Python爬虫怎样抓取表格数据_Python爬虫提取网页中表格数据的实用方法

import requests
from bs4 import BeautifulSoup
<p>url = '<a href="https://www.php.cn/link/f630930295f2102fb56edc9f88de45fb">https://www.php.cn/link/f630930295f2102fb56edc9f88de45fb</a>'
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')</p><p>table = soup.find('table')  # 可根据class或id更精确选择
data = []
for row in table.find_all('tr'):
cols = row.find_all(['td', 'th'])
data.append([col.get_text(strip=True) for col in cols])</p><h1>data 现在是一个二维列表，可写入CSV</h1><p>

import pandas as pd
<p>url = '<a href="https://www.php.cn/link/85e9b5dce4f9484f6731b0d778f8cc2e">https://www.php.cn/link/85e9b5dce4f9484f6731b0d778f8cc2e</a>'
tables = pd.read_html(url)  # 返回一个包含所有表格的列表
df = tables[0]  # 取第一个表格
print(df.head())

from selenium import webdriver
from bs4 import BeautifulSoup
import time
<p>driver = webdriver.Chrome()
driver.get('<a href="https://www.php.cn/link/8edc69aa76b7aac408ba3c248aa8d7d4">https://www.php.cn/link/8edc69aa76b7aac408ba3c248aa8d7d4</a>')
time.sleep(3)  # 等待JS加载</p><p>soup = BeautifulSoup(driver.page_source, 'html.parser')
table = soup.find('table')</p><h1>后续提取逻辑同BeautifulSoup</h1><p>driver.quit()

import csv
<p>with open('table_data.csv', 'w', encoding='utf-8', newline='') as f:
writer = csv.writer(f)
writer.writerows(data)