Crawling emails with python

import re
import requests
import requests.exceptions
from urllib.parse import urlsplit
from collections import deque
from bs4 import BeautifulSoup

# starting url. replace google with your own url.
starting_url = 'http://www.miet.ac.in'

# a queue of urls to be crawled
unprocessed_urls = deque([starting_url])

# set of already crawled urls for email
processed_urls = set()

# a set of fetched emails
emails = set()

# process urls one by one from unprocessed_url queue until queue is empty
while len(unprocessed_urls):

    # move next url from the queue to the set of processed urls
    url = unprocessed_urls.popleft()
    processed_urls.add(url)

    # extract base url to resolve relative links
    parts = urlsplit(url)
    base_url = "{0.scheme}://{0.netloc}".format(parts)
    path = url[:url.rfind('/')+1] if '/' in parts.path else url

    # get url's content
    print("Crawling URL %s" % url)
    try:
        response = requests.get(url)
    except (requests.exceptions.MissingSchema, requests.exceptions.ConnectionError):
        # ignore pages with errors and continue with next url
        continue

    # extract all email addresses and add them into the resulting set
    # You may edit the regular expression as per your requirement
    new_emails = set(re.findall(r"[a-z0-9\.\-+_]+@[a-z0-9\.\-+_]+\.[a-z]+", response.text, re.I))
    emails.update(new_emails)
    print(emails)
    # create a beutiful soup for the html document
    soup = BeautifulSoup(response.text, 'lxml')

    # Once this document is parsed and processed, now find and process all the anchors i.e. linked urls in this document
    for anchor in soup.find_all("a"):
        # extract link url from the anchor
        link = anchor.attrs["href"] if "href" in anchor.attrs else ''
        # resolve relative links (starting with /)
        if link.startswith('/'):
            link = base_url + link
        elif not link.startswith('http'):
            link = path + link
        # add the new url to the queue if it was not in unprocessed list nor in processed list yet
        if not link in unprocessed_urls and not link in processed_urls:
            unprocessed_urls.append(link)

Source: pythoncircle.com

Similar codes

5 votes226 views3 answers
Update in django orm
Python
6 votes203 views2 answers
Flask form options
Python
0 vote227 views1 answer
Pyelastic search get document
Python
0 vote267 views1 answer
Add a new categorical column to an existing table python
Python
0 vote218 views1 answer
Geodataframe get crs
Python
0 vote208 views1 answer
Selenium proxy python chrome
Python
0 vote196 views1 answer
Python regeression line
Python
94 votes217 views5 answers
How to rename columns using panda object
Python
0 vote212 views1 answer
Set_flip_h( false )
Python
0 vote192 views10 answers
PEP 428: The pathlib module – object-oriented filesystem paths.
Python