google search with python requests library
Request Overview
The Google search request is a standard HTTP GET command. It includes a collection of parameters relevant to your queries. These parameters are included in the request URL as name=value pairs separated by ampersand (&) characters. Parameters include data like the search query and a unique CSE ID (cx) that identifies the CSE that is making the HTTP request. The WebSearch or Image Search service returns XML results in response to your HTTP requests.
First, you must get your CSE ID (cx parameter) at Control Panel of Custom Search Engine
Then, See the official Google Developers site for Custom Search.
There are many examples like this:
http://www.google.com/search?
start=0
&num=10
&q=red+sox
&cr=countryCA
&lr=lang_fr
&client=google-csbe
&output=xml_no_dtd
&cx=00255077836266642015:u-scht7a-8i
And there are explained the list of parameters that you can use.
import requests
from bs4 import BeautifulSoup
headers_Get = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:49.0) Gecko/20100101 Firefox/49.0',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Language': 'en-US,en;q=0.5',
'Accept-Encoding': 'gzip, deflate',
'DNT': '1',
'Connection': 'keep-alive',
'Upgrade-Insecure-Requests': '1'
}
def google(q):
s = requests.Session()
q = '+'.join(q.split())
url = 'https://www.google.com/search?q=' + q + '&ie=utf-8&oe=utf-8'
r = s.get(url, headers=headers_Get)
soup = BeautifulSoup(r.text, "html.parser")
output = []
for searchWrapper in soup.find_all('h3', {'class':'r'}): #this line may change in future based on google's web page structure
url = searchWrapper.find('a')["href"]
text = searchWrapper.find('a').text.strip()
result = {'text': text, 'url': url}
output.append(result)
return output
Will return an array of google results in {'text': text, 'url': url} format. Top result url would be google('search query')[0]['url']