def __init__(self, domain, threads, mode='DEV'):
self.domain = domain
self.mode = mode
self.MAX_THREADS = threads
self.buildQueue = []
self.readSemaphore = True
self.invertedIndexSemaphore = True
self.hubAuthFile = 'domains/' + self.domain + '/' + self.domain + "_HubAuth.json"
self.hubAuthScores = FileIO.readJsonFile(self.hubAuthFile)
self.pageRankFile = 'domains/' + self.domain + '/' + self.domain + "_pageRank.json"
self.pageRanks = FileIO.readJsonFile(self.pageRankFile)
def build(self):
filePath = 'domains/' + self.domain + '/' + self.domain + "_index.txt"
pageRankFile = 'domains/' + self.domain + '/' + self.domain + "_pageRank.json"
rawData = FileIO.readJsonFile(filePath)
count = 0
for entry in rawData.keys():
count += 1
doc = rawData[entry]
if doc['title'] == None:
doc['title'] = 'No Title'
self.addDocumentToCollection(
url=entry,
title=doc['title'],
body=doc['body'],
description=doc['description'],
pageRank=self.pageRanks[entry],
hub=self.hubAuthScores[doc['title']][0],
authority=self.hubAuthScores[doc['title']][1])
self.buildInvertedIndex(doc['body'], entry)
if self.mode == 'DEV' and count >= 5:
break
def runParser(self):
if not os.path.isfile(self.crawledFile):
log('error', 'No crawled file.')
return self
self.links = FileIO.fileToSet(self.crawledFile)
if not self.links:
log('error', 'Crawled file is empty')
return self
data = FileIO.readJsonFile(self.indexFile)
for link in self.links:
if link not in data:
obj = extractData(link)
data[link] = {
'docId': DataParser.docId,
'title': obj['title'],
'body': obj['body']
}
DataParser.docId += 1
FileIO.deleteFileContents(self.indexFile)
FileIO.writeJsonFile(data, self.indexFile)
