Python爬虫学习笔记（二）

#抓取一个电影网页再点进一部影片抓取影片信息
import requests
import json
if __name__=="__main__":
    # 'Request URL: https://movie.douban.com/j/new_search_subjects?sort=U&range=0,10&tags=%E5%8A%B1%E5%BF%97&start=0&genres=%E5%8A%A8%E4%BD%9C'
    # 'Request URL: https://movie.douban.com/j/new_search_subjects?sort=U&range=0,10&tags=%E5%8A%B1%E5%BF%97&start=0&genres=%E5%96%9C%E5%89%A7'
    url = 'https://movie.douban.com/j/new_search_subjects'
    headers = {
    
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3947.100 Safari/537.36"}
    # get请求 Query String Parameters
    params = {
    
      "sort": "U",
                "range": "0,10",
                "tags":"",
                "start": "0",
                "genres": "惊悚"}
    res_obj = requests.get(url=url,params=params,headers=headers).json()
    list_movieid  = []#电影的id列表
    movie_data = []#电影的详细信息
    for movie in res_obj['data']:
        list_movieid.append(movie['id'])
        movie_url = 'https://m.douban.com/rexxar/api/v2/gallery/subject_feed'
        params ={
    
    "start": "0",
               "count": "4",
                "subject_id": movie['id'],
                "ck": "null"}
        header = {
    
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3947.100 Safari/537.36"}
        moviedata= requests.get(url=url,params=params,headers=headers).json()
       # print(moviedata)
    #     movie_data.append(moviedata)
    # print(movie_data)
    print(list_movieid)

    # fp = open('./movie2.json','w',encoding='UTF-8')
    # json.dump(res_obj,fp,ensure_ascii=False)