def runSitemapCrawler(self):
startTime = time.time()
headers = {
'User-Agent':
"Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Mobile Safari/537.36"
}
xmlQueue = set()
xmlQueue.add(self.sitemapURL)
htmlQueue = set()
log('sitemap', 'Crawling XML Sitemap for ' + self.siteName)
while (len(xmlQueue) != 0):
nextParse = requests.get(xmlQueue.pop(), headers=headers)
newXMLLinks = self.findNewLinksXML(nextParse)
for link in newXMLLinks:
if '.xml' in link:
if 'archive' not in link:
xmlQueue.add(link)
else:
htmlQueue.add(link)
FileIO.deleteFileContents(self.crawledFile)
FileIO.setToFile(htmlQueue, self.crawledFile)
log(
'time', 'Finished crawling XML sitemap for ' + self.siteName +
' in ' + str(time.time() - startTime) + ' seconds')
def runParser(self):
FileIO.deleteFileContents(self.indexFile)
if not os.path.isfile(self.crawledFile):
log('error', 'No crawled file.')
return self
self.links = FileIO.fileToSet(self.crawledFile)
self.linksList = list(self.links)
if not self.links:
log('error', 'Crawled file is empty')
return self
threadPool = []
for i in range(0, self.MAX_THREADS):
newThread = Thread(name='parser_' + str(i),
target=self.parserWorker)
threadPool.append(newThread)
for i in range(0, self.MAX_THREADS):
threadPool[i].start()
for i in range(0, self.MAX_THREADS):
threadPool[i].join()
self.saveLinkGraphs()
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 saveConfigFile(self):
'''
method when pressing Menu item for loading config file
'''
savefile = QFileDialog.getSaveFileName(self,
'Select where the config file should be saved',self.lastdir)
if not savefile:
return
file_obj = FileIO(savefile)
file_obj.writeFile(self, ParameterWrap)
self.lastdir = self.dirs.getParentDir(str(savefile))
def saveConfigFile(self):
'''
method when pressing Menu item for loading config file
'''
savefile = QFileDialog.getSaveFileName(
self, 'Select where the config file should be saved', self.lastdir)
if not savefile:
return
file_obj = FileIO(savefile)
file_obj.writeFile(self, ParameterWrap)
self.lastdir = self.dirs.getParentDir(str(savefile))
def setup():
""" Read book info from file, if file exists. """
global counter
data = fileIO.readAsString(BOOKS_FILE_NAME)
if len(data) > 0:
make_book_list(data)
counter = fileIO.readAsPosInt(COUNTER_FILE_NAME)
if counter == -1:
counter = len(book_list)
def loadConfigFile(self):
'''
method for loading config-file (from Menu item)
'''
loadfile = QFileDialog.getOpenFileName(self,
'Select where the config file is located',self.lastdir)
if not loadfile:
return
file_obj = FileIO(loadfile)
file_obj.loadFile(self,ParameterWrap)
self.dirs.inputdir = self.inputdirectory.text()
self.dirs.initSinDirectory()
self.lastdir = self.dirs.getParentDir(str(loadfile))
def __init__(self, siteName, baseURL):
self.siteName = siteName
self.baseURL = baseURL
FileIO.createSiteFileSetup(self.siteName, self.baseURL)
self.queueFile = 'domains/' + siteName + '/' + siteName + '_queue.txt'
self.crawledFile = 'domains/' + siteName + '/' + siteName + '_crawled.txt'
self.queue = set()
self.crawled = set()
self.numCrawled = 0
self.outlinkGraph = Graph()
self.inlinkGraph = Graph()
self.inlinkGraphFile = 'domains/' + siteName + '/' + siteName + '_inlinks.json'
self.outlinkGraphFile = 'domains/' + siteName + '/' + siteName + '_outlinks.json'
self.sitemapURL = self.findXMLSitemap()
def loadConfigFile(self):
'''
method for loading config-file (from Menu item)
'''
loadfile = QFileDialog.getOpenFileName(
self, 'Select where the config file is located', self.lastdir)
if not loadfile:
return
file_obj = FileIO(loadfile)
file_obj.loadFile(self, ParameterWrap)
self.dirs.inputdir = self.inputdirectory.text()
self.dirs.initSinDirectory()
self.lastdir = self.dirs.getParentDir(str(loadfile))
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 search(self):
path = 'search_index'
for file in os.listdir(path):
if file.endswith(".json") or file.endswith(".txt"):
indices = FileIO(path + '/' + file).read_file()["indices"]
for object in indices:
print object["word_index"]
if self.check_words(object["word_index"]) > 0:
self.results.append(object)
def record(self):
"""Start or end recording
"""
if self.camera.is_recording:
self.camera.stop_recording()
self.rec_button.setText('&Rec')
self.rec_act.setText('&Record')
self.write_text("save : {}".format(self.video_filename))
else:
self.video_filename = FileIO.get_filename(self.filename_rule, self.video_suffix, self.parent_dir)
self.camera.start_recording(self.video_filename, self.video_codec)
self.rec_button.setText('Stop rec')
self.rec_act.setText('Stop record')
def __init__(self, siteName, baseURL, threads):
self.siteName = siteName
self.baseURL = baseURL
self.crawledFile = 'domains/' + siteName + '/' + siteName + '_crawled.txt'
self.indexFile = FileIO.createSiteIndexFile(self.siteName)
self.links = set()
self.linksList = None
self.readSemaphore = True
self.writeSemaphore = True
self.MAX_THREADS = threads
self.inlinkGraph = Graph()
self.outlinkGraph = Graph()
self.inlinkGraphFile = 'domains/' + siteName + '/' + siteName + '_inlinks.json'
self.outlinkGraphFile = 'domains/' + siteName + '/' + siteName + '_outlinks.json'
def parserWorker(self):
buffer = []
while (len(self.linksList) > 0):
while (not self.readSemaphore):
pass
self.readSemaphore = False
start = len(self.linksList) - DataParser.MAX_BUFFER_LEN - 1 if len(
self.linksList) > DataParser.MAX_BUFFER_LEN else 0
end = len(self.linksList)
toParse = self.linksList[start:end]
del self.linksList[start:end]
self.readSemaphore = True
for link in toParse:
obj = extractData(link)
self.addNewLinksToGraphs(obj['link'], obj['newLinks'])
buffer.append('link: ' + link + '\n')
title = obj['title'] if obj['title'] != None else self.siteName
buffer.append('title: ' + title + '\n')
buffer.append('description: ' + obj['description'] + '\n', )
beforeCleanupBody = obj['body'].replace('\n', ' ')
afterCleanupBody = ' '.join(beforeCleanupBody.split())
buffer.append('body: ' + afterCleanupBody + '\n\n')
while (not self.writeSemaphore):
pass
self.writeSemaphore = False
FileIO.writeToFile(self.indexFile, "".join(buffer))
self.writeSemaphore = True
buffer[:] = []
def shutdown():
"""Save all data to a file - one for books, one for the current counter value, for persistent storage"""
output_data = make_output_data()
# Create data directory
fileIO.mkdir(DATA_DIR)
# write data to file
fileIO.overwrite(BOOKS_FILE_NAME, output_data)
# write counter to data
fileIO.overwrite(COUNTER_FILE_NAME, counter)
def run(self):
for url_object in self.url_list:
extract_object = extraction.Extraction(url_object)
url_object['word_index'] = extract_object.get_text()
# try:
# # open('search_index/' + data.index_file, 'w')
# file = FileIO('search_index/' + data.index_file)
# print file.create_file(url_object)
# except:
# file = FileIO('search_index/' + data.index_file)
# print file.create_file(url_object)
# file = FileIO('search_index/' + data.get_index_file())
# print file.create_file(url_object)
# f = open(os.path.dirname(__file__) + '/../data.yml')
if os.path.isfile('../search_index/' + data.index_file):
file = FileIO('../search_index/' + data.index_file)
file.update_file(url_object)
else:
file = FileIO('../search_index/' + data.index_file)
file.create_file(url_object)
def save_frame(self):
"""Save the frame on the window as an image.
"""
if self.filename_rule == "Manual":
self.save_frame_manual()
if not self.filename:
return None
prm = re.sub(r"\.(.*)", ".csv", str(self.filename))
else:
self.filename = FileIO.get_filename(self.filename_rule, self.image_suffix, self.parent_dir)
prm = str(self.filename).replace(self.image_suffix, "csv")
if not self.dst.exists():
self.dst.mkdir(parents=True)
im = Image.fromarray(self.camera.frame)
im.save(self.filename)
# make a parameter file
with open(prm, "w") as f:
for name, key in self.current_params.items():
f.write("{},{}\n".format(name, self.current_params[name]["value"]))
self.write_text("{:<10}: {}".format("save image", self.filename))
self.write_text("{:<10}: {}".format("save param", prm))
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)
def saveLinkGraphs(self):
FileIO.writeJsonFile(self.outlinkGraph.nodes, self.outlinkGraphFile)
FileIO.writeJsonFile(self.inlinkGraph.nodes, self.inlinkGraphFile)
def getUrls(file):
fileio = FileIO()
return fileio.fileRead(file)
def runSpider(self, iterations):
startTime = time.time()
for i in range(0, iterations):
self.queue = FileIO.fileToSet(self.queueFile)
self.crawled = FileIO.fileToSet(self.crawledFile)
newLinks = set()
newCrawledLinks = set()
while (len(self.queue) != 0):
nextLink = self.queue.pop()
res = self.crawlPage(nextLink)
newCrawledLinks.add(nextLink)
newLinks = newLinks.union(res)
FileIO.deleteFileContents(self.queueFile)
FileIO.setToFile(newLinks, self.queueFile)
FileIO.setToFile(newCrawledLinks, self.crawledFile)
FileIO.writeJsonFile(self.outlinkGraph.nodes, self.outlinkGraphFile)
FileIO.writeJsonFile(self.inlinkGraph.nodes, self.inlinkGraphFile)
log(
'time', "Crawler for " + self.siteName +
" execution Finished. Runtime: " + str(time.time() - startTime) +
"seconds. Total links crawled: " + str(self.numCrawled))
def multiple_search(self, file):
path = 'search_index'
indices = FileIO(path + '/' + file).read_file()["indices"]
for object in indices:
if self.check_words(object["word_index"]) > 0:
self.results.append(object)
def __init__(self, *args, **kwargs): FileIO.__init__(self, *args, **kwargs) self.data_list = [] self.stemmer = PorterStemmer() # correct syntax? self.score_map = self.ranges =
from os import path
intention = sys.argv[1]
midi_file_name = sys.argv[2]
name = None
if intention == "-hide":
message_file_name = sys.argv[3]
if path.isfile(midi_file_name):
if path.isfile(message_file_name):
parts = midi_file_name.split(".")
extension = parts[-1]
if extension != "mid":
print "The file must have a .mid extension"
else:
fileIO = FileIO()
message = fileIO.get_text_from(message_file_name)
hider = Hider()
hider.hide(midi_file_name, message)
print "The output file name will be: " "secret_in_" + midi_file_name
else:
print "You must put the message file in the same directory as midistegano.py"
else:
print "You must put the .mid file in the same directory as run.py"
elif intention == "-reveal":
if path.isfile(midi_file_name):
parts = midi_file_name.split(".")
name = parts[0]
extension = parts[-1]
def __init__(self, siteName):
self.siteName = siteName
self.crawledFile = 'domains/' + siteName + '/' + siteName + '_crawled.txt'
self.indexFile = FileIO.createSiteIndexFile(self.siteName)
self.links = set()
def __init__(self, *args, **kwargs):
FileIO.__init__(self, *args, **kwargs)
self.data_list = []
from book import Book
from fileIO import FileIO as fileIO
from datetime import date
from pprint import pprint # debugging tool
import json
DATA_DIR = 'data'
BOOKS_FILE_NAME = str(fileIO.pathJoin(DATA_DIR, 'wishlist.txt'))
COUNTER_FILE_NAME = str(fileIO.pathJoin(DATA_DIR, 'counter.txt'))
separator = '^^^' # a string probably not in any valid data relating to a book
book_list = []
counter = 0
def setup():
""" Read book info from file, if file exists. """
global counter
data = fileIO.readAsString(BOOKS_FILE_NAME)
if len(data) > 0:
make_book_list(data)
counter = fileIO.readAsPosInt(COUNTER_FILE_NAME)
if counter == -1:
counter = len(book_list)
def is_book(book_id):
def __init__(self, *args, **kwargs): FileIO.__init__(self, *args, **kwargs) self.data_list = []
def main():
print("Iniciando...")
file = FileIO("./test.txt")
vec = file.read_as_vector()
print(vec)
from fileIO import FileIO
from preprocess import Preprocessing
from decisionTree import DecisionTree
if __name__ == '__main__':
filename = 'house-votes-84.data.txt'
fileio = FileIO()
data = fileio.read_csv(filename)
preprocessing = Preprocessing()
preprocessing.assume_missing_values(data)
for percent in range(3, 8):
training_data, testing_data = preprocessing.split_into_training_and_testing(data, percent/float(10))
attributes_number = len(training_data[0]) - 1
decision_tree = DecisionTree()
root_node = decision_tree.build(training_data)
# decision_tree.print()
# print("Classification: ")
accuracy = 0
for row in testing_data:
classified = decision_tree.classify(row, decision_tree.root)
classified.calc_percentages(len(testing_data))
if classified.republicans_percent > 50.0 and row[0] == 'republican' or (
classified.democrats_percent > 50.0 and row[0] == 'democrat'):
accuracy += 1
accuracy = accuracy / float(len(testing_data))
print("Accuracy using training data", percent/float(10)*100, "% is: ", accuracy)
def __init__(self, *args, **kwargs):
FileIO.__init__(self, *args, **kwargs)
self.is_flat = False
