blogspot scrapper

scrap.py

"""
This script scrapes a Blogspot blog by iterating back in its history.

Usage:
    1. Provide blogspot links
    2. Press CTRL-C when you want to stop it.

Note: Your IP-number may be temporarily banned from the Blogger service if over-used.
Use on your own risk.
"""

import requests
import io
import re
from bs4 import BeautifulSoup 
file1 = open('link.txt', 'r')
lines = file1.readlines()
counter = 0

for l in lines:
    counter += 1 #Update the counter from proper filenames 
    page = requests.get(l)
    soup = BeautifulSoup(page.content, "html.parser") 
    div = soup.find_all("div", {"class": "entry"})
    with open(str(counter) + ".html", "w") as outputfile: #open file
        outputfile.write(str(div)) #write to file         
        print("Press CTRL-C to exit the program.")