用python对电影的爬取 并保存在csv

import requests
import re
import csv
from lxml import etree
class movie(object):
def init(self):
self.ur=“https://www.ygdy8.net/html/gndy/dyzz/list_23_{}.html”
self.headers={“User-Agent”: “Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:73.0) Gecko/20100101 Firefox/73.0”}
self.baseur=“https://www.ygdy8.net”
#访问页面
def findtip(self,ur):
response=requests.get(ur,headers=self.headers)
response.encoding=“gb2312”
#获取电影名字
test=re.findall(r’<a.?class=“ulink”(.?)’,response.text,re.S)
#对名字进行处理
mingzi = []
for int in test:
a = int.replace(‘BD中英双字幕’, ‘’)
c = a.replace(‘BD国英双语双字’, ‘’)
d = c.replace(‘BD国语中字’, ‘’)
h = d.replace(‘BD中字’, ‘’)
k = h.replace(‘BD国语中英双字’, ‘’)
t = h.replace(’>’, ‘’)
o = t.replace(‘2019年’, ‘’)
mingzi.append(o)
# 获得电影链接
text=etree.HTML(response.text)
movie_url=text.xpath("//b/a[@class=‘ulink’]/@href")
#对连接进行处理
lianjie = []
for page in movie_url:
movieurl = self.baseur + page
lianjie.append(movieurl)
self.addname(mingzi,lianjie)
#保存数据
def addname(self,mingzi,lianjie):
namelianjie=zip(mingzi,lianjie)
with open(‘ss.csv’,‘a’,encoding=‘utf-8’,newline=’’) as f:
for namelianjie1 in namelianjie:
write=csv.writer(f)
write.writerow(namelianjie1)
#获取所有页数
def findpage(self):
for page in range(10):
b=self.ur.format(page)
self.findtip(b)

moviewibet=movie()
moviewibet.findpage()