python爬虫 json.decoder.JSONDecodeError如何解决

Question

编了一个爬取豆瓣排行榜信息的爬虫代码

import requests
import json

if __name__ == '__main__':
    url = 'https://movie.douban.com/typerank'
    param = {
        'type':'24',
        'interval_id':'100: 90',
        'action':'',
        'start':'1', 
        'limit':'20', 
    }
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:84.0) Gecko/20100101 Firefox/84.0'
    }

    response = requests.get(url=url,params=param,headers=headers)

    list_data = response.json()

    fp = open('./douban.jason','w',encoding='utf-8')
    json.dump(list_data,fp=fp,ensure_ascii=False)

    print('over!!!')

 

最终出现了一下错误，求大神帮忙解答

Traceback (most recent call last):
  File "C:/Users/PycharmProjects/pythonProject/04requests实战之豆瓣电影爬取.py", line 21, in <module>
    list_data = response.json()
  File "C:\Users\PycharmProjects\pythonProject\venv\lib\site-packages\requests\models.py", line 900, in json
    return complexjson.loads(self.text, **kwargs)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.8_3.8.2032.0_x64__qbz5n2kfra8p0\lib\json\__init__.py", line 357, in loads
    return _default_decoder.decode(s)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.8_3.8.2032.0_x64__qbz5n2kfra8p0\lib\json\decoder.py", line 337, in decode
    obj, end = self.raw_decode(s, idx=_w(s, 0).end())
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.8_3.8.2032.0_x64__qbz5n2kfra8p0\lib\json\decoder.py", line 355, in raw_decode
    raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

 

Answer 1

你这个程序返回的是html,并不是json

正确的请求

import requests
import json

if __name__ == '__main__':
    url = 'https://movie.douban.com/j/search_subjects'
    param = {
        "type": "movie",
"tag": "热门",
"page_limit": 50,
"page_start": 0,
    }
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:84.0) Gecko/20100101 Firefox/84.0'
    }

    response = requests.get(url=url,params=param,headers=headers)
    response.encoding = response.apparent_encoding
    list_data = response.json()

    fp = open('./douban.jason','w',encoding='utf-8')
    json.dump(list_data,fp=fp,ensure_ascii=False)

    print('over!!!')