Created
July 13, 2016 15:31
-
-
Save rms1000watt/615769df8b8d97eaa7b24c46de1eb9e5 to your computer and use it in GitHub Desktop.
Python script to extract phone numbers and emails from html pages that were web scraped
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 re | |
import glob | |
def main(): | |
outputFile = 'output.tsv' | |
files = glob.glob('*.html') | |
print "Extracting from %s files" %(len(files)) | |
data = [] | |
for file in files: | |
with open(file, 'rb') as f: | |
content = f.read() | |
email = getEmail(content) | |
phone = getPhone(content) | |
name = file[:-5] | |
data.append([name, email, phone]) | |
with open(outputFile, 'wb') as f: | |
header = 'name\temail\tphone\r\n' | |
f.write(header) | |
for row in data: | |
string = '\t'.join(row) + '\r\n' | |
f.write(string) | |
def getEmail(string): | |
email = '' | |
emailRegEx = re.compile('\"mailto\:[0-9a-zA-Z\@\.]{1,}\"') | |
m = emailRegEx.search(string) | |
if m: | |
email = m.group(0)[8:-1] | |
return email | |
def getPhone(string): | |
phone = '' | |
phoneRegEx = re.compile('\"tel\:[\(\)\-0-9\ ]{1,}\"') | |
m = phoneRegEx.search(string) | |
if m: | |
phone = m.group(0)[5:-1] | |
return phone | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment