import requests
from urllib.parse import urlencode
from pyquery import PyQuery as pq
#from pymongo import MongoClient
import jieba
import wordcloud
base_url = 'https://m.weibo.cn/api/container/getIndex?'
headers = {
#'Host': 'm.weibo.cn',
'Referer': 'https://m.weibo.cn/u/6390210715',
'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 = 20
def get_page(page):
params = {
'type': 'uid',
'value': '6390210715',
'containerid': '1076036390210715',
'page': page
}
url = base_url + urlencode(params)
爬取我的微博并生成词云图
最新推荐文章于 2024-03-29 09:30:22 发布