Pyton利用Ajax提取微博

提取马云微博

from urllib.parse import urlencode
import requests
from pyquery import PyQuery as pq

max_page = 14

base_url = 'https://m.weibo.cn/api/container/getIndex?'
headers = {
    'Host': 'm.weibo.cn',
    'Referer': 'https://m.weibo.cn/u/2145291155',
    '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',
}

def get_page(page):
    params = {
        'type': 'uid',
        'value': '2145291155',
        'containerid': '1076032145291155',
        'page': page
    }
    url = base_url + urlencode(params)
    try:
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return response.json()
    except requests.ConnectionError as e:
        print('Error', e.args)

def parse_page(json):
    if json:
        data = json.get('data')
        cards = data.get('cards')
        for item in cards:
            mblog = item.get('mblog')
            weibo = {}
            weibo['created_at'] = mblog.get('created_at')
            weibo['text'] = pq(mblog.get('text')).text()
            weibo['attitudes'] = mblog.get('attitudes_count')
            weibo['comments'] = mblog.get('comments_count')
            weibo['reposts'] = mblog.get('reposts_count')
            yield weibo

if __name__ == '__main__':
    for page in range(1,max_page +1):
        json = get_page(page)
        results = parse_page(json)
        for result in results:
            print(result)

修改成提取自己的微博

from urllib.parse import urlencode
import requests
from pyquery import PyQuery as pq

max_page = 14

base_url = 'https://m.weibo.cn/api/container/getIndex?'
headers = {
    'Host': 'm.weibo.cn',
    'Referer': 'https://m.weibo.cn/u/2145291155',
    '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',
}

def get_page(page):
    params = {
        'type': 'uid',
        # 用户uid
        'value': '1583624660',
        # 这个对应的值也需要更改
        'containerid': '1076031583624660',
        'page': page
    }
    url = base_url + urlencode(params)
    try:
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return response.json()
    except requests.ConnectionError as e:
        print('Error', e.args)

def parse_page(json):
    if json:
        data = json.get('data')
        cards = data.get('cards')
        for item in cards:
            mblog = item.get('mblog')
            weibo = {}
            weibo['created_at'] = mblog.get('created_at')
            weibo['text'] = pq(mblog.get('text')).text()
            weibo['attitudes'] = mblog.get('attitudes_count')
            weibo['comments'] = mblog.get('comments_count')
            weibo['reposts'] = mblog.get('reposts_count')
            yield weibo

if __name__ == '__main__':
    for page in range(1,max_page +1):
        json = get_page(page)
        results = parse_page(json)
        for result in results:
            print(result)