yuanhau/news-analyze
1
0
Fork 0
mirror of https://github.com/hpware/news-analyze.git synced 2025-06-23 21:14:23 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

Implement structural updates and optimizations across multiple modules

Browse source
This commit is contained in:
yuanhau 2025-05-10 23:21:36 +08:00
parent 5d58016b1d
commit bf38065e52
4 changed files with 19 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

17
scraping/main.py
View file

@ -1,7 +1,18 @@
from urllib.request import urlopen
import time
import re # Regular expressions
from urllib.request import urlopen # URL request lib.
from bs4 import BeautifulSoup # BeautifulSoup lib.
url = "https://tw.news.yahoo.com/"
headers = {
'User-Agent': 'NewsSceraperBot/1.0 (news.yuanhau.com)'
}
#url = "https://tw.news.yahoo.com/"
url = "https://news.google.com/home?hl=zh-TW&gl=TW&ceid=TW:zh-Hant"
page = urlopen(url)
html_bytes = page.read()
html = html_bytes.decode("utf-8")
soup = BeautifulSoup(html, "html.parser")
page
print(soup.find_all("article"))