2012-12-16 17:57:02 +00:00
|
|
|
#!/usr/bin/env python
|
|
|
|
|
|
|
|
import os
|
|
|
|
import sys
|
|
|
|
import lib.feedparser as feedparser
|
|
|
|
#import feedparser
|
|
|
|
import re
|
2013-01-02 17:56:46 +00:00
|
|
|
import logger
|
2013-02-09 03:34:02 +00:00
|
|
|
import mylar
|
2013-04-12 02:14:27 +00:00
|
|
|
import unicodedata
|
2012-12-16 17:57:02 +00:00
|
|
|
|
2013-04-12 02:14:27 +00:00
|
|
|
|
|
|
|
def Startit(searchName, searchIssue, searchYear, ComicVersion):
|
2012-12-16 17:57:02 +00:00
|
|
|
#searchName = "Uncanny Avengers"
|
|
|
|
#searchIssue = "01"
|
|
|
|
#searchYear = "2012"
|
|
|
|
#clean up searchName due to webparse.
|
|
|
|
searchName = searchName.replace("%20", " ")
|
2013-05-09 02:22:47 +00:00
|
|
|
if "," in searchName:
|
|
|
|
searchName = searchName.replace(",", "")
|
2013-01-02 17:56:46 +00:00
|
|
|
logger.fdebug("name:" + str(searchName))
|
|
|
|
logger.fdebug("issue:" + str(searchIssue))
|
|
|
|
logger.fdebug("year:" + str(searchYear))
|
2012-12-16 17:57:02 +00:00
|
|
|
splitSearch = searchName.split(" ")
|
|
|
|
joinSearch = "+".join(splitSearch)+"+"+searchIssue
|
|
|
|
searchIsOne = "0"+searchIssue
|
|
|
|
searchIsTwo = "00"+searchIssue
|
|
|
|
|
2013-04-12 02:14:27 +00:00
|
|
|
if "-" in searchName:
|
|
|
|
searchName = searchName.replace("-", '((\\s)?[-:])?(\\s)?')
|
|
|
|
|
|
|
|
regexName = searchName.replace(" ", '((\\s)?[-:])?(\\s)?')
|
|
|
|
|
|
|
|
|
2013-02-09 03:34:02 +00:00
|
|
|
if mylar.USE_MINSIZE:
|
|
|
|
size_constraints = "minsize=" + str(mylar.MINSIZE)
|
|
|
|
else:
|
|
|
|
size_constraints = "minsize=10"
|
2012-12-16 17:57:02 +00:00
|
|
|
|
2013-02-09 03:34:02 +00:00
|
|
|
if mylar.USE_MAXSIZE:
|
|
|
|
size_constraints = size_constraints + "&maxsize=" + str(mylar.MAXSIZE)
|
|
|
|
|
2013-03-01 20:20:39 +00:00
|
|
|
if mylar.USENET_RETENTION != None:
|
|
|
|
max_age = "&age=" + str(mylar.USENET_RETENTION)
|
|
|
|
|
2013-04-14 06:56:12 +00:00
|
|
|
feed = feedparser.parse("http://nzbindex.nl/rss/alt.binaries.comics.dcp/?sort=agedesc&" + str(size_constraints) + str(max_age) + "&dq=%s&max=50&more=1" %joinSearch)
|
2012-12-16 17:57:02 +00:00
|
|
|
|
|
|
|
totNum = len(feed.entries)
|
|
|
|
|
|
|
|
keyPair = {}
|
|
|
|
regList = []
|
|
|
|
entries = []
|
|
|
|
mres = {}
|
|
|
|
countUp = 0
|
|
|
|
|
2013-01-02 17:56:46 +00:00
|
|
|
logger.fdebug(str(totNum) + " results")
|
2012-12-16 17:57:02 +00:00
|
|
|
|
|
|
|
while countUp < totNum:
|
|
|
|
urlParse = feed.entries[countUp].enclosures[0]
|
|
|
|
#keyPair[feed.entries[countUp].title] = feed.entries[countUp].link
|
|
|
|
keyPair[feed.entries[countUp].title] = urlParse["href"]
|
|
|
|
|
|
|
|
countUp=countUp+1
|
|
|
|
|
|
|
|
|
2013-04-12 02:14:27 +00:00
|
|
|
# thanks to SpammyHagar for spending the time in compiling these regEx's!
|
2012-12-16 17:57:02 +00:00
|
|
|
|
2013-04-12 02:14:27 +00:00
|
|
|
regExTest=""
|
2012-12-16 17:57:02 +00:00
|
|
|
|
2013-04-12 02:14:27 +00:00
|
|
|
regEx = "(%s\\s*(0)?(0)?%s\\s*\\(%s\\))" %(regexName, searchIssue, searchYear)
|
|
|
|
regExOne = "(%s\\s*(0)?(0)?%s\\s*\\(.*?\\)\\s*\\(%s\\))" %(regexName, searchIssue, searchYear)
|
2012-12-16 17:57:02 +00:00
|
|
|
|
2013-04-12 02:14:27 +00:00
|
|
|
#Sometimes comics aren't actually published the same year comicVine says - trying to adjust for these cases
|
|
|
|
regExTwo = "(%s\\s*(0)?(0)?%s\\s*\\(%s\\))" %(regexName, searchIssue, int(searchYear)+1)
|
|
|
|
regExThree = "(%s\\s*(0)?(0)?%s\\s*\\(%s\\))" %(regexName, searchIssue, int(searchYear)-1)
|
|
|
|
regExFour = "(%s\\s*(0)?(0)?%s\\s*\\(.*?\\)\\s*\\(%s\\))" %(regexName, searchIssue, int(searchYear)+1)
|
|
|
|
regExFive = "(%s\\s*(0)?(0)?%s\\s*\\(.*?\\)\\s*\\(%s\\))" %(regexName, searchIssue, int(searchYear)-1)
|
2012-12-16 17:57:02 +00:00
|
|
|
|
2013-04-12 02:14:27 +00:00
|
|
|
regexList=[regEx, regExOne, regExTwo, regExThree, regExFour, regExFive]
|
2012-12-16 17:57:02 +00:00
|
|
|
|
|
|
|
for title, link in keyPair.items():
|
2013-07-10 01:45:10 +00:00
|
|
|
logger.fdebug("titlesplit: " + str(title.split("\"")))
|
2013-04-12 02:14:27 +00:00
|
|
|
splitTitle = title.split("\"")
|
|
|
|
|
|
|
|
for subs in splitTitle:
|
2013-07-10 01:45:10 +00:00
|
|
|
logger.fdebug(subs)
|
2013-04-12 02:14:27 +00:00
|
|
|
regExCount = 0
|
|
|
|
if len(subs) > 10:
|
|
|
|
#Looping through dictionary to run each regEx - length + regex is determined by regexList up top.
|
2013-07-10 01:45:10 +00:00
|
|
|
# while regExCount < len(regexList):
|
|
|
|
# regExTest = re.findall(regexList[regExCount], subs, flags=re.IGNORECASE)
|
|
|
|
# regExCount = regExCount +1
|
|
|
|
# if regExTest:
|
|
|
|
# logger.fdebug(title)
|
|
|
|
# entries.append({
|
|
|
|
# 'title': subs,
|
|
|
|
# 'link': str(link)
|
|
|
|
# })
|
|
|
|
entries.append({
|
|
|
|
'title': subs,
|
|
|
|
'link': str(link)
|
|
|
|
})
|
|
|
|
|
2012-12-16 17:57:02 +00:00
|
|
|
|
|
|
|
if len(entries) >= 1:
|
|
|
|
mres['entries'] = entries
|
|
|
|
return mres
|
|
|
|
# print("Title: "+regList[0])
|
|
|
|
# print("Link: "+keyPair[regList[0]])
|
|
|
|
else:
|
2013-01-02 17:56:46 +00:00
|
|
|
logger.fdebug("No Results Found")
|
2012-12-16 17:57:02 +00:00
|
|
|
return "no results"
|