tos_report_crawler.py

import requests
import threading
from lxml import etree

# Variables =)
users = ["muhtrix", "Tomsi203", "ShivaLu", "Zael17"]
startRange = 3341838
chunks = 50

xreporter = '//*[@id="reportInfo"]/div[3]/span[2]/span[1]'
xreason   = '//*[@id="reportInfo"]/div[6]/span[2]/span'

def check_id_advanced(i):
    r = requests.get('https://www.blankmediagames.com/Trial/viewReport.php?id=' + str(i))
    tree = etree.HTML(r.text)
    reporter = tree.xpath(xreporter)
    reason = tree.xpath(xreason)
    
    if len(reporter) > 0:
        for user in users:
            if (reporter[0].text.find(user) != -1):
                print("\n")
                print("####### REPORT: " + user + " #######")

                reason = tree.xpath(xreason)
                if len(reason) > 0:
                    print("####### REASON: " + reason[0].text + " #######")

                print("https://www.blankmediagames.com/Trial/viewReport.php?id=" + str(i))


if __name__ == "__main__":
    i = startRange
    while i < len(range(4000000)):
        threads = list()

        for chunk in range(chunks):
            x = threading.Thread(target=check_id_advanced, args=(i+chunk,), daemon=True)
            threads.append(x)

            if (i+chunk) % 100 == 0:
                print("@" + str(i+chunk))

        for thread in threads:
            thread.start()

        for thread in threads:
            thread.join()

        i = i + chunks