1. import requests, time
    2. from pyquery import PyQuery as pq
    3. # 这里的抓取最不同的就是，翻页参数since_id的获取，这个参数的下一页是在上一页的since_id中，所以要从响应中获取并更新since_id，其余就没有什么难度了
    6. # 获取响应数据
    7. def get_page(url):
    8.     print('since_id----', since_id)
    9.     headers = {
    10.         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36',
    11.         'Referer': 'https://m.weibo.cn/u/2830678474',
    12.         'X-Requested-With': 'XMLHttpRequest'
    13.     }
    14.     params = {
    15.         'type': 'uid',
    16.         'value': '2830678474',
    17.         'containerid': '1076032830678474',
    18.         'since_id': since_id
    19.     }
    20.     try:
    21.         response = requests.get(url, headers=headers, params=params)
    22.         if response.status_code == 200:
    23.             return response.json()
    24.     except requests.ConnectionError as e:
    25.         print('Error', e)
    27. # 解析响应数据，包括更新since_id参数
    28. def parse_page(json_data):
    29.     global since_id
    30.     items = json_data.get('data').get('cards')
    31.     for item in items:
    32.         weibo = {}
    33.         weibo['id'] = item.get('mblog').get('id')
    34.         weibo['created_at'] = item.get('mblog').get('created_at')
    35.         weibo['text'] = pq(item.get('mblog').get('text')).text()
    36.         weibo['bid'] = item.get('mblog').get('bid')
    37.         since_id = json_data.get('data').get('cardlistInfo').get('since_id')
    38.         yield weibo
    40. # 执行主程序
    41. def run(page):
    42.     url = 'https://m.weibo.cn/api/container/getIndex'
    43.     json_data = get_page(url)
    44.     results = parse_page(json_data)
    45.     for result in results:
    46.         print(result)
    47.     print(f'第{page}页完成')
    51. if __name__ == '__main__':
    52.     since_id = ''
    53.     for page in range(3):
    54.         run(page+1)