|
import os
|
|
from Forums.OnniForums.parser import onniForums_description_parser
|
|
from Forums.OnniForums.parser import onniForums_listing_parser
|
|
from bs4 import BeautifulSoup
|
|
|
|
baseUrl = './HTML_Pages/06272023/Listing/httponnii6niq53gv3rvjpi7z5axkasurk2x5w5lwliep4qyeb2azagxn4qdonionForumCardingFraud.html'
|
|
|
|
with open(baseUrl, 'r') as file:
|
|
testHTML = file.read()
|
|
|
|
soup = BeautifulSoup(testHTML, 'html.parser')
|
|
|
|
output = onniForums_listing_parser(soup)
|
|
|
|
print(output)
|
|
|
|
all_descriptions = os.listdir("./HTML_Pages/06272023/Description/")[1:]
|
|
|
|
total = len(all_descriptions)
|
|
descriptions_with_unicode_error = 0
|
|
|
|
print("\nTESTING DESCRIPTION PARSER:\n")
|
|
|
|
for desc in all_descriptions:
|
|
|
|
print(f"\nTesting: ./HTML_Pages/06272023/Description/{desc} \n")
|
|
|
|
|
|
|
|
try:
|
|
with open(f"./HTML_Pages/06272023/Description/{desc}", "r") as file:
|
|
test_html = file.read()
|
|
|
|
soup = BeautifulSoup(test_html, features="html.parser")
|
|
|
|
description_output = onniForums_description_parser(soup)
|
|
|
|
print(f"\nTopic name : {description_output[0]}")
|
|
print(f"Contents : {description_output[1]}")
|
|
print(f"Users : {description_output[2]}")
|
|
print(f"Dates posted: {description_output[3]}")
|
|
print(f"Feedbacks : {description_output[4]}")
|
|
print(f"Statuses : {description_output[5]}")
|
|
print(f"Reputations : {description_output[6]}")
|
|
print(f"Signatures : {description_output[7]}")
|
|
print(f"Interests : {description_output[8]}\n")
|
|
|
|
except UnicodeDecodeError:
|
|
descriptions_with_unicode_error += 1
|
|
print(f"UnicodeDecodeError: the file `{desc}` cannot be decoded by Python!")
|
|
|
|
print("\nTESTING COMPLETE\n")
|
|
print(f"Number of descriptions : {total}")
|
|
print(f"Descriptions w/ errors : {descriptions_with_unicode_error}")
|
|
print(f"Failure percentage : {round(descriptions_with_unicode_error/total, 4) * 100}%\n")
|
|
|
|
|