import requests,re
from openpyxl import Workbook
wb=Workbook()
ws =wb.active
ws.append(["韩剧名","主演","详情介绍"])
headers = {
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.36"
}
page_url="https://www.hjutv.cn/show_2________{}___.html"
detail_url="https://www.hjutv.cn/detail_{}.html"
response =requests.get(url=page_url,headers=headers)
for i in range(1,2):#################采集多页修改这里
  url = page_url.format(i)
  response = requests.get(url=url, headers=headers)
  html = response.text 
  tvplay_pattern = re.compile(r'<li >(.*?)</li>',re.S)
  tvplay_list = tvplay_pattern .findall(html)
  # 匹配剧名
  name_pattern =re.compile(r'<p ><a[^>]+>([^<]+)',re.S)
  # 匹配演员名
  actor_name_p_pattern =re.compile(r'<p >(.*?)</p>',re.S)#获取所有演员a标签html代码
  actor_name_pattern =re.compile(r'<a[^>]+>([^<]+)',re.S)#获取演员
  #URL正则
  href_pattern=re.compile(r'detail_(\d+)',re.S)
  #介绍正则
  intro_pattern=re.compile(r'<div ><span>([^<]+)',re.S)
  for tvplay in tvplay_list:
    #try:
      name = name_pattern.findall(tvplay)
      if len(name)==0:#没找到名称
        name="---"
      else:
        name = name[0]
      actor_name=""
      actor_name_p=actor_name_p_pattern.findall(tvplay)
      if len(actor_name_p):
        actor_name=actor_name_pattern.findall(actor_name_p[0])
        actor_name=','.join(actor_name)

      #############获取详情介绍
      href=href_pattern.findall(tvplay)[0]
      href=detail_url.format(href)
      detail=requests.get(href,headers=headers).text
      detail=intro_pattern.findall(detail)
      if len(detail):
        detail=detail[0]
      else:
        detail="---"

      #############获取详情介绍
      print(name,actor_name,detail)
      ws.append([name,actor_name,detail])
    #except:
      #print(tvplay)
      #break
wb.save("韩剧.xlsx")