From: Ciaran Gultnieks Date: Mon, 2 Jan 2012 16:50:49 +0000 (+0000) Subject: Unescape scraped version names X-Git-Tag: 0.1~1191 X-Git-Url: http://www.chiark.greenend.org.uk/ucgi/~ianmdlvl/git?a=commitdiff_plain;h=1f0f1a65ee90b95b633e82a95381f09f6cf8abe2;p=fdroidserver.git Unescape scraped version names --- diff --git a/checkmarket2.py b/checkmarket2.py index 760c5b59..d1568291 100755 --- a/checkmarket2.py +++ b/checkmarket2.py @@ -24,7 +24,7 @@ import re import urllib import time from optparse import OptionParser - +import HTMLParser import common #Read configuration... @@ -40,6 +40,8 @@ parser.add_option("-v", "--verbose", action="store_true", default=False, # Get all apps... apps = common.read_metadata(options.verbose) +html_parser = HTMLParser.HTMLParser() + for app in apps: if app['disabled']: @@ -55,15 +57,15 @@ for app in apps: m = re.search('
([^>]+)
', page) if m: - version = m.group(1) + version = html_parser.unescape(m.group(1)) m = re.search('data-paramValue="(\d+)">
Latest Version<', page) if m: vercode = m.group(1) - if vercode is None: + if not vercode: print "...couldn't find version code" - elif version is None: + elif not version: print "...couldn't find version" elif vercode == app['marketvercode'] and version == app['marketversion']: print "...up to date"