diff options
author | Christian Ruppert <idl0r@gentoo.org> | 2009-07-20 17:01:21 +0200 |
---|---|---|
committer | Sebastian Pipping <sebastian@pipping.org> | 2009-07-21 01:35:40 +0200 |
commit | 7538e4997b579daf07ffd6789f37815bc0d141d4 (patch) | |
tree | 3247d2e8810a18bf46a0c71263cb07834589089d /mirrorselect | |
parent | Add idl0r to list of authors (diff) | |
download | mirrorselect-7538e4997b579daf07ffd6789f37815bc0d141d4.tar.gz mirrorselect-7538e4997b579daf07ffd6789f37815bc0d141d4.tar.bz2 mirrorselect-7538e4997b579daf07ffd6789f37815bc0d141d4.zip |
Migrated to tabs everywhere. Minor cleanup as complained by pylint.
Diffstat (limited to 'mirrorselect')
-rw-r--r-- | mirrorselect/mirrorparser.py | 108 | ||||
-rw-r--r-- | mirrorselect/mirrorparser3.py | 60 |
2 files changed, 84 insertions, 84 deletions
diff --git a/mirrorselect/mirrorparser.py b/mirrorselect/mirrorparser.py index 4b07f0f..1240690 100644 --- a/mirrorselect/mirrorparser.py +++ b/mirrorselect/mirrorparser.py @@ -23,68 +23,68 @@ from HTMLParser import HTMLParser MIRRORS_XML = 'http://www.gentoo.org/main/en/mirrors.xml?passthru=1' class MirrorParser(HTMLParser): - """ - MirrorParser objects are fed an html input stream via the feed() method. - After the instance is closed, the lines atribute contains an array with - elements of the form: (url, description) - """ + """ + MirrorParser objects are fed an html input stream via the feed() method. + After the instance is closed, the lines atribute contains an array with + elements of the form: (url, description) + """ - def __init__(self): - HTMLParser.__init__(self) + def __init__(self): + HTMLParser.__init__(self) - self.lines = [] - self.line = [] + self.lines = [] + self.line = [] - self.get_desc = False - self.in_sect = False - self.sect_good = False - self.check_title = False + self.get_desc = False + self.in_sect = False + self.sect_good = False + self.check_title = False - self.sects = ('North America', 'South America', 'Europe', 'Australia', - 'Asia', 'Other Mirrors:', 'Partial Mirrors') + self.sects = ('North America', 'South America', 'Europe', 'Australia', + 'Asia', 'Other Mirrors:', 'Partial Mirrors') - def handle_starttag(self, tag, attrs): - if tag == 'section': - self.in_sect = True - if (tag == 'title') and self.in_sect: - self.check_title = True - if (tag == 'uri') and self.sect_good: #This is a good one - self.line.append(dict(attrs)['link']) #url - self.get_desc = True #the next data block is the description + def handle_starttag(self, tag, attrs): + if tag == 'section': + self.in_sect = True + if (tag == 'title') and self.in_sect: + self.check_title = True + if (tag == 'uri') and self.sect_good: #This is a good one + self.line.append(dict(attrs)['link']) #url + self.get_desc = True #the next data block is the description - def handle_data(self, data): - if self.check_title and (data in self.sects): - self.sect_good = True - if self.get_desc: - if data.endswith('*'): - data = data.replace('*', '') - data = '* ' + data - self.line.append(data) - self.get_desc = False + def handle_data(self, data): + if self.check_title and (data in self.sects): + self.sect_good = True + if self.get_desc: + if data.endswith('*'): + data = data.replace('*', '') + data = '* ' + data + self.line.append(data) + self.get_desc = False - def handle_endtag(self, tag): - if tag == 'section': - self.in_sect = False - self.sect_good = False - if (tag == 'uri') and (len(self.line) == 2): - self.lines.append(tuple(self.line)) - self.line = [] + def handle_endtag(self, tag): + if tag == 'section': + self.in_sect = False + self.sect_good = False + if (tag == 'uri') and (len(self.line) == 2): + self.lines.append(tuple(self.line)) + self.line = [] - def tuples(self): - return self.lines + def tuples(self): + return self.lines - def uris(self): - return [url for url, description in self.lines] + def uris(self): + return [url for url, description in self.lines] if __name__ == '__main__': - import urllib - parser = MirrorParser() - try: - parser.feed(urllib.urlopen(MIRRORS_XML).read()) - except EnvironmentError: - pass - parser.close() - print '===== tuples' - print parser.tuples() - print '===== uris' - print parser.uris() + import urllib + parser = MirrorParser() + try: + parser.feed(urllib.urlopen(MIRRORS_XML).read()) + except EnvironmentError: + pass + parser.close() + print '===== tuples' + print parser.tuples() + print '===== uris' + print parser.uris() diff --git a/mirrorselect/mirrorparser3.py b/mirrorselect/mirrorparser3.py index 1bde004..f307c6f 100644 --- a/mirrorselect/mirrorparser3.py +++ b/mirrorselect/mirrorparser3.py @@ -25,35 +25,35 @@ from xml.etree import ElementTree as ET MIRRORS_3_XML = 'http://www.gentoo.org/main/en/mirrors3.xml' class MirrorParser3: - def __init__(self): - self._reset() - - def _reset(self): - self._dict = {} - - def parse(self, text): - self._reset() - for mirrorgroup in ET.XML(text): - for mirror in mirrorgroup: - name = '' - for e in mirror: - if e.tag == 'name': - name = e.text - if e.tag == 'uri': - uri = e.text - self._dict[uri] = [name, mirrorgroup.get("countryname")] - - def tuples(self): - return [(url, name) for url, name in self._dict.items()] - - def uris(self): - return [url for url, name in self._dict.items()] + def __init__(self): + self._reset() + + def _reset(self): + self._dict = {} + + def parse(self, text): + self._reset() + for mirrorgroup in ET.XML(text): + for mirror in mirrorgroup: + name = '' + for e in mirror: + if e.tag == 'name': + name = e.text + if e.tag == 'uri': + uri = e.text + self._dict[uri] = [name, mirrorgroup.get("countryname")] + + def tuples(self): + return [(url, name) for url, name in self._dict.items()] + + def uris(self): + return [url for url, name in self._dict.items()] if __name__ == '__main__': - import urllib - parser = MirrorParser3() - parser.parse(urllib.urlopen(MIRRORS_3_XML).read()) - print '===== tuples' - print parser.tuples() - print '===== uris' - print parser.uris() + import urllib + parser = MirrorParser3() + parser.parse(urllib.urlopen(MIRRORS_3_XML).read()) + print '===== tuples' + print parser.tuples() + print '===== uris' + print parser.uris() |