-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathscraper.py
More file actions
executable file
·24 lines (18 loc) · 799 Bytes
/
scraper.py
File metadata and controls
executable file
·24 lines (18 loc) · 799 Bytes
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
#!/usr/bin/python
from BeautifulSoup import BeautifulSoup
import urllib, urllib2
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)
linkdictionary = {}
for li in soup.findAll('li', attrs={'class':'g'}):
sLink = li.find('a')
print sLink['href']
sSpan = li.find('span', attrs={'class':'st'})
print sSpan
return linkdictionary
if __name__ == '__main__':
links = google_scrape('beautifulsoup')