# -*- coding:utf-8 -*-
'''
@Author: 董咚咚
@contact: [email protected]
@Time: 2023/7/31 17:02
@version: 1.0
'''
import requests
import re
import xlwt
from bs4 import BeautifulSoup
url = "https://www.dygod.net/html/gndy/dyzz/"
hd = {
'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'
}
#linkurl = "https://www.dygod.net/html/gndy/dyzz/20230712/120036.html"
def getmanget(linkurl):
res = requests.get(linkurl)
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])
#代码正式开始
count = 0 #记录爬取电影的数量，每爬取一次，就在下面的列表里面添加一次
total = [] #用来储存记录信息的列表
workbook = xlwt.Workbook(encoding="utf-8")
worksheet = workbook.add_sheet('sheet1')
for i in range(2,3): #页面数量，就是从第二页到第八页，页数可以自己测试
url = "https://www.dygod.net/html/gndy/dyzz/index_"+str(i)+".html"
#print(url) #用来测试所爬取的网站是否有效
res = requests.get(url,headers=hd)
res.encoding = res.apparent_encoding
#print(res.text) #获取相关和列表
soup = BeautifulSoup(res.text,"html.parser")
#print(soup.title,type(soup.title)) #查看电影的名字
ret = soup.find_all(class_="tbspan",style = "margin-top:6px") #此内容都可以用Fn+F12查看,找到所有电影的表格
for x in ret: #遍历每个电影的表格
info = []
#print(x.find("a").string) #打印除a标签的内容，即电影的名称
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'') #查看电影译名
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) #打印出相关的年代
info.append(str(n))
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) #打印出相关的片名
info.append(str(n).split("/")[0])
pat = re.compile(r"◎产 地(.*)\n")
ret = re.findall(pat,str(x))
for n in ret:
n = n.replace(u'\u3000', u'')
print("◎产 地:",n) #打印出相关的片名
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) #打印出相关的片名
info.append(str(n).split("/")[0])
pat = re.compile(r"◎字 幕(.*)\n")
ret = re.findall(pat,str(x))
for n in ret:
n = n.replace(u'\u3000', u'')
print("◎字 幕:",n) #打印出相关的片名
info.append(str(n).split("/")[0])
pat = re.compile(r"◎上映日期(.*)\n")
ret = re.findall(pat,str(x))
for n in ret:
n = n.replace(u'\u3000', u'')
print("◎上映日期:",n) #打印出相关的片名
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))
print(count,info)
saveExcel(worksheet,count,info)
count+=1
print("="*150) #将列表转换成百分比的形式
workbook.save("movie.xls")
print(count)
