python爬虫作业

import requests
import re

import xlwt
from bs4 import BeautifulSoup
url = "https://www.dygod.net/html/gndy/dyzz/"
hd = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36 Edg/115.0.1901.188'
}

def getmanget(linkurl):
    res = requests.get(linkurl, headers=hd)
    res.encoding = res.apparent_encoding
    soup = BeautifulSoup(res.text, "html.parser")
    ret = soup.find_all("a")
    for n in ret:
        if "magnet" in str(n.string):
            return n.string

def saveExcle(worksheet, count, lst):
    for i in range(6):
        worksheet.write(count, i, lst[i])

count = 0
total = []
workbook = xlwt.Workbook(encoding="utf-8")  # 创建workbook对象
worksheet = workbook.add_sheet('sheet1')

for i in range(2, 3):
    url = "https://www.dygod.net/html/gndy/dyzz/index_"+str(i)+".html"

    res = requests.get(url, headers=hd)
    res.encoding = res.apparent_encoding

    soup = BeautifulSoup(res.text, "html.parser")

    ret = soup.find_all(class_="tbspan",style="margin-top:6px")
    # print(ret)

    for x in ret:
       info = []
       print(x.find("a").string)
       info.append(x.find("a").string)

       pat = re.compile(r"◎译  名(.*)\n")
       ret = re.findall(pat,str(x))
       for n in ret:
           n = n.replace(u'\u3000',u'')
           print("◎译  名",n)
           info.append(str(n).split("/")[0])

       pat = re.compile(r"◎片  名(.*)\n")
       ret = re.findall(pat, str(x))
       for n in ret:
           n = n.replace(u'\u3000', u'')
           print("◎片  名",n)
       info.append(str(n).split("/")[0])

       pat = re.compile(r"◎年  代(.*)\n")
       ret = re.findall(pat, str(x))
       for n in ret:
           n = n.replace(u'\u3000', u'')
           print("◎年  代", n)
       info.append(str(n).split("/")[0])

       pat = re.compile(r"◎类  别(.*)\n")
       ret = re.findall(pat, str(x))
       for n in ret:
           n = n.replace(u'\u3000', u'')
           print("◎类  别", n)
       info.append(str(n).split("/")[0])

       linkurl = "https://www.dygod.net" + x.find("a").get("href")
       manget = getmanget(linkurl)
       if manget:
           info.append(str(manget))

       saveExcle(worksheet,count,info)
       count += 1
       print("="*100)

workbook.save("movie.xls")
print(count)

 

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值