import time, sys, re
class ParserTest:
def tomegabytes(string):
spl = string.split(" ")
if spl[1] == 'MB':
return float(spl[0])
if spl[1] == 'GB':
return float(spl[0])*1000
downs = {
'tvsdx264': 'Scott_And_Bailey',
'moviesdvdr': 'Die.Slow'
}
testInp = "NEW in TV/SD-X264: -> Embarrassing.Bodies.S06E04.WS.PDTV.x264-C4TV (Uploaded 28 seconds after pre) - (299.39 MB) - (http://www.sceneaccess.org/details.php?id=537074)"
m = re.findall('(?<=NEW in ).+(?=\: )', testInp)
a = re.findall('(?<= -> ).+(?= \(Uploaded)', testInp)
s = re.findall('\d+.\d+ [G|M]B', testInp)
u = re.findall('(?<=http://www\.sceneaccess\.org/details\.php\?id\=)\d+(?=\))', testInp)
if m and a and s and u:
cat = m[0].replace("/","").replace("-","").lower()
rel = a[0]
size = tomegabytes(s[0])
tId = u[0]
print "Maths: %s, %s, %s %s" %(cat, rel, size, tId)
else:
print "No match"
if __name__ == '__main__':
p = ParserTest()