|
@ -161,6 +161,7 @@ class FileDownloader(object): |
|
|
|
|
|
|
|
|
def download(self, url_list): |
|
|
def download(self, url_list): |
|
|
"""Download a given list of URLs.""" |
|
|
"""Download a given list of URLs.""" |
|
|
|
|
|
retcode = 0 |
|
|
if len(url_list) > 1 and self.fixed_template(): |
|
|
if len(url_list) > 1 and self.fixed_template(): |
|
|
sys.exit('ERROR: fixed output name but more than one file to download') |
|
|
sys.exit('ERROR: fixed output name but more than one file to download') |
|
|
|
|
|
|
|
@ -171,7 +172,10 @@ class FileDownloader(object): |
|
|
continue |
|
|
continue |
|
|
# Suitable InfoExtractor found |
|
|
# Suitable InfoExtractor found |
|
|
suitable_found = True |
|
|
suitable_found = True |
|
|
results = [x for x in ie.extract(url) if x is not None] |
|
|
|
|
|
|
|
|
all_results = ie.extract(url) |
|
|
|
|
|
results = [x for x in all_results if x is not None] |
|
|
|
|
|
if len(results) != len(all_results): |
|
|
|
|
|
retcode = 1 |
|
|
|
|
|
|
|
|
if len(results) > 1 and self.fixed_template(): |
|
|
if len(results) > 1 and self.fixed_template(): |
|
|
sys.exit('ERROR: fixed output name but more than one file to download') |
|
|
sys.exit('ERROR: fixed output name but more than one file to download') |
|
@ -192,29 +196,37 @@ class FileDownloader(object): |
|
|
filename = self._params['outtmpl'] % result |
|
|
filename = self._params['outtmpl'] % result |
|
|
except (ValueError, KeyError), err: |
|
|
except (ValueError, KeyError), err: |
|
|
self.to_stderr('ERROR: invalid output template: %s' % str(err)) |
|
|
self.to_stderr('ERROR: invalid output template: %s' % str(err)) |
|
|
|
|
|
retcode = 1 |
|
|
continue |
|
|
continue |
|
|
try: |
|
|
try: |
|
|
self.pmkdir(filename) |
|
|
self.pmkdir(filename) |
|
|
except (OSError, IOError), err: |
|
|
except (OSError, IOError), err: |
|
|
self.to_stderr('ERROR: unable to create directories: %s' % str(err)) |
|
|
self.to_stderr('ERROR: unable to create directories: %s' % str(err)) |
|
|
|
|
|
retcode = 1 |
|
|
continue |
|
|
continue |
|
|
try: |
|
|
try: |
|
|
outstream = open(filename, 'wb') |
|
|
outstream = open(filename, 'wb') |
|
|
except (OSError, IOError), err: |
|
|
except (OSError, IOError), err: |
|
|
self.to_stderr('ERROR: unable to open for writing: %s' % str(err)) |
|
|
self.to_stderr('ERROR: unable to open for writing: %s' % str(err)) |
|
|
|
|
|
retcode = 1 |
|
|
continue |
|
|
continue |
|
|
try: |
|
|
try: |
|
|
self._do_download(outstream, result['url']) |
|
|
self._do_download(outstream, result['url']) |
|
|
outstream.close() |
|
|
outstream.close() |
|
|
except (OSError, IOError), err: |
|
|
except (OSError, IOError), err: |
|
|
self.to_stderr('ERROR: unable to write video data: %s' % str(err)) |
|
|
self.to_stderr('ERROR: unable to write video data: %s' % str(err)) |
|
|
|
|
|
retcode = 1 |
|
|
continue |
|
|
continue |
|
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err: |
|
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err: |
|
|
self.to_stderr('ERROR: unable to download video data: %s' % str(err)) |
|
|
self.to_stderr('ERROR: unable to download video data: %s' % str(err)) |
|
|
|
|
|
retcode = 1 |
|
|
continue |
|
|
continue |
|
|
break |
|
|
break |
|
|
if not suitable_found: |
|
|
if not suitable_found: |
|
|
self.to_stderr('ERROR: no suitable InfoExtractor: %s' % url) |
|
|
self.to_stderr('ERROR: no suitable InfoExtractor: %s' % url) |
|
|
|
|
|
retcode = 1 |
|
|
|
|
|
|
|
|
|
|
|
return retcode |
|
|
|
|
|
|
|
|
def _do_download(self, stream, url): |
|
|
def _do_download(self, stream, url): |
|
|
request = urllib2.Request(url, None, std_headers) |
|
|
request = urllib2.Request(url, None, std_headers) |
|
@ -359,10 +371,10 @@ class YoutubeIE(InfoExtractor): |
|
|
self.to_stdout('[youtube] Logging in') |
|
|
self.to_stdout('[youtube] Logging in') |
|
|
login_results = urllib2.urlopen(request).read() |
|
|
login_results = urllib2.urlopen(request).read() |
|
|
if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None: |
|
|
if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None: |
|
|
self.to_stderr('WARNING: Unable to log in: bad username or password') |
|
|
|
|
|
|
|
|
self.to_stderr('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.to_stderr('WARNING: Unable to log in: %s' % str(err)) |
|
|
|
|
|
|
|
|
self.to_stderr('WARNING: unable to log in: %s' % str(err)) |
|
|
return |
|
|
return |
|
|
|
|
|
|
|
|
# Confirm age |
|
|
# Confirm age |
|
@ -375,13 +387,13 @@ class YoutubeIE(InfoExtractor): |
|
|
self.to_stdout('[youtube] Confirming age') |
|
|
self.to_stdout('[youtube] Confirming age') |
|
|
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: |
|
|
sys.exit('ERROR: Unable to confirm age: %s' % str(err)) |
|
|
|
|
|
|
|
|
sys.exit('ERROR: unable to confirm age: %s' % str(err)) |
|
|
|
|
|
|
|
|
def _real_extract(self, url): |
|
|
def _real_extract(self, url): |
|
|
# Extract video id from URL |
|
|
# Extract video id from URL |
|
|
mobj = re.match(r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$', url) |
|
|
mobj = re.match(r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$', url) |
|
|
if mobj is None: |
|
|
if mobj is None: |
|
|
self.to_stderr('ERROR: Invalid URL: %s' % url) |
|
|
|
|
|
|
|
|
self.to_stderr('ERROR: invalid URL: %s' % url) |
|
|
return [None] |
|
|
return [None] |
|
|
video_id = mobj.group(2) |
|
|
video_id = mobj.group(2) |
|
|
|
|
|
|
|
@ -403,13 +415,13 @@ class YoutubeIE(InfoExtractor): |
|
|
self.to_stdout('[youtube] %s: Downloading video webpage' % video_id) |
|
|
self.to_stdout('[youtube] %s: Downloading video webpage' % video_id) |
|
|
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: |
|
|
sys.exit('ERROR: Unable to download video: %s' % str(err)) |
|
|
|
|
|
|
|
|
sys.exit('ERROR: unable to download video: %s' % str(err)) |
|
|
self.to_stdout('[youtube] %s: Extracting video information' % video_id) |
|
|
self.to_stdout('[youtube] %s: Extracting video information' % video_id) |
|
|
|
|
|
|
|
|
# "t" param |
|
|
# "t" param |
|
|
mobj = re.search(r', "t": "([^"]+)"', video_webpage) |
|
|
mobj = re.search(r', "t": "([^"]+)"', video_webpage) |
|
|
if mobj is None: |
|
|
if mobj is None: |
|
|
self.to_stderr('ERROR: Unable to extract "t" parameter') |
|
|
|
|
|
|
|
|
self.to_stderr('ERROR: unable to extract "t" parameter') |
|
|
return [None] |
|
|
return [None] |
|
|
video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s' % (video_id, mobj.group(1)) |
|
|
video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s' % (video_id, mobj.group(1)) |
|
|
if format_param is not None: |
|
|
if format_param is not None: |
|
@ -419,14 +431,14 @@ class YoutubeIE(InfoExtractor): |
|
|
# uploader |
|
|
# uploader |
|
|
mobj = re.search(r'More From: ([^<]*)<', video_webpage) |
|
|
mobj = re.search(r'More From: ([^<]*)<', video_webpage) |
|
|
if mobj is None: |
|
|
if mobj is None: |
|
|
self.to_stderr('ERROR: Unable to extract uploader nickname') |
|
|
|
|
|
|
|
|
self.to_stderr('ERROR: unable to extract uploader nickname') |
|
|
return [None] |
|
|
return [None] |
|
|
video_uploader = mobj.group(1) |
|
|
video_uploader = mobj.group(1) |
|
|
|
|
|
|
|
|
# title |
|
|
# title |
|
|
mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage) |
|
|
mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage) |
|
|
if mobj is None: |
|
|
if mobj is None: |
|
|
self.to_stderr('ERROR: Unable to extract video title') |
|
|
|
|
|
|
|
|
self.to_stderr('ERROR: unable to extract video title') |
|
|
return [None] |
|
|
return [None] |
|
|
video_title = mobj.group(1).decode('utf-8') |
|
|
video_title = mobj.group(1).decode('utf-8') |
|
|
video_title = re.sub(ur'(?u)&(.+?);', lambda x: unichr(htmlentitydefs.name2codepoint[x.group(1)]), video_title) |
|
|
video_title = re.sub(ur'(?u)&(.+?);', lambda x: unichr(htmlentitydefs.name2codepoint[x.group(1)]), video_title) |
|
@ -526,7 +538,8 @@ if __name__ == '__main__': |
|
|
or '%(id)s.%(ext)s'), |
|
|
or '%(id)s.%(ext)s'), |
|
|
}) |
|
|
}) |
|
|
fd.add_info_extractor(youtube_ie) |
|
|
fd.add_info_extractor(youtube_ie) |
|
|
fd.download(args) |
|
|
|
|
|
|
|
|
retcode = fd.download(args) |
|
|
|
|
|
sys.exit(retcode) |
|
|
|
|
|
|
|
|
except KeyboardInterrupt: |
|
|
except KeyboardInterrupt: |
|
|
sys.exit('\nERROR: Interrupted by user') |
|
|
sys.exit('\nERROR: Interrupted by user') |