python鎬庝箞鎶撳彇缃戦〉鏁版嵁
Python鍙互浣跨敤澶氱搴撴潵鎶撳彇缃戦〉鏁版嵁锛屾渶甯哥敤鐨勬槸requests鍜孊eautifulSoup搴撱€?/p>
- 浣跨敤requests搴撳彂閫丠TTP璇锋眰鏉ヨ幏鍙栫綉椤垫暟鎹細
import requests
url = "http://example.com"
response = requests.get(url)
# 妫€鏌ヨ姹傛槸鍚︽垚鍔?/span>
if response.status_code == 200:
# 鎵撳嵃缃戦〉鍐呭
print(response.text)
- 浣跨敤BeautifulSoup搴撹В鏋愮綉椤垫暟鎹細
from bs4 import BeautifulSoup
# 鍋囪宸茬粡浣跨敤requests搴撹幏鍙栦簡缃戦〉鍐呭锛屽瓨鍌ㄥ湪response鍙橀噺涓?/span>
soup = BeautifulSoup(response.text, "html.parser")
# 浣跨敤BeautifulSoup鎻愪緵鐨勬柟娉曟潵鎻愬彇鏁版嵁
# 渚嬪锛屾彁鍙栨墍鏈?lt;a>鏍囩涓殑閾炬帴
links = soup.find_all("a")
for link in links:
print(link.get("href"))
璇锋敞鎰忥紝鍏蜂綋鐨勬姄鍙栨柟娉曚細鏍规嵁缃戦〉鐨勭粨鏋勫拰鏁版嵁鐨勪綅缃€屾湁鎵€涓嶅悓銆傛湁鏃跺€欏彲鑳借繕闇€瑕佸鐞嗕竴浜涚綉椤垫覆鏌撴垨鍔ㄦ€佸姞杞界殑闂锛屽彲浠ヤ娇鐢╯elenium搴撴潵妯℃嫙娴忚鍣ㄨ涓恒€?/p>
相关问答