pip install beautifulsoup4

from bs4 import BeautifulSoup
import requests
# 億牛云爬蟲代理參數(shù)配置
proxyHost = "u6205.5.tp.16yun.cn"
proxyPort = "5445"
proxyUser = "16QMSOML"
proxyPass = "280651"
# 創(chuàng)建代理字典
proxies = {
    "http": f"http://{proxyUser}:{proxyPass}@{proxyHost}:{proxyPort}",
    "https": f"https://{proxyUser}:{proxyPass}@{proxyHost}:{proxyPort}"
}
# 目標網(wǎng)頁的URL
url = "https://example.com"
# 發(fā)送請求并獲取頁面內(nèi)容
response = requests.get(url, proxies=proxies)
html_content = response.text
# 使用BeautifulSoup解析頁面
soup = BeautifulSoup(html_content, "html.parser")
# 示例：提取頁面中的標題
title = soup.title.text
print("頁面標題：", title)
# 示例：提取頁面中的所有鏈接
links = soup.find_all("a")
print("頁面鏈接：")
for link in links:
    print(link.get("href"))
# 示例：提取頁面中的特定元素
specific_element = soup.find("div", class_="specific-class")
print("特定元素內(nèi)容：", specific_element.text)

# 查找第一個具有特定class屬性的div元素
div_element = soup.find("div", class_="my-class")
# 查找第一個具有特定id屬性的p元素
p_element = soup.find("p", id="my-id")

# 提取所有具有特定class屬性的a元素
a_elements = soup.select("a.my-class")
# 提取所有具有特定id屬性的p元素
p_elements = soup.select("p#my-id")

# 獲取特定元素的文本內(nèi)容
element_text = element.get_text()