天堂电影网-python

爬取天堂电影网的电影名称及播放链接保存到csv文件中

步骤：进入主页面获取每个电影的跳转网址进行拼接获得新的网址再新网址获取播放链接进行拼接最后获得完全播放网址

import requests
import re
import csv
url = "https://www.sjchess.com"
url_new = ''
dic = {"title":[],"url":[]}
f = open('data_film.csv',mode='w',encoding='utf8')
write_csv = csv.writer(f)
headers = {
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36"
}
response = requests.get(url=url,headers=headers)
# print(response.text)
#正则,获取子页面链接和电影姓名
a_ = re.compile(r'<li class="stui-vodlist__item">.*?href="(?P<url>.*?)".*?title="(?P<title_>.*?)"',re.S)
object1 = a_.finditer(response.text)
for i in object1:
    url_new = url + str(i['url'])#子页面链接
    title = i['title_']#电影名称
    # print( url + str(i['url']))
    # print(i['title_'])
    #继续获取下载链接
    response_new = requests.get(url=url_new,headers=headers)
    object2 = re.compile(r' <ul class="stui-content__playlist">.*? <li><a href="(?P<url_>.*?)"',re.S)
    # print(response_new.text)
    url_add = object2.finditer(response_new.text)
    for it in url_add:
        # print(i['title_'],url + str(it['url_']))
        dic['title'] = title
        dic['url'] = url + str(it['url_'])
        write_csv.writerow(dic.values())
f.close()
response.close()
response_new.close()