetrcParseError), err:
self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err)) self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % u(err))
return return
if useremail is None: if useremail is None:
@ -2130,7 +2130,7 @@ def _real_initialize(self):
self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
return return
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' % compat_str(err)) self._downloader.to_stderr(u'WARNING: unable to log in: %s' % u(err))
return return
def _real_extract(self, url): def _real_extract(self, url):
@ -2147,7 +2147,7 @@ def _real_extract(self, url):
page = urllib2.urlopen(request) page = urllib2.urlopen(request)
video_webpage = page.read() video_webpage = page.read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
return return
# Start extracting information # Start extracting information
@ -2281,13 +2281,13 @@ def _real_extract(self, url):
'urlhandle': urlh 'urlhandle': urlh
} }
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % u(err))
return return
if info is None: # Regular URL if info is None: # Regular URL
try: try:
json_code = urlh.read() json_code = urlh.read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % u(err))
return return
try: try:
@ -2355,7 +2355,7 @@ def _real_extract(self,url):
self.report_download_webpage(video_id) self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read() webpage = 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 retrieve video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return return
self.report_extraction(video_id) self.report_extraction(video_id)
@ -2454,7 +2454,7 @@ def _real_extract(self, url):
htmlHandle = urllib2.urlopen(req) htmlHandle = urllib2.urlopen(req)
html = htmlHandle.read() html = htmlHandle.read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err)) self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
return return
if dlNewest: if dlNewest:
url = htmlHandle.geturl() url = htmlHandle.geturl()
@ -2487,7 +2487,7 @@ def _real_extract(self, url):
urlHandle = urllib2.urlopen(playerUrl_raw) urlHandle = urllib2.urlopen(playerUrl_raw)
playerUrl = urlHandle.geturl() playerUrl = urlHandle.geturl()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to find out player URL: ' + unicode(err)) self._downloader.trouble(u'ERROR: unable to find out player URL: ' + u(err))
return return
uri = mMovieParams[0][1] uri = mMovieParams[0][1]
@ -2496,7 +2496,7 @@ def _real_extract(self, url):
try: try:
indexXml = urllib2.urlopen(indexUrl).read() indexXml = urllib2.urlopen(indexUrl).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download episode index: ' + unicode(err)) self._downloader.trouble(u'ERROR: unable to download episode index: ' + u(err))
return return
results = [] results = []
@ -2517,7 +2517,7 @@ def _real_extract(self, url):
try: try:
configXml = urllib2.urlopen(configReq).read() configXml = urllib2.urlopen(configReq).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err)) self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
return return
cdoc = xml.etree.ElementTree.fromstring(configXml) cdoc = xml.etree.ElementTree.fromstring(configXml)
@ -2600,7 +2600,7 @@ def _real_extract(self, url):
m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type']) m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type'])
webPage = webPageBytes.decode(m.group(1) if m else 'utf-8') webPage = webPageBytes.decode(m.group(1) if m else 'utf-8')
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err)) self._downloader.trouble(u'ERROR: unable to download webpage: ' + u(err))
return return
descMatch = re.search('<meta name="description" content="([^"]*)"', webPage) descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
@ -2616,7 +2616,7 @@ def _real_extract(self, url):
try: try:
configJSON = urllib2.urlopen(configUrl).read() configJSON = urllib2.urlopen(configUrl).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download configuration: ' + unicode(err)) self._downloader.trouble(u'ERROR: unable to download configuration: ' + u(err))
return return
# Technically, it's JavaScript, not JSON # Technically, it's JavaScript, not JSON
@ -2625,7 +2625,7 @@ def _real_extract(self, url):
try: try:
config = json.loads(configJSON) config = json.loads(configJSON)
except (ValueError,), err: except (ValueError,), err:
self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + unicode(err)) self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + u(err))
return return
playlist = config['playlist'] playlist = config['playlist']
@ -2673,7 +2673,7 @@ def _real_extract(self, url):
try: try:
webpage = urllib2.urlopen(request).read() webpage = 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 download video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
return return
m = re.search(r'id="video:(?P<internalvideoid>[0-9]+)"', webpage) m = re.search(r'id="video:(?P<internalvideoid>[0-9]+)"', webpage)
@ -2692,7 +2692,7 @@ def _real_extract(self, url):
try: try:
metaXml = urllib2.urlopen(xmlUrl).read() metaXml = urllib2.urlopen(xmlUrl).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % u(err))
return return
mdoc = xml.etree.ElementTree.fromstring(metaXml) mdoc = xml.etree.ElementTree.fromstring(metaXml)
@ -2738,7 +2738,7 @@ def _real_extract(self, url):
try: try:
webpage = urllib2.urlopen(request).read() webpage = 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 download video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
return return
self.report_extraction(video_id) self.report_extraction(video_id)
@ -2824,7 +2824,7 @@ def _real_extract(self, url):
try: try:
webpage = urllib2.urlopen(request).read() webpage = 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 download video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
return return
self.report_extraction('%s/%s' % (uploader, slug_title)) self.report_extraction('%s/%s' % (uploader, slug_title))
@ -2859,7 +2859,7 @@ def _real_extract(self, url):
try: try:
upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d') upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d')
except Exception, e: except Exception, e:
self._downloader.to_stderr(compat_str(e)) self._downloader.to_stderr(u(e))
# for soundcloud, a request to a cross domain is required for cookies # for soundcloud, a request to a cross domain is required for cookies
request = urllib2.Request('http://media.soundcloud.com/crossdomain.xml', std_headers) request = urllib2.Request('http://media.soundcloud.com/crossdomain.xml', std_headers)
@ -2903,7 +2903,7 @@ def _real_extract(self, url):
try: try:
webpage = urllib2.urlopen(request).read() webpage = 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 download video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
return return
self.report_extraction(url) self.report_extraction(url)
@ -3017,7 +3017,7 @@ def _real_extract(self, url):
self.report_download_json(file_url) self.report_download_json(file_url)
jsonData = urllib2.urlopen(request).read() jsonData = 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 retrieve file: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % u(err))
return return
# parse JSON # parse JSON
@ -3094,7 +3094,7 @@ def _real_extract(self, url):
try: try:
metaXml = urllib2.urlopen(xmlUrl).read() metaXml = urllib2.urlopen(xmlUrl).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % unicode(err)) self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % u(err))
return return
mdoc = xml.etree.ElementTree.fromstring(metaXml) mdoc = xml.etree.ElementTree.fromstring(metaXml)
try: try:
@ -3117,7 +3117,7 @@ def _real_extract(self, url):
try: try:
coursepage = urllib2.urlopen(url).read() coursepage = urllib2.urlopen(url).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err)) self._downloader.trouble(u'ERROR: unable to download course info page: ' + u(err))
return return
m = re.search('<h1>([^<]+)</h1>', coursepage) m = re.search('<h1>([^<]+)</h1>', coursepage)
@ -3154,7 +3154,7 @@ def _real_extract(self, url):
try: try:
rootpage = urllib2.urlopen(rootURL).read() rootpage = urllib2.urlopen(rootURL).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err)) self._downloader.trouble(u'ERROR: unable to download course info page: ' + u(err))
return return
info['title'] = info['id'] info['title'] = info['id']
@ -3201,7 +3201,7 @@ def _real_extract(self, url):
try: try:
webpage = urllib2.urlopen(request).read() webpage = 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 download video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
return return
mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage) mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage)
@ -3234,7 +3234,7 @@ def _real_extract(self, url):
try: try:
metadataXml = urllib2.urlopen(request).read() metadataXml = 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 download video metadata: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % u(err))
return return
mdoc = xml.etree.ElementTree.fromstring(metadataXml) mdoc = xml.etree.ElementTree.fromstring(metadataXml)
@ -3321,7 +3321,7 @@ def _real_extract(self, url):
self.report_download_webpage(video_id) self.report_download_webpage(video_id)
jsondata = urllib2.urlopen(request).read() jsondata = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error) as err: except (urllib2.URLError, httplib.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return return
self.report_extraction(video_id) self.report_extraction(video_id)
@ -3497,7 +3497,7 @@ def _real_extract(self, url):
try: try:
webpage = urllib2.urlopen(request).read() webpage = 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 retrieve entry webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % u(err))
return return
# Extract update date # Extract update date
@ -3539,7 +3539,7 @@ def _real_extract(self, url):
try: try:
webpage = urllib2.urlopen(request).read() webpage = 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 retrieve video webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
return return
self.report_extract_vid_page(video_page) self.report_extract_vid_page(video_page)

View File

@ -27,9 +27,9 @@
} }
try: try:
compat_str = unicode # Python 2 u = unicode # Python 2
except NameError: except NameError:
compat_str = str u = str
def preferredencoding(): def preferredencoding():
"""Get preferred encoding. """Get preferred encoding.
@ -47,7 +47,7 @@ def preferredencoding():
def htmlentity_transform(matchobj): def htmlentity_transform(matchobj):
"""Transforms an HTML entity to a Unicode character. """Transforms an HTML entity to a 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.
@ -58,7 +58,6 @@ def htmlentity_transform(matchobj):
if entity in htmlentitydefs.name2codepoint: if entity in htmlentitydefs.name2codepoint:
return unichr(htmlentitydefs.name2codepoint[entity]) return unichr(htmlentitydefs.name2codepoint[entity])
# Unicode character
mobj = re.match(ur'(?u)#(x?\d+)', entity) mobj = re.match(ur'(?u)#(x?\d+)', entity)
if mobj is not None: if mobj is not None:
numstr = mobj.group(1) numstr = mobj.group(1)
@ -67,7 +66,7 @@ def htmlentity_transform(matchobj):
numstr = u'0%s' % numstr numstr = u'0%s' % numstr
else: else:
base = 10 base = 10
return unichr(long(numstr, base)) return unichr(int(numstr, base))
# Unknown entity in name, return its literal representation # Unknown entity in name, return its literal representation
return (u'&%s;' % entity) return (u'&%s;' % entity)
@ -235,7 +234,7 @@ def orderedSet(iterable):
def unescapeHTML(s): def unescapeHTML(s):
""" """
@param s a string (of type unicode) @param s a string
""" """
assert type(s) == type(u'') assert type(s) == type(u'')
@ -244,7 +243,7 @@ def unescapeHTML(s):
def encodeFilename(s): def encodeFilename(s):
""" """
@param s The name of the file (of type unicode) @param s The name of the file
""" """
assert type(s) == type(u'') assert type(s) == type(u'')