Created
July 30, 2019 03:21
-
-
Save zenosxx/0809d9f6a77cbda894c66e130358e05a to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests,re,os,schedule,time,subprocess | |
from bs4 import BeautifulSoup | |
from urllib.parse import urlparse | |
from sendgrid import SendGridAPIClient | |
from sendgrid.helpers.mail import Mail | |
url=str(input("Enter domain:\n")) | |
#using request module to fetch html page | |
def fetch(url): | |
try: | |
data = requests.get(url,timeout=10) | |
print(url) | |
return data.text | |
except requests.exceptions.RequestException as e: | |
return "None" | |
#using html parser to grab script tag src and saving into List | |
def grab_js(url): | |
data = [] | |
content=fetch(url) | |
soup = BeautifulSoup(content, 'html.parser') | |
soup = soup.find_all('script') | |
for url in soup: | |
data.append(url.get('src')) | |
data = list(filter(None,data)) | |
print(data) | |
return data | |
#using regex to find and add domain to relative url | |
def check(): | |
url_check=grab_js(url) | |
for i in range(0,len(url_check)): | |
regex=re.search('https?|//',url_check[i]) | |
if regex == None: | |
url_check[i] = url+url_check[i] | |
return url_check | |
#sudo npm install -g diff2html-cli | |
#using diff to compare & diff2html-cli for templating | |
def report(original,duplicate,reportname): | |
cmd="diff -u "+ original +" "+ duplicate + "| diff2html -i stdin -F data/report/"+reportname | |
output = subprocess.check_output(cmd, shell=True) | |
if "support" in output.decode("utf-8"): | |
print("No New Changes Detected..") | |
else: | |
report = subprocess.check_output('cat data/report/'+reportname, shell=True) | |
report = report.decode("utf-8") | |
send_report(report) | |
print("reporting done") | |
url_list=check() | |
def save_list(): | |
save = open("list.txt","w") | |
for i in range(0,len(url_list)): | |
save.write(url_list[i]+"\n") | |
def original(): | |
for i in range(0,len(url_list)): | |
#print(url_list[i]) | |
data=fetch(url_list[i]) | |
file = open('data/original/'+os.path.basename(url_list[i]), "w") | |
file.write(data) | |
def duplicate(): | |
for i in range(0,len(url_list)): | |
#print(url_list[i]) | |
data=fetch(url_list[i]) | |
file = open('data/duplicate/'+os.path.basename(url_list[i]), "w") | |
file.write(data) | |
original() | |
#save_list() | |
def job(): | |
print("Schedule Job Started running...") | |
duplicate() | |
for i in range(0,len(url_list)): | |
filename=os.path.basename(url_list[i]) | |
timestamp=str(int(time.time())) | |
report('data/original/'+filename,'data/duplicate/'+filename,timestamp+filename+".html") | |
original() | |
def send_report(data_report): | |
message = Mail(from_email='', | |
to_emails='', | |
subject='Sending with Twilio SendGrid is Fun', | |
html_content=data_report) | |
try: | |
sg = SendGridAPIClient('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') | |
response = sg.send(message) | |
print(response.status_code) | |
except Exception as e: | |
print(str(e)) | |
schedule.every(5).seconds.do(job) | |
while True: | |
schedule.run_pending() | |
time.sleep(1) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment