import requests from urllib.parse import urlencode base_url = 'https://m.weibo.cn/api/container/getIndex?' headers = { 'Host': 'm.weibo.cn', 'Referer': 'https://m.weibo.cn/u/2830678474', 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36', 'X-Requested-With': 'XMLHttpRequest', } # 模拟请求头 def get_page(page): params = { 'type': 'uid', 'value': '2830678474', 'containerid': '1076032830678474', 'page': page } url = base_url + urlencode(params) response = requests.get(url, headers=headers) return response.json() # 由于内容是由ajax加载,响应的内容是json的形式 if __name__ == '__main__': for page in range(1,3): result = get_page(page) print(result)
Python爬虫基础(一)——HTTP (2)
内容版权声明:除非注明,否则皆为本站原创文章。