Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-07 09:01:38 -04:00
Code Issues Packages Projects Releases Wiki Activity

pep8

Browse Source
This commit is contained in:
Kovid Goyal 2014-08-17 09:01:31 +05:30
parent 65877258a0
commit af642adeb9
1 changed files with 25 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
src/calibre/web/fetch/simple.py
View File

@ -27,6 +27,7 @@ class FetchError(Exception):
pass
class closing(object):
'Context to automatically close something at the end of a block.'
def __init__(self, thing):
@ -95,7 +96,7 @@ def default_is_link_wanted(url, tag):
class RecursiveFetcher(object):
LINK_FILTER = tuple(re.compile(i, re.IGNORECASE) for i in
('.exe\s*$', '.mp3\s*$', '.ogg\s*$', '^\s*mailto:', '^\s*$'))
#ADBLOCK_FILTER = tuple(re.compile(i, re.IGNORECASE) for it in
# ADBLOCK_FILTER = tuple(re.compile(i, re.IGNORECASE) for it in
# (
#
# )
@ -203,7 +204,6 @@ class RecursiveFetcher(object):
tag.extract()
return self.preprocess_html_ext(soup)
def fetch_url(self, url):
data = None
self.log.debug('Fetching', url)
@ -246,8 +246,8 @@ class RecursiveFetcher(object):
data = response(f.read()+f.read())
data.newurl = f.geturl()
except urllib2.URLError as err:
if hasattr(err, 'code') and responses.has_key(err.code):
raise FetchError, responses[err.code]
if hasattr(err, 'code') and err.code in responses:
raise FetchError(responses[err.code])
if getattr(err, 'reason', [0])[0] == 104 or \
getattr(getattr(err, 'args', [None])[0], 'errno', None) in (-2,
-3): # Connection reset by peer or Name or service not known
@ -262,7 +262,6 @@ class RecursiveFetcher(object):
self.last_fetch_at = time.time()
return data
def start_fetch(self, url):
soup = BeautifulSoup(u'<a href="'+url+'" />')
self.log.debug('Downloading')
@ -593,9 +592,16 @@ def option_parser(usage=_('%prog URL\n\nWhere URL is for example http://google.c
parser.add_option('--encoding', default=None,
help=_('The character encoding for the websites you are trying to download. The default is to try and guess the encoding.'))
parser.add_option('--match-regexp', default=[], action='append', dest='match_regexps',
help=_('Only links that match this regular expression will be followed. This option can be specified multiple times, in which case as long as a link matches any one regexp, it will be followed. By default all links are followed.'))
help=_('Only links that match this regular expression will be followed. '
'This option can be specified multiple times, in which case as long '
'as a link matches any one regexp, it will be followed. By default all '
'links are followed.'))
parser.add_option('--filter-regexp', default=[], action='append', dest='filter_regexps',
help=_('Any link that matches this regular expression will be ignored. This option can be specified multiple times, in which case as long as any regexp matches a link, it will be ignored. By default, no links are ignored. If both filter regexp and match regexp are specified, then filter regexp is applied first.'))
help=_('Any link that matches this regular expression will be ignored.'
' This option can be specified multiple times, in which case as'
' long as any regexp matches a link, it will be ignored. By'
' default, no links are ignored. If both filter regexp and match'
' regexp are specified, then filter regexp is applied first.'))
parser.add_option('--dont-download-stylesheets', action='store_true', default=False,
help=_('Do not download CSS stylesheets.'), dest='no_stylesheets')
parser.add_option('--verbose', help=_('Show detailed output information. Useful for debugging'),