v4l3n71n/web_scrap
1
0
Fork 0
Code Issues Pull Requests Projects Releases 10 Wiki Activity

test webscrapping

Browse Source
This commit is contained in:
Valentin CZERYBA 2023-02-28 21:52:12 +01:00
parent 0262e99d22
commit 64118a3c20
1 changed files with 12 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
web_scrap.py
View File

@ -3,10 +3,17 @@
# Python 3 # Python 3
# Extraction des liens d'une page web # Extraction des liens d'une page web
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
import urllib.request import requests
with urllib.request.urlopen('https://www.clarissariviere.com/') as response: page = requests.get("https://www.clarissariviere.com")
webpage = response.read()
soup = BeautifulSoup(webpage, 'html.parser') if page.status_code == 200:
soup = BeautifulSoup(page.text, 'html.parser')
for anchor in soup.find_all('a'): for anchor in soup.find_all('a'):
print(anchor.get('href', '/')) print(anchor.get('href', '/'))
#with urllib.request.urlopen('https://www.clarissariviere.com/index.html') as response:
# print(response)
#webpage = response.read()
#soup = BeautifulSoup(webpage, 'html.parser')
#for anchor in soup.find_all('a'):
# print(anchor.get('href', '/'))