google search with python requests library

input:

import requests

def googleSearch(query):
    with requests.session() as c:
        url = 'https://www.google.co.in'
        query = {'q': query}
        urllink = requests.get(url, params=query)
        print urllink.url

googleSearch('Linkin Park')

output:

https://www.google.co.in/?q=Linkin+Park

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']

In this code by using bs4 you can get all the h3 and print their text

# Import the beautifulsoup 
# and request libraries of python.
import requests
import bs4
  
# Make two strings with default google search URL
# 'https://google.com/search?q=' and
# our customized search keyword.
# Concatenate them
text= "c++ linear search program"
url = 'https://google.com/search?q=' + text
  
# Fetch the URL data using requests.get(url),
# store it in a variable, request_result.
request_result=requests.get( url )
  
# Creating soup from the fetched request
soup = bs4.BeautifulSoup(request_result.text,"html.parser")
filter=soup.find_all("h3")
for i in range(0,len(filter)):
    print(filter[i].get_text())

The readable way to send a request with many query parameters would be to pass URL parameters as a dictionary:

params = {
  'q': 'minecraft', # search query
  'gl': 'us',       # country where to search from   
  'hl': 'en',       # language 
}

requests.get('URL', params=params)

But, in order to get the actual response (output/text/data) that you see in the browser you need to send additional headers, more specifically user-agent which is needed to act as a "real" user visit when bot or browser sends a fake user-agent string to announce themselves as a different client.

The reason that your request might be blocked is that the default requests user agent is python-requests and websites understand that. Check what’s your user agent.

You can read more about it in the blog post I wrote about how to reduce the chance of being blocked while web scraping.

Pass user-agent:

headers = {
    'User-agent':
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36'
}

requests.get('URL', headers=headers)

---

Code and example in the online IDE:

from bs4 import BeautifulSoup
import requests, lxml

headers = {
    'User-agent':
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36'
}

params = {
  'q': 'minecraft',
  'gl': 'us',
  'hl': 'en',
}

html = requests.get('https://www.google.com/search', headers=headers, params=params)
soup = BeautifulSoup(html.text, 'lxml')

for result in soup.select('.tF2Cxc'):
  title = result.select_one('.DKV0Md').text
  link = result.select_one('.yuRUbf a')['href']
  print(title, link, sep='n')

---

Alternatively, you can achieve the same thing by using Google Organic API from SerpApi. It’s a paid API with a free plan.

The difference is that you don’t have to create it from scratch and maintain it.

Code to integrate:

import os
from serpapi import GoogleSearch

params = {
  "engine": "google",
  "q": "tesla",
  "hl": "en",
  "gl": "us",
  "api_key": os.getenv("API_KEY"),
}

search = GoogleSearch(params)
results = search.get_dict()

for result in results["organic_results"]:
  print(result['title'])
  print(result['link'])

Disclaimer, I work for SerpApi.

You can use ‘webbroser’, I think it doesn’t get easier than that:

import webbrowser

query = input('Enter your query: ')
webbrowser.open(f'https://google.com/search?q={query}')