python 如何:使用Python和Google查找数百个电子邮件地址
Posted
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了python 如何:使用Python和Google查找数百个电子邮件地址相关的知识,希望对你有一定的参考价值。
#!/usr/bin/python
import sys
import re
import string
import httplib
import urllib2
import re
def StripTags(text):
finished = 0
while not finished:
finished = 1
start = text.find("<")
if start >= 0:
stop = text[start:].find(">")
if stop >= 0:
text = text[:start] + text[start+stop+1:]
finished = 0
return text
if len(sys.argv) != 2:
print "\nrsx.py : Find hundreds of e-mail adresses on Google.\n"
print "\nUsage : ./rsx.py \n"
print "\nexemple: ./rsx.py gmail.com \n"
sys.exit(1)
domain_name=sys.argv[1]
d={}
page_counter = 0
try:
while page_counter <400:
results = 'http://groups.google.com/groups?q='+str(domain_name)+'&hl=en&lr=&ie=UTF-8&start=' + repr(page_counter) + '&sa=N'
request = urllib2.Request(results)
request.add_header('User-Agent','Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0)')
opener = urllib2.build_opener()
text = opener.open(request).read()
emails = (re.findall('([\w\.\-]+@'+domain_name+')',StripTags(text)))
for email in emails:
d[email]=1
uniq_emails=d.keys()
page_counter = page_counter +10
except IOError:
print "No result found!"+""
page_counter_web=0
try:
print "\n\n+++++++++++++++++++++++++++++++++++++++++++++++++++++"+""
print "+ Results:"+""
print "+++++++++++++++++++++++++++++++++++++++++++++++++++++\n\n"+""
while page_counter_web >400 :
results_web = 'http://www.google.com/search?q=%40'+str(domain_name)+'&hl=en&lr=&ie=UTF-8&start=' + repr(page_counter_web) + '&sa=N'
request_web = urllib2.Request(results_web)
request_web.add_header('User-Agent','Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0)')
opener_web = urllib2.build_opener()
text = opener_web.open(request_web).read()
emails_web = (re.findall('([\w\.\-]+@'+domain_name+')',StripTags(text)))
for email_web in emails_web:
d[email_web]=1
uniq_emails_web=d.keys()
page_counter_web = page_counter_web +10
except IOError:
print "No results found!"+""
for uniq_emails_web in d.keys():
print uniq_emails_web+""
以上是关于python 如何:使用Python和Google查找数百个电子邮件地址的主要内容,如果未能解决你的问题,请参考以下文章
如何使用 Python 运行 Google gsutil
如何使用GAE收听Google表格,然后运行一组python代码?
如何在Google App Engine上建立flex和python代码之间的通信
如何使用 Python 控制 Google Hangouts?
如何在 python 中使用现有的 google chrome 配置文件和 selenium chrome webdriver?
如何将 AJAX 与 Google App Engine (Python) 结合使用