Created
May 28, 2022 07:11
-
-
Save Suleman-Elahi/891737ce8f1f674f4c8339bd5654e826 to your computer and use it in GitHub Desktop.
A simple script to get all Google Ads from Google Search results directly. Downloads ad title, link, and description.
This file contains 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
from bs4 import BeautifulSoup | |
import requests, csv | |
import lxml | |
from requests.structures import CaseInsensitiveDict | |
ads = [] | |
key = input("Enter a keyword/domain/brand: ") | |
headers = CaseInsensitiveDict() | |
headers["authority"] = "www.google.com" | |
headers["User-Agent"]: "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.19582" | |
headers["accept"] = "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9" | |
headers["accept-language"] = "en-US,en;q=0.9" | |
headers["cache-control"] = "max-age=0" | |
headers["cookie"] = "SID=KggpaEyTE7l4AxeJkOoox8FjqNoZmdzectCSFSUNmKE4D1br29p2xiDHyh5KZLNM_k0JOQ.; __Secure-1PSID=KggpaEyTE7l4AxeJkOoox8FjqNoZmdzectCSFSUNmKE4D1brG6IVvOZGVDZBwhmDtbqHZg.; __Secure-3PSID=KggpaEyTE7l4AxeJkOoox8FjqNoZmdzectCSFSUNmKE4D1brdFTR6bjSfPYV4lIEqPlg7w.; HSID=A83ab3uLXbjczC13e; SSID=AvK1tOQd4HSDWFFl_; APISID=NJKGyeuVPJQcnE0W/A9aceC63PUPsCT6EO; SAPISID=SnSsieEZPmV-RPfe/AMjZfROErTGSpcLN7; __Secure-1PAPISID=SnSsieEZPmV-RPfe/AMjZfROErTGSpcLN7; __Secure-3PAPISID=SnSsieEZPmV-RPfe/AMjZfROErTGSpcLN7; 1P_JAR=2022-05-27-12; NID=511=qhk932_clF2_815gfm746w0EhctRcRSHLM9UVN9GgRgp2StxG2Q4-LMykwY6dKmyYYCTU1e7m8uCZzekfQtEeDOiB3Ih8WoP8Y1EwUOz01WsHSa5uNqHKIYofSoH17Lf4oEnKw5RV35qLpskECg13QeqcipqZv_YzB10gX21HruiHdcTNSWoKQshpaLRLbG1hEDIdDezdWU_Jk2lswUeQ2HMUBThQeCtoVHQfZ66XHNZvRvG48soJlPrIMjc7c1UhoHOqgl8g2MGkEl_lAjPBnnaXzRpG3JI7qAnhwCaf1OdJsun; OGPC=748494848-3:; AEC=AakniGO6VhnoolbZtMIMHXIh77ecte_1VItg_HeZICJIBduHo5VfQe5MJb0; mp_52e5e0805583e8a410f1ed50d8e0c049_mixpanel=%7B%22distinct_id%22%3A%20%2218105768ac912b-0de1392e0bcacd-54161253-100200-18105768aca873%22%2C%22%24device_id%22%3A%20%2218105768ac912b-0de1392e0bcacd-54161253-100200-18105768aca873%22%2C%22%24initial_referrer%22%3A%20%22%24direct%22%2C%22%24initial_referring_domain%22%3A%20%22%24direct%22%2C%22%24search_engine%22%3A%20%22google%22%7D; DV=g0k6MwHaRt8Q8JiFc16AWAbeGLpYEBg; SIDCC=AJi4QfG3B3Im0WYhRWEXRpt67kozRDv_r-sUogFBk7j3g3D9z11Qz7M1MpaC3U9Sr8W8_xSZxw; __Secure-3PSIDCC=AJi4QfHuo9Mec4YCHs-tMwhpnjQ5LgytoaPSADqj1rEkOfWwaL4It5qqLO9-5N4A4vvfS0iAoaM" | |
html = requests.get('https://www.google.com/search?q='+key, headers=headers) | |
soup = BeautifulSoup(html.text,'html.parser') | |
titles=soup.select('div[role="heading"]') | |
links=soup.select('div[role="link"]') | |
desc=soup.select('div[class="MUxGbd yDYNvb lyLwlc"]') | |
for i in range(len(titles)): | |
info = { | |
"Title": titles[i].text, | |
"Description": desc[i].text, | |
"Link": links[i].text | |
} | |
ads.append(info) | |
with open("ads.csv", 'w+') as file: | |
csvwriter = csv.DictWriter(file, fieldnames=list(ads[0].keys())) | |
csvwriter.writeheader() | |
csvwriter.writerows(ads) | |
input("Press any key to exit...") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment