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

menu nav list

Browse Source
This commit is contained in:
Valentin CZERYBA 2023-02-28 22:03:03 +01:00
parent 64118a3c20
commit a03489ee21
1 changed files with 5 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
web_scrap.py
View File

@ -9,11 +9,8 @@ page = requests.get("https://www.clarissariviere.com")
if page.status_code == 200: if page.status_code == 200:
soup = BeautifulSoup(page.text, 'html.parser') soup = BeautifulSoup(page.text, 'html.parser')
for anchor in soup.find_all('a'): ul = soup.find_all("ul", id="listsmooth")
print(anchor.get('href', '/')) for anchor in ul[0].find_all("a"):
#with urllib.request.urlopen('https://www.clarissariviere.com/index.html') as response: href = anchor.get('href', '/')
# print(response) if href != "#" and href != "http://www.clarissariviere.com/":
#webpage = response.read() print(href)
#soup = BeautifulSoup(webpage, 'html.parser')
#for anchor in soup.find_all('a'):
# print(anchor.get('href', '/'))