python爬虫

爬虫爬取网站：https://www.dygod.net/html/gndy/dyzz/

源码：

import requests
import re
import xlwt
from bs4 import BeautifulSoup
url = "https://www.dygod.net/html/gndy/dyzz/"
hd = {
 # 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'
 'User-Agent': 'Mozilla/4.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36'
}
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
    return None
def insertDB():
    pass
def saveExcel(worksheet,count,lst):
    for i in range(6):
           worksheet.write(count,i,lst[i])
count = 0
total = []
workbook = xlwt.Workbook(encoding="utf-8")
workbook = workbook.add_sheet('sheet1')
for i in range(2,3):
     url = "https://www.dygod.net/html/gndy/dyzz/index_"+str(i)+".html"
     # print(url)
     # exit(0)
     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")
     for x in ret:
         info = []
         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"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))
         pat = re.compile(r"产 地(.*)\n")
         ret  =re.findall(pat,str(x))
         for n in ret:
             n = n.replace(u'\u3000',u'')
             print(r"产 地(.*)\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(r"类 别:",str(n).split("/")[0])
             info.append(str(n).split("/")[0])
         linkurl = "https://www.dygod.net/"+x.find("a").get("href")
         manget = getmanget(linkurl)
         if manget:
            print("下载地址:",manget)
            info.append(str(manget))

爬取结果：