Python爬虫实战案例之爬取喜马拉雅音频数据详解

import requests
import parsel # 数据解析模块
import re

url = 'https://www.ximalaya.com/youshengshu/4256765/p{}/'.format(page)
headers = {
 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36'}

response = requests.get(url=url, headers=headers)
html_data = response.text

selector = parsel.Selector(html_data)
lis = selector.xpath('//div[@class="sound-list _is"]/ul/li')

for li in lis:
 try:
  title = li.xpath('.//a/@title').get() + '.m4a'
  href = li.xpath('.//a/@href').get()
  # print(title, href)

  m4a_id = href.split('/')[-1]
  # print(href, m4a_id)

  # 发送指定id值json数据请求(src)
  json_url = 'https://www.ximalaya.com/revision/play/v1/audio"htmlcode">

with open('video\\' + new_title, mode='wb') as f:
 f.write(m4a_data)
 print('保存完成:', title)


最后还要处理文件名非法字符


def change_title(title):
 pattern = re.compile(r"[\/\\\:\*\"\<\>\|]") # '/ \ : * " < > |'
 new_title = re.sub(pattern, "_", title) # 替换为下划线
 return new_title


完整代码


import re

import requests
import parsel # 数据解析模块


def change_title(title):
 """处理文件名非法字符的方法"""
 pattern = re.compile(r"[\/\\\:\*\"\<\>\|]") # '/ \ : * " < > |'
 new_title = re.sub(pattern, "_", title) # 替换为下划线
 return new_title


for page in range(13, 33):
 print('---------------正在爬取第{}页的数据----------------'.format(page))
 # 1.确定数据所在的链接地址(url) 逆向分析 网页性质(静态网页/动态网页)
 url = 'https://www.ximalaya.com/youshengshu/4256765/p{}/'.format(page)
 headers = {
  'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36'}

 # 2.通过代码发送url地址的请求
 response = requests.get(url=url, headers=headers)
 html_data = response.text
 # print(html_data)

 # 3.解析数据(要的, 筛选不要的) 解析音频的 id值
 selector = parsel.Selector(html_data)
 lis = selector.xpath('//div[@class="sound-list _is"]/ul/li')

 for li in lis:
  try:
   title = li.xpath('.//a/@title').get() + '.m4a'
   href = li.xpath('.//a/@href').get()
   # print(title, href)

   m4a_id = href.split('/')[-1]
   # print(href, m4a_id)

   # 发送指定id值json数据请求(src)
   json_url = 'https://www.ximalaya.com/revision/play/v1/audio"text-align: center">