Network Preview爬虫笔记

这个是文档

from lxml import etree
from pyquery import PyQuery as pq
import time
import json
import requests
headers={
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36'
         }
url="https://m.weibo.cn/api/container/getIndex?containerid=100103type%3D1%26q%3D%E7%96%AB%E6%83%85&page_type=searchall&page=2"
page_text=requests.get(url=url,headers=headers).text

cards=json.loads(page_text)["data"]["cards"]

for card in cards:
    a=pq(card["mblog"]["text"]).text()
    b=card["mblog"]["source"]
    c=card["mblog"]["user"]["screen_name"]
    d=card["mblog"]["created_at"]
    e=card["scheme"]
    print(a)
    print(b)
    print(c)
    print(d)
    print(e)
    print('##############################################################')

这个是json()

from lxml import etree
from pyquery import PyQuery as pq
import time
import json
import requests
headers={
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36'
         }
url="https://m.weibo.cn/api/container/getIndex?containerid=100103type%3D1%26q%3D%E7%96%AB%E6%83%85&page_type=searchall&page=2"
page_text=requests.get(url=url,headers=headers).json()

cards=page_text["data"]["cards"]

for card in cards:
    a=pq(card["mblog"]["text"]).text()
    b=card["mblog"]["source"]
    c=card["mblog"]["user"]["screen_name"]
    d=card["mblog"]["created_at"]
    e=card["scheme"]
    print(a)
    print(b)
    print(c)
    print(d)
    print(e)
    print('##############################################################')