微博爬虫

import requests
from urllib.parse import urlencode
from pyquery import PyQuery as pq
from pymongo import MongoClient   #链接Mongdb数据库
import json

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 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36            ',
    'X-Requested-With': 'XMLHttpRequest',
}
client = MongoClient()    #链接数据库
db = client['weibo']    #数据库下指定操做哪一个数据库表头
collection = db['weibo']    #指定数据库表头db之下小列表weibo
max_page = 10

def get_page(page):   #获取网页json文本,返回值为json
    params = {
        'type': 'uid',
        'value': '2830678474',
        'containerid': '1076032830678474',
        'page': page
    }
    url = base_url + urlencode(params)
    try:
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return response.json(), page
    except requests.ConnectionError as e:
        print('Error', e.args)

def parse_page(json, page: int):
    if json:
        items = json.get('data').get('cards')
        for index, item in enumerate(items):
            if page == 1 and index == 1:
                continue
            else:
                item = item.get('mblog', {})
                weibo = {}
                weibo['id'] = item.get('id')
                weibo['text'] = pq(item.get('text')).text()
                weibo['attitudes'] = item.get('attitudes_count')
                weibo['comments'] = item.get('comments_count')
                weibo['reposts'] = item.get('reposts_count')
                yield weibo

def save_to_mongo(result):
    if collection.insert_one(result):    #链接数据库且将数据添加
        print('Saved to Mongo')

if __name__ == '__main__':
     for page in range(1, max_page + 1):
        json1 = get_page(page)
        results = parse_page(*json1)    #*表示参数是一个元组,**表示形参是一个字典
        for result in results:
            print(result)
            with open('456789.json','a',encoding='utf-8') as file:
                file.write(json.dumps(result,ensure_ascii=False))
                file.write('\n')
            save_to_mongo(result)