Python爬虫新手入门教学（八）：爬取论坛文章保存成PDF

import pdfkit
import requests
import parsel

html_str = """
<!doctype html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>Document</title>
</head>
<body>
{article}
</body>
</html>
"""


def save(article, title):
    pdf_path = 'pdf\\' + title + '.pdf'
    html_path = 'html\\' + title + '.html'
    html = html_str.format(article=article)
    with open(html_path, mode='w', encoding='utf-8') as f:
        f.write(html)
        print('{}已下载完成'.format(title))
    # exe 文件存放的路径
    config = pdfkit.configuration(wkhtmltopdf='C:\\Program Files\\wkhtmltopdf\\bin\\wkhtmltopdf.exe')
    # 把 html 经过 pdfkit 变成 pdf 文件
    pdfkit.from_file(html_path, pdf_path, configuration=config)


def main(html_url):
    # 请求头
    headers = {
        "Host": "blog.csdn.net",
        "Referer": "https://blog.csdn.net/qq_41359265/article/details/102570971",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36",
    }
    # 用户信息
    cookie = {
        'Cookie': '你本身的cookie'
    }
    response = requests.get(url=html_url, headers=headers, cookies=cookie)
    selector = parsel.Selector(response.text)
    urls = selector.css('.article-list h4 a::attr(href)').getall()
    for html_url in urls:
        response = requests.get(url=html_url, headers=headers, cookies=cookie)
        # text 文本（字符串）
        # 遭遇了反扒
        # print(response.text)
        """如何把 HTML 变成 PDF 格式"""
        # 提取文章部分
        sel = parsel.Selector(response.text)
        # css 选择器
        article = sel.css('article').get()
        title = sel.css('h1::text').get()
        save(article, title)


if __name__ == '__main__':
    url = 'https://blog.csdn.net/fei347795790/article/list/1'
    main(url)

Python爬虫新手入门教学（八）：爬取论坛文章保存成PDF

前言

前文内容

基本开发环境

相关模块的使用

1、目标需求

2、网页数据分析

完整实现代码