爬虫之游戏攻略

最新推荐文章于 2024-07-31 08:45:00 发布

码腮克

最新推荐文章于 2024-07-31 08:45:00 发布

阅读量419

点赞数

文章标签：游戏 python

本文链接：https://blog.csdn.net/weixin_44212595/article/details/106957619

版权

import bs4
from bs4 import BeautifulSoup as bs
import requests
import re
import docx
from docx.shared import Inches
from urllib.request import urlretrieve
def downpic(url):
    urlretrieve(url, 'E:\图.jpg')
r = re.compile(r'(http)://(img)[^\s]*?(.jpg)')

def gettxt(url):
    head = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36'}
    res = requests.get(url,headers = head , timeout = 500)
    res.encoding = "utf-8"
    html = res.text

    soup = bs(html, 'lxml')
    info = soup.find_all("p")
    doc = docx.Document()
    for i in range(0, len(info)-28):
        #print(info[i])
        if info[i].string == None:
            try:
                a = info[i].find("a")['href']
            except:
                doc.add_paragraph(info[i].text)
            try:
                picurl = re.search(r, a).group()
                downpic(picurl)
                doc.add_picture("E:\图.jpg", width=Inches(5.6))
            except:
                pass
        else:
            doc.add_paragraph(info[i].text)
    doc.save("E:/攻略/"+info[0].text+".docx")

url ="https://www.gamersky.com/handbook/201712/990054_"
for i in range(2,106):
    url2 = url + str(i) + ".shtml"
    gettxt(url2)