Python爬虫html网址实战笔记

仅供学习参考

一、获取html网址中文本和链接，写入TXT文件中

import requests
from lxml import html

base_url = "https://abcdef自己的网址要改"
response = requests.get(base_url)
response.encoding = 'utf-8'  # 指定正确的编码方式

tree = html.fromstring(response.content, parser=html.HTMLParser(encoding='utf-8'))

# 固定部分XPath，只有最后一个div的索引会变化，自己修改，复制网址的xpath路径
fixed_xpath = "/html/body/div[4]/div[2]/ul/li[{div_index}]/a"

filename = "现TXT文本内容.txt"

with open(filename, "w", encoding="utf-8") as f:
    for div_index in range(1, 100):  # 假设有100个人
        # 构建完整的XPath
        xpath = fixed_xpath.format(div_index=div_index)

        # 使用XPath定位每个人员信息的元素
        person_elements = tree.xpath(xpath)

        for person_element in person_elements:
            # 获取网址路径和姓名信息
            url_path = person_element.get("href")
            full_url = base_url + url_path if url_path else ""
            name = person_element.xpath('string()').strip()  # 提取文本内容并去除空格

            # 仅输出网址中的路径部分
            url_path = full_url.replace(base_url, "")
            output_str = f"网址路径：{url_path}\n姓名：{name}\n\n"
            print(output_str)
            f.write(output_str)

print(f"输出已保存到文件 {filename}")

结果：现TXT文本内容

网址路径：http://abc.html
姓名：abc

二、根据现有的TXT文本，打开链接找到需要的内容。将内容放入姓名之后，以新的文本输出

import re
import requests
from lxml import html

# 读取文件内容
with open("现TXT文本内容.txt", "rb") as file:
    content = file.read().decode('utf-8', 'ignore')

lines = content.splitlines()

email_xpath = '/html/body/div[4]/div/div/div/div/div[2]/div[1]/div[2]/div[4]/div[1]/text()'

filename = "现TXT文本内容邮箱.txt"

with open(filename, "w", encoding="utf-8") as f:
    # 遍历每一行内容
    for i in range(0, len(lines), 1):
        url_line = lines[i]  # 当前行为URL
        name_line = lines[i + 1]  # 下一行为姓名

        # 从URL和姓名行中提取URL和姓名信息
        url_match = re.search(r"https?://[^\s]+", url_line)
        name_match = re.search(r"姓名：(.+)", name_line)

        # 如果URL和姓名都匹配到了
        if url_match and name_match:
            url = url_match.group()
            name = name_match.group(1)

            # 发送GET请求到URL获取页面内容
            response = requests.get(url)
            # 将页面内容转为XPath对象
            tree = html.fromstring(response.content)

            # 使用XPath表达式提取邮箱信息
            email = tree.xpath(email_xpath)
            email = email[0] if email else "未找到邮箱地址"

            # 将姓名和邮箱信息写入文件
            output_str = f"{name}：{email}\n"
            print(output_str)
            f.write(output_str)

# 输出保存结果
print(f"输出已保存到文件 {filename}")

输出TXT文本内容
abc：abc@aa.com
...