解析JSON web输出

您可以解析命令,然后使用 dumps 方法:

# Send HTTP requests
import requests

import json

from bs4 import BeautifulSoup


class WebScraper:

    def send_http_request():

        # Obtain the URL via user input
        url = input('Input the URL:\n')

        # Get the webpage
        r = requests.get(url)

        soup = BeautifulSoup(r.content, 'html.parser')

        # Check response object's status code
        if r:
            p = json.loads("".join(soup.find('script', {'type':'application/ld+json'}).contents))
            output = json.dumps({"title": p["name"], "description": p["description"]})
            print(output)
        else:
            print('\nInvalid movie page!')


WebScraper.send_http_request()

{"title": "Star Wars: Episode V - The Empire Strikes Back", "description": "Star Wars: Episode V - The Empire Strikes Back is a movie starring Mark Hamill, Harrison Ford, and Carrie Fisher. After the Rebels are brutally overpowered by the Empire on the ice planet Hoth, Luke Skywalker begins Jedi training..."}

您只需要从中创建一个新词典 p 给我两把钥匙 name 和 description .

        # Check response object's status code
        if r:
            p = json.loads("".join(soup.find('script', {'type':'application/ld+json'}).contents))
            desired_output = {"title": p["name"], "description": p["description"]}
            print(desired_output)
        else:
            print('\nInvalid movie page!')

输出:

{'title': 'Star Wars: Episode V - The Empire Strikes Back', 'description': 'Star Wars: Episode V - The Empire Strikes Back is a movie starring Mark Hamill, Harrison Ford, and Carrie Fisher. After the Rebels are brutally overpowered by the Empire on the ice planet Hoth, Luke Skywalker begins Jedi training...'}