Last active
October 24, 2016 17:17
-
-
Save shafayeatsumit/9c33438d8c1a452417ca1a088df05c88 to your computer and use it in GitHub Desktop.
scrape first few pages in google
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
from bs4 import BeautifulSoup | |
import urllib,urllib2 | |
import re | |
def google_scrape(query): | |
address = "http://www.google.com/search?q=%s&num=100&hl=en&start=0" % (urllib.quote_plus(query)) | |
request = urllib2.Request(address, None, {'User-Agent':'Mosilla/5.0 (Macintosh; Intel Mac OS X 10_7_4) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11'}) | |
urlfile = urllib2.urlopen(request) | |
page = urlfile.read() | |
soup = BeautifulSoup(page) | |
text= soup.get_text() | |
new_emails = set(re.findall(r"[a-z0-9\.\-+_]+@[a-z0-9\.\-+_]+\.[a-z]+", text, re.I)) | |
print new_emails | |
if __name__ == '__main__': | |
links = google_scrape('mafinar khan email') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment