White learns to crawl

This is the 17th day of my participation in the August More text Challenge. For details, see: August More Text Challenge

Directly on the code and renderings

Python requests for requests in requests (requests for requests in requests)

request

Remember to add the request header, the get method

    headers = {
        'Host': 'api.bilibili.com'.'Referer': 'https://www.bilibili.com/video/av77413543'.'User-Agent': 'the Mozilla / 5.0 (Windows NT 10.0; Win64; X64) AppleWebKit/537.36 (KHTML like Gecko) Chrome/78.0.3904.108 Safari/537.36'
    }
    info = 'https://api.bilibili.com/x/web-interface/archive/stat?aid=' + av
    info_rsp = requests.get(url=info, headers=headers)
Copy the code

parsing

Parse directly using JSON

 
    info_rsp = requests.get(url=info, headers=headers)
    info_json = info_rsp.json()
  
Copy the code

Then parse the response part of the comment

comment_url = 'https://api.bilibili.com/x/v2/reply'
        page = 1
        while True:
            now_time = int(time.time() * 1000)
            param = {
                'callback': 'jQuery17205146934182044087_' + str(now_time),
                'jsonp': 'jsonp'.'pn': page,
                'type': '1'.'oid': av,
                'sort': '2'.'_': now_time
            }
            rsp = requests.get(url=comment_url, headers=headers, params=param)
            rsp_str = rsp.text.replace('jQuery17205146934182044087_' + str(now_time) + "(".' ').strip(') ')
            com_json = json.loads(rsp_str)


Copy the code

save

And then the file here to save the operation

 com_json['code'] = =0:
                try:
                    replies = com_json['data'] ['replies']
                    print('Current {} page'.format(page))
                    for replie in replies:
                        # print(replie)
                        print('{}\n{}\n'.format('Nickname:' + replie['member'] ['uname'].'Comment content:' + replie['content'] ['message']))
                        fp.write('{}\n{}\n'.format('Nickname:' + replie['member'] ['uname'].'Comment content:' + replie['content'] ['message']))
                    page += 1
                    time.sleep(1)
Copy the code

The complete code

import requests
import re
import time
import json
def get_info() :
    headers = {
        'Host': 'api.bilibili.com'.'Referer': 'https://www.bilibili.com/video/av77413543'.'User-Agent': 'the Mozilla / 5.0 (Windows NT 10.0; Win64; X64) AppleWebKit/537.36 (KHTML like Gecko) Chrome/78.0.3904.108 Safari/537.36'
    }
    info = 'https://api.bilibili.com/x/web-interface/archive/stat?aid=' + av
    info_rsp = requests.get(url=info, headers=headers)
    info_json = info_rsp.json()

    with open(av + '_info.txt'.'w', encoding='utf-8') as fp:
        if info_json['code'] = =0:
            fp.write('Number of plays: {}\n'.format(info_json['data'] ['view']))
            fp.write('Number of bullets: {}\n'.format(info_json['data'] ['danmaku']))
            fp.write('Collection number: {}\n'.format(info_json['data'] ['favorite']))
            fp.write('Number of coins: {}\n'.format(info_json['data'] ['coin']))
            fp.write('Share number: {}\n'.format(info_json['data'] ['share']))
            fp.write('Number of likes: {}\n'.format(info_json['data'] ['like']))

            print('Number of views :', info_json['data'] ['view'])
            print('Bullet count :', info_json['data'] ['danmaku'])
            print('Likes :', info_json['data'] ['like'])
            print('Collection number :', info_json['data'] ['favorite'])
            print('Number of coins :', info_json['data'] ['coin'])
            print(Number of forwards:, info_json['data'] ['share'])
        fp.write('\n')
        comment_url = 'https://api.bilibili.com/x/v2/reply'
        page = 1
        while True:
            now_time = int(time.time() * 1000)
            param = {
                'callback': 'jQuery17205146934182044087_' + str(now_time),
                'jsonp': 'jsonp'.'pn': page,
                'type': '1'.'oid': av,
                'sort': '2'.'_': now_time
            }
            rsp = requests.get(url=comment_url, headers=headers, params=param)
            rsp_str = rsp.text.replace('jQuery17205146934182044087_' + str(now_time) + "(".' ').strip(') ')
            com_json = json.loads(rsp_str)
            print(a)if com_json['code'] = =0:
                try:
                    replies = com_json['data'] ['replies']
                    print('Current {} page'.format(page))
                    for replie in replies:
                        # print(replie)
                        print('{}\n{}\n'.format('Nickname:' + replie['member'] ['uname'].'Comment content:' + replie['content'] ['message']))
                        fp.write('{}\n{}\n'.format('Nickname:' + replie['member'] ['uname'].'Comment content:' + replie['content'] ['message']))
                    page += 1
                    time.sleep(1)
                except Exception as e:
                    break
# av = '77413543'
av = input('Please enter av number:')
get_info()
Copy the code