Last active
September 16, 2021 10:51
-
-
Save 000hen/ea92eafc858d94674f5984ab943eccfb to your computer and use it in GitHub Desktop.
Google Fetcher
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # !!Install BeautifulSoup, Requests First!! | |
| import requests as rs | |
| import sys | |
| import json | |
| from bs4 import BeautifulSoup | |
| from urllib.parse import parse_qs, urlparse | |
| search = [ | |
| # String of what you want to search | |
| ] | |
| respond = [] | |
| for t in search: | |
| dt = rs.get("https://www.google.com/search?q={}".format(t)) | |
| respond.append({ | |
| "query": t, | |
| "respond": dt.text | |
| }) | |
| fg = [] | |
| for g in respond: | |
| dt = g["respond"] | |
| soup = BeautifulSoup(dt, 'html.parser') | |
| title = soup.find_all(class_="BNeawe vvjwJb AP7Wnd") | |
| desc = soup.find_all(class_="BNeawe s3v9rd AP7Wnd") | |
| descG = [] | |
| for i in desc: | |
| try: | |
| descG.append(i.findChildren(class_="BNeawe s3v9rd AP7Wnd")[0].text) | |
| except: | |
| i = None | |
| for i in range(len(title)): | |
| try: | |
| url = title[i].parent.parent["href"] | |
| desc = descG[i] | |
| urlP = urlparse("http://example.com{}".format(url)).query | |
| urlP = parse_qs(urlP, keep_blank_values=True) | |
| print("---------------") | |
| print("I caughted: {}, \n\nContent:\n{}, \n\nURL: \n{}".format(title[i].text, desc, urlP["q"][0])) | |
| print("---------------") | |
| fg.append({ | |
| "searchQuery": g["query"], | |
| "searchTitle": title[i].text, | |
| "searchDescription": desc, | |
| "searchSiteURL": urlP["q"][0], | |
| "searchURL": "https://www.google.com/search?q={}".format(g["query"]) | |
| }) | |
| except: | |
| i = None | |
| f = open("search.json", "w", encoding="utf-8") | |
| f.write(json.dumps(fg)) | |
| f.close() | |
| sys.exit() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment