python爬虫实现博客数据爬取

本次抓取利用requests库请求网页，返回json数据，所以需要通过json来解析text数据；pyquery解析网页数据；数据最终保存在mongodb中。

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

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',
}

client = MongoClient()
db = client['weibo']
collection = db['weibo']
max_page = 10


def get_page(page):
    params = {
        'type': 'uid',
        'value': '2830678474',
        'containerid': '1076032830678474',