Permalink
Browse files

ExtractorError for errors during extraction

  • Loading branch information...
1 parent a34dd63 commit 1c256f7047051bf351ed5aedb95d8e705685a06b @phihag phihag committed Jan 1, 2013
Showing with 29 additions and 7 deletions.
  1. +17 −5 youtube_dl/FileDownloader.py
  2. +1 −2 youtube_dl/InfoExtractors.py
  3. +11 −0 youtube_dl/utils.py
@@ -210,7 +210,7 @@ def fixed_template(self):
"""Checks if the output template is fixed."""
return (re.search(u'(?u)%\\(.+?\\)s', self.params['outtmpl']) is None)
- def trouble(self, message=None):
+ def trouble(self, message=None, tb=None):
"""Determine action to take when a download problem appears.
Depending on if the downloader has been configured to ignore
@@ -220,7 +220,9 @@ def trouble(self, message=None):
if message is not None:
self.to_stderr(message)
if self.params.get('verbose'):
- self.to_stderr(u''.join(traceback.format_list(traceback.extract_stack())))
+ if tb is None:
+ tb = u''.join(traceback.format_list(traceback.extract_stack()))
+ self.to_stderr(tb)
if not self.params.get('ignoreerrors', False):
raise DownloadError(message)
self._download_retcode = 1
@@ -485,14 +487,24 @@ def download(self, url_list):
# Warn if the _WORKING attribute is False
if not ie.working():
- self.trouble(u'WARNING: the program functionality for this site has been marked as broken, '
- u'and will probably not work. If you want to go on, use the -i option.')
+ self.to_stderr(u'WARNING: the program functionality for this site has been marked as broken, '
+ u'and will probably not work. If you want to go on, use the -i option.')
# Suitable InfoExtractor found
suitable_found = True
# Extract information from URL and process it
- videos = ie.extract(url)
+ try:
+ videos = ie.extract(url)
+ except ExtractorError as de: # An error we somewhat expected
+ self.trouble(u'ERROR: ' + compat_str(de), compat_str(u''.join(traceback.format_tb(de.traceback))))
+ break
+ except Exception as e:
+ if self.params.get('ignoreerrors', False):
+ self.trouble(u'ERROR: ' + compat_str(e), tb=compat_str(traceback.format_exc()))
+ break
+ else:
+ raise
if len(videos or []) > 1 and self.fixed_template():
raise SameFileError(self.params['outtmpl'])
@@ -3808,8 +3808,7 @@ def _real_extract(self, url):
webpage_bytes = urlh.read()
webpage = webpage_bytes.decode('utf-8', 'ignore')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
- return
+ raise ExtractorError(u'unable to download webpage: %s' % compat_str(err))
m = re.search(r'data-title="(?P<title>.+)"',webpage)
title = m.group('title')
m = re.search(r'<a class="state" data-content-type="channel" data-content-id="(?P<uploader>\d+)"',webpage)
View
@@ -410,6 +410,17 @@ def encodeFilename(s):
else:
return s.encode(sys.getfilesystemencoding(), 'ignore')
+
+class ExtractorError(Exception):
+ """Error during info extraction."""
+ def __init__(self, msg, tb=None):
+ """ tb is the original traceback (so that it can be printed out) """
+ super(ExtractorError, self).__init__(msg)
+ if tb is None:
+ tb = sys.exc_info()[2]
+ self.traceback = tb
+
+
class DownloadError(Exception):
"""Download Error exception.

0 comments on commit 1c256f7

Please sign in to comment.