Ajax请求的爬取

下面模拟Ajax请求将前10页微博全部爬取下来：

from urllib.parse import urlencode
import requests
from pyquery import PyQuery as pq
base_url = 'https://m.weibo.cn/api/container/getIndex?'#表示请求的url的前半部分

headers = {
    'Host':'m.weibo.cn',
    'Referer':'https://m.weibo.cn/u/2830678474',
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) '
                 'AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36',
    'X-Requested-With':'XMLHttpRequest'
}

def get_page(page):
    #构造参数字典
    params = {
        #固定参数
        'type':'uid',
        'value':'2830678474',
        'containerid':'1076032830678474',
        #可变参数
        'page':'page'
    }
    url = base_url + urlencode(params)#urlencode()方法将参数转化为URL的get请求然后形成新的URL
    try:
        response = requests.get(url,headers=headers)
        #如果请求成功就将内容解析为JSON返回
        if response.status_code == 200:
            return response.json()
    except requests.ConnectionError as e:
        print('Error',e.args)

#解析方法
def parse_page(json):
    if json:
        items = json.get('data').get('cards')
        for item in items:
            item = item.get('mblog')
            weibo = {}
            weibo['id'] = item.get('id')
            weibo['text'] = pq(item.get('text')).text()#利用pyquery将正文中的HTML标签去掉
            weibo['attitudes'] = item.get('comments_count')
            weibo['reposts'] = item.get('reposts_count')
            yield weibo

#遍历10页page
if __name__ == '__main__':
    for page in range(1,11):
        json = get_page(page)
        results = parse_page(json)
        for result in results:
            print(result)