cid/Web_Scrape
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Fix browser agent

Browse Source
This commit is contained in:
master
2023-12-30 23:17:41 -05:00
parent 125f968a47
commit 8e34d94acd
1 changed files with 1 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
main.py
View File

@ -3,7 +3,6 @@ from bs4 import BeautifulSoup
from urllib.parse import urlparse, urlunparse from urllib.parse import urlparse, urlunparse
import pandas as pd import pandas as pd
headers = {'User-Agent': 'myprogram/1.0'}
def scrape_headings(url): def scrape_headings(url):
try: try:
# Check if the URL has a scheme (http/https), and add one if missing # Check if the URL has a scheme (http/https), and add one if missing
@ -42,7 +41,7 @@ def scrape_headings(url):
def main(): def main():
url = input("Enter the URL: ") url = input("Enter the URL: ")ls
scrape_headings(url) scrape_headings(url)
# df = pd.DataFrame(scrape_headings(url)) # df = pd.DataFrame(scrape_headings(url))
search_again = input("Do you want to search again? y/n:").lower() search_again = input("Do you want to search again? y/n:").lower()