python爬虫实战，爬虫之路，永无止境

Posted 2023-02-23 主打Python

python爬虫实战

好久没给大家跟新爬虫文章了，抱歉抱歉，这期给大家带来一篇小爬虫，希望大家喜欢，喜欢的来个关注，支持一下博主，谢谢各位了。

写代码了各位宝宝们
这里要注意一点就是要记得提前登录，cookie要用登录后的

headers = 
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/'
                          '87.0.4280.88 Safari/537.36',
            'Referer': 请用自己的,
            'Cookie': 请用自己的,
            'csrf': 请用自己的,
            'Host': 'www.kuwo.cn'
        

在翻页的时候可以利用for循环进行遍历

        for i in range(page):
            start_url = f'http://www.kuwo.cn/api/www/search/searchMusicBykeyWord?key=singer_name&pn=' \\
                        f'i + 1&rn=30&httpsStatus=1&reqId=d301af60-6e1e-11ec-840f-dfca3a2ceb68'

解析数据

response = requests.get(start_url, headers=headers).json()
            # 解析得到song_names, song_rids
            song_names = jsonpath.jsonpath(response, '$..name')
            song_rids = jsonpath.jsonpath(response, '$..rid')

遍历得到song_name, song_rid 构造song_info_url

# 遍历得到song_name, song_rid 构造song_info_url
            for song_name, song_rid in zip(song_names, song_rids):
                song_info_url = 'http://www.kuwo.cn/api/v1/www/music/playUrl?mid=' \\
                                '&type=music&httpsStatus=1&reqId=c0ac92a0-6e35-11ec-b428-05be0a87bc11'.format(song_rid)

源码展示：

# !/usr/bin/nev python
# -*-coding:utf8-*-

from threading import Thread
import tkinter as tk
import os, requests, jsonpath
from requests_html import HTMLSession
session = HTMLSession()


class kuwoSpider(object):

    def __init__(self):
        """定义可视化窗口，并设置窗口和主题大小布局"""
        self.window = tk.Tk()
        self.window.title('音乐下载器')
        self.window.geometry('800x600')

        """创建label_user按钮，与说明书"""
        self.label_user = tk.Label(self.window, text='请输入要下载的歌手名字：',
                                   font=('Arial', 12), width=130, height=2)
        self.label_user.pack()
        """创建label_user关联输入"""
        self.entry_user = tk.Entry(self.window, show=None, font=('Arial', 14))
        self.entry_user.pack(after=self.label_user)

        """创建label_passwd按钮，与说明书"""
        self.label_passwd = tk.Label(self.window, text="请输入爬取页数: ", font=('Arial', 12), width=30, height=2)
        self.label_passwd.pack()
        """创建label_passwd关联输入"""
        self.entry_passwd = tk.Entry(self.window, show=None, font=('Arial', 14))
        self.entry_passwd.pack(after=self.label_passwd)

        """创建Text富文本框，用于按钮操作结果的展示"""
        self.text1 = tk.Text(self.window, font=('Arial', 12), width=85, height=22)
        self.text1.pack()

        """定义按钮1，绑定触发事件方法"""

        self.button_1 = tk.Button(self.window, text='爬取', font=('Arial', 12), width=10, height=1,
                                  command=self.run)
        self.button_1.pack(before=self.text1)

        """定义按钮2，绑定触发事件方法"""
        self.button_2 = tk.Button(self.window, text='清除', font=('Arial', 12), width=10, height=1,
                                  command=self.parse_hit_click_2)
        self.button_2.pack(anchor="e")
    def run(self):
        Thread(target=self.parse_hit_click_1).start()

    def parse_hit_click_1(self):
        """定义触发事件1,调用main函数"""
        singer_name = self.entry_user.get()
        page = int(self.entry_passwd.get())
        self.main(singer_name, page)

    def main(self, singer_name, page):
        headers = 
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/'
                          '87.0.4280.88 Safari/537.36',
            'Referer': 请用自己的,
            'Cookie': 请用自己的,
            'csrf': 请用自己的,
            'Host': 'www.kuwo.cn'
        
        for i in range(page):
            start_url = f'http://www.kuwo.cn/api/www/search/searchMusicBykeyWord?key=singer_name&pn=' \\
                        f'i + 1&rn=30&httpsStatus=1&reqId=d301af60-6e1e-11ec-840f-dfca3a2ceb68'
            response = requests.get(start_url, headers=headers).json()
            # 解析得到song_names, song_rids
            song_names = jsonpath.jsonpath(response, '$..name')
            song_rids = jsonpath.jsonpath(response, '$..rid')
            # 遍历得到song_name, song_rid 构造song_info_url
            for song_name, song_rid in zip(song_names, song_rids):
                song_info_url = 'http://www.kuwo.cn/api/v1/www/music/playUrl?mid=' \\
                                '&type=music&httpsStatus=1&reqId=c0ac92a0-6e35-11ec-b428-05be0a87bc11'.format(song_rid)
                # 请求得到 song_info
                try:
                    song_info = requests.get(song_info_url, headers=headers).json()
                    # 解析得到song_url
                    song_url = jsonpath.jsonpath(song_info, '$..url')[0]

                    # 请求得到song_content
                    try:
                        song_content = requests.get(song_url).content
                    except Exception as e:
                        continue
                    # 创建文件夹
                    if not os.path.exists('./'.format(singer_name)):
                        os.mkdir('./'.format(singer_name))
                    # 保存数据
                    try:
                        with open('.//.mp3'.format(singer_name, song_name), 'wb')as f:
                            f.write(song_content)
                            self.text1.insert("insert", '********下载成功'.format(song_name))
                            self.text1.insert("insert", '\\n ')
                            self.text1.insert("insert", '\\n ')
                    except Exception as e:
                        continue
                except Exception as e:
                    continue

    def parse_hit_click_2(self):
        """定义触发事件2，删除文本框中内容"""
        self.entry_user.delete(0, "end")
        self.entry_passwd.delete(0, "end")
        self.text1.delete("1.0", "end")

    def center(self):
        """创建窗口居中函数方法"""
        ws = self.window.winfo_screenwidth()
        hs = self.window.winfo_screenheight()
        x = int((ws / 2) - (800 / 2))
        y = int((hs / 2) - (600 / 2))
        self.window.geometry('x++'.format(800, 600, x, y))

    def run_loop(self):
        """禁止修改窗体大小规格"""
        self.window.resizable(False, False)
        """窗口居中"""
        self.center()
        """窗口维持--持久化"""
        self.window.mainloop()


if __name__ == '__main__':
    b = kuwoSpider()
    b.run_loop()

代码仅供学习使用

祝大家学习python顺利

代码仅供学习使用