Email Extractor

irrelevant code remove
This commit is contained in:
Sayan Roy 2022-10-09 22:01:42 +05:30 committed by GitHub
parent a9428eacd6
commit 303d1cae16
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -1,11 +1,4 @@
# -*- coding: utf-8 -*-
"""Untitled0.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1BuQhjlIL_OYu39gpE2NQNZx9KJ_kPy3o
"""
import requests
from bs4 import BeautifulSoup
@ -50,61 +43,3 @@ df.to_csv('email.csv', index=False)
files.download("email.csv")
urllib.request.urlopen('https://www.youracclaim.com/badges/42b5d2d4-7c14-4c1a-b78a-adb3ac04105b/public_url').read().decode("utf-8")
import urllib.request
fp = urllib.request.urlopen("http://royninja.github.io/contact.html")
mybytes = fp.read()
mystr = mybytes.decode("utf8")
fp.close()
print(mystr)
import urllib.request
fp = urllib.request.urlopen("http://royninja.github.io/contact.html")
mybytes = fp.read()
mystr = mybytes.decode("utf8")
fp.close()
print(mystr)
webUrl = urllib.request.urlopen("https://royninja.github.io")
pip install email-scraper
scrape_emails(mystr)
import requests
from bs4 import BeautifulSoup
url = 'https://royninja.github.io/'
reqs = requests.get(url)
soup = BeautifulSoup(reqs.text, 'html.parser')
urls = []
for link in soup.find_all('a'):
urls.append(link.get('href'))
urls[1]
url+urls[1]
BufautifulSoup(requests.get(url+urls[1]).text,'html.parser')
url2