python————精简头条街拍抓取-优快云博客

本文介绍了一种使用Python爬取今日头条图片的方法，通过解析JSON数据获取文章链接，再从文章页面中提取图片URL并下载保存。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import json
import os
import re
from _md5 import md5
import random
import user_agent
import requests
from json import loads
image_list = []
def get_url():
	url = 'https://www.toutiao.com/search_content/?offset=0&format=json&keyword=%E8%A1%97%E6%8B%8D&autoload=true&count=20&cur_tab=3&from=gallery&pd='
	result = requests.get(url)
	article_url = []
	if result.status_code == 200 :
		info = loads(result.text)
		get_info = info['data']
		# print(type(get_info))#列表信息；
		for i in get_info:
			# print(type(i))#字典类型；
			article_url.append(i['article_url'])
		return article_url
			# for key in i:#键名；
			# 	print(key)
header = {'user-agent': 'user_agent'}
def parse_url(url):
	try:
		for i in url:
			result = requests.get(i,headers=header)
			info = re.search(r'JSON.parse\("(.*?)"\),',result.text)
			image_info = re.search(r'url\\":\\"(.*?)\\"',info.group(1),re.S)
			image_url = re.sub('\\\\','',image_info.group(1))
			image_list.append(image_url)
			for i in image_list:
				image = requests.get(i)
				path = 'E:\python\练习\python_try\image'
				file_path = '{0}/{1}.{2}'.format(path, md5(image.content).hexdigest(), 'jpg')
				if not os.path.exists(file_path):
					with open(file_path, 'wb') as f:
						f.write(image.content)
						print('正在下载。。。',i)
						f.close()
	except AttributeError:
		pass
if __name__ == '__main__':
    url = get_url()
    parse_url(url)