Created
August 13, 2012 14:58
-
-
Save ivh/3341501 to your computer and use it in GitHub Desktop.
extract emails from a set of links that have one each
This file contains hidden or 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
#!/usr/bin/env python | |
import codecs | |
import lxml.html | |
out=codecs.open('names_emails.dat','w','utf-8') | |
out2=open('emails.dat','w') | |
for link in open('comlinks.txt'): | |
html=lxml.html.parse(link) | |
d=html.xpath('.//div[@class="profile_box"]')[0] | |
dots=d.findall('.//img[@alt="."]') | |
for dot in dots: dot.text='.' | |
ats=d.findall('.//img[@alt="@"]') | |
for at in ats: at.text='@' | |
lxml.html.etree.strip_tags(d,'img') | |
x,name,x,ema=d.getchildren()[:4] | |
ema=[t for t in ema.itertext()] | |
for i,s in enumerate(ema): | |
if s.startswith('Email'): | |
email=s.split()[-1] | |
break; | |
final='"%s" <%s>'%(name.text,email) | |
print final | |
out.write(final) | |
out.write('\n') | |
out2.write('%s\n'%email) | |
name,email='','' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment