Last active
August 29, 2015 14:21
-
-
Save theSage21/947323396fa9b8225c53 to your computer and use it in GitHub Desktop.
Email extractor from html table.
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 os | |
import re | |
from bs4 import BeautifulSoup | |
def get_files(): | |
folder = os.path.join(os.getcwd(), 'html') | |
names = [os.path.join(folder, i) for i in os.listdir(folder)] | |
names.sort() | |
return names | |
def get_html(filename): | |
print('Getting html') | |
f = open(filename, 'r') | |
html = ''.join(f.readlines()) | |
f.close() | |
html = html.replace('(at)', '@') | |
html = html.replace('(dot)', '.') | |
return html | |
def get_emails(html): | |
print('boiling soup') | |
soup = BeautifulSoup(html) | |
print('getting html') | |
td = [i.text for i in soup.findAll('td')] | |
lines = ' '.join(td) | |
print('doing regex matching') | |
email_regex = re.compile(r'<[^<>]+?@gmail\.com>') | |
emails = [i[1:-1] for i in email_regex.findall(lines)] | |
return emails | |
if __name__ == '__main__': | |
files = get_files() | |
for f in files: | |
print(f) | |
html = get_html(f) | |
emails = get_emails(html) | |
print(len(emails), 'found') | |
fl = open('mails', 'a') | |
fl.writelines([i + '\n' for i in emails]) | |
fl.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment