Spaces:
Running
Running
File size: 1,710 Bytes
76489d2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 |
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 i_search(url):
response = requests.get(url)
response.raise_for_status()
soup = BeautifulSoup(response.content, 'html.parser')
return ' '.join([p.text for p in soup.find_all('p')])
def b_search(q):
#s = requests.Session()
#url = q
#r = s.get(url, headers=headers_Get)
r=requests.get(q)
soup = BeautifulSoup(r.text, "html.parser")
output = []
for searchWrapper in soup.find_all('article'): #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
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 |