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

Merge branch 'master' of gitea.gorillamail.biz:cid/Web_Scrape

Browse Source
This commit is contained in:
master
2023-12-30 23:15:47 -05:00
parent 89b432ea2a 0c9cea5225
commit 125f968a47
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
main.py
View File

@ -3,6 +3,7 @@ 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