Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- #!/usr/bin/python
- import json
- import urllib
- def showsome(searchfor):
- query = urllib.urlencode({'q': searchfor})
- url = 'http://ajax.googleapis.com/ajax/services/search/web?v=1.0&%s' % query
- search_response = urllib.urlopen(url)
- search_results = search_response.read()
- results = json.loads(search_results)
- data = results['responseData']
- print 'Total results: %s' % data['cursor']['estimatedResultCount']
- hits = data['results']
- print 'Top %d hits:' % len(hits)
- for h in hits: print ' ', h['url']
- print 'For more results, see %s' % data['cursor']['moreResultsUrl']
- showsome('ermanno olmi')
- #!/usr/bin/python3
- import json
- import urllib.request, urllib.parse
- def showsome(searchfor):
- query = urllib.parse.urlencode({'q': searchfor})
- url = 'http://ajax.googleapis.com/ajax/services/search/web?v=1.0&%s' % query
- search_response = urllib.request.urlopen(url)
- search_results = search_response.read().decode("utf8")
- results = json.loads(search_results)
- data = results['responseData']
- print('Total results: %s' % data['cursor']['estimatedResultCount'])
- hits = data['results']
- print('Top %d hits:' % len(hits))
- for h in hits: print(' ', h['url'])
- print('For more results, see %s' % data['cursor']['moreResultsUrl'])
- showsome('ermanno olmi')
- # Get the first 20 hits for: "Breaking Code" WordPress blog
- from google import search
- for url in search('"Breaking Code" WordPress blog', stop=20):
- print(url)
- # Get the first 20 hits for "Mariposa botnet" in Google Spain
- from google import search
- for url in search('Mariposa botnet', tld='es', lang='es', stop=20):
- print(url)
- import urllib2
- def getgoogleurl(search,siteurl=False):
- if siteurl==False:
- return 'http://www.google.com/search?q='+urllib2.quote(search)
- else:
- return 'http://www.google.com/search?q=site:'+urllib2.quote(siteurl)+'%20'+urllib2.quote(search)
- def getgooglelinks(search,siteurl=False):
- #google returns 403 without user agent
- headers = {'User-agent':'Mozilla/11.0'}
- req = urllib2.Request(getgoogleurl(search,siteurl),None,headers)
- site = urllib2.urlopen(req)
- data = site.read()
- site.close()
- #no beatifulsoup because google html is generated with javascript
- start = data.find('<div id="res">')
- end = data.find('<div id="foot">')
- if data[start:end]=='':
- #error, no links to find
- return False
- else:
- links =[]
- data = data[start:end]
- start = 0
- end = 0
- while start>-1 and end>-1:
- #get only results of the provided site
- if siteurl==False:
- start = data.find('<a href="/url?q=')
- else:
- start = data.find('<a href="/url?q='+str(siteurl))
- data = data[start+len('<a href="/url?q='):]
- end = data.find('&sa=U&ei=')
- if start>-1 and end>-1:
- link = urllib2.unquote(data[0:end])
- data = data[end:len(data)]
- if link.find('http')==0:
- links.append(link)
- return links
- links = getgooglelinks('python','http://www.stackoverflow.com/')
- for link in links:
- print link
- from lib.google_search_results import GoogleSearchResults
- params = {
- "q" : "Coffee",
- "location" : "Austin, Texas, United States",
- "hl" : "en",
- "gl" : "us",
- "google_domain" : "google.com",
- "api_key" : "demo",
- }
- query = GoogleSearchResults(params)
- dictionary_results = query.get_dictionary()
Add Comment
Please, Sign In to add comment