From dffe34cb766b058f73e151585fab585b56a141b7 Mon Sep 17 00:00:00 2001 From: evilhero Date: Tue, 18 Sep 2012 10:42:57 -0400 Subject: [PATCH] improved searching results by limiting 2ndary results through filters --- mylar/parseit.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/mylar/parseit.py b/mylar/parseit.py index 7640b11d..08bf3a2a 100755 --- a/mylar/parseit.py +++ b/mylar/parseit.py @@ -19,6 +19,7 @@ import urllib2 import re import helpers import logger +import datetime from decimal import Decimal from HTMLParser import HTMLParseError @@ -87,6 +88,7 @@ def MysterBinScrape(comsearch): return mres def GCDScraper(ComicName, ComicYear, Total, ComicID): + NOWyr = datetime.date.today().year comicnm = ComicName comicyr = ComicYear comicis = Total @@ -96,7 +98,8 @@ def GCDScraper(ComicName, ComicYear, Total, ComicID): #print ( "comichave: " + str(comicis) ) #print ( "comicid: " + str(comicid) ) comicnm = re.sub(' ', '%20', comicnm) - input = 'http://www.comics.org/series/name/' + str(comicnm) + '/sort/alpha/' + #input = 'http://www.comics.org/series/name/' + str(comicnm) + '/sort/alpha/' + input = 'http://www.comics.org/search/advanced/process/?target=series&method=icontains&logic=False&order2=date&order3=&start_date=' + str(comicyr) + '-01-01&end_date=' + str(NOWyr) + '-12-31&series=' + str(comicnm) + '&is_indexed=None' response = urllib2.urlopen ( input ) soup = BeautifulSoup ( response)