爬取王垠的博客

本文来源吾爱破解论坛

本帖最后由 wushaominkk 于 2019-3-11 16:33 编辑


成果下载链接：
https://pan.baidu.com/s/1acbueRlh5SFhh7OBlJL2qw 提取码: qedu

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

__author__ = 'jiangwenwen'
import pdfkit
import time
import requests
from bs4 import BeautifulSoup
from fake_useragent import UserAgent

ua = UserAgent()

headers = {
    "Host": "www.yinwang.org",
    "User-Agent": ua.random,
    "Referer": "http://www.yinwang.org/",
}

# 代{过}{滤}理服务器
proxyHost = "http-dyn.abuyun.com"
proxyPort = "9020"

# 代{过}{滤}理隧道验证信息
proxyUser = "HJEG872M8LONIE4Dee"
proxyPass = "26C89049A9EE5BA9"

proxyMeta = "http://%(user)s:%(pass)s@%(host)s:%(port)s" % {
  "host": proxyHost,
  "port": proxyPort,
  "user": proxyUser,
  "pass": proxyPass,
}

proxies = {
    "http": proxyMeta,
    "https": proxyMeta,
}

response = requests.get("http://www.yinwang.org/", headers=headers, proxies=proxies)
soup = BeautifulSoup(response.content, 'html.parser')
tags = soup.find_all("li", class_="list-group-item title")

for child in tags:
    start = time.time()
    url = "http://www.yinwang.org" + child.a.get('href')
    file_name = "D:\Python\资料\王垠的博客\\" + child.a.string + ".pdf"
    print("文件打印中...")
    headers["User-Agent"] = ua.random
    print("User-Agent是：{0}".format(headers["User-Agent"]))
    content = requests.get(url, headers=headers, timeout=None, proxies=proxies).text
    pdfkit.from_string(content, file_name)
    end = time.time()
    print("打印成功，本次打印耗时：%0.2f秒" % (end - start))