# -*- coding: utf-8 -*-
#需要的库
import requests as rq
import pandas as pd
from bs4 import BeautifulSoup as bs
from pymongo import MongoClient
client=MongoClient()
database=client.pachong 
collection=database.maoyan
data=[]
maodata=[]
mdata=[]
for i in range(10):
    #获取网址、伪装浏览器、获取网页源代码
    url='https://maoyan.com/board/4?offset='+str(i*10)
    header={'User-Agent':'Chrome/55.0.2883.75'}
    sources=rq.get(url,headers=header).text
    
    soup=bs(sources,'html.parser') #获取网页源代码转化成标准的HTML结构语句
    #查找需要的数据
    ranks=soup.find_all('i',class_="board-index")
    names=soup.find_all('p',class_='name')
    actors=soup.find_all('p',class_='star')
    times=soup.find_all('p',class_="releasetime")
    scores=soup.find_all('p',class_="score")
    
    for r,n,a,t,s in zip(ranks,names,actors,times,scores):
        rank=r.get_text().strip()
        name=n.get_text().strip()   #去掉两边的空格
        actor=a.get_text().strip()[2:]
        time=t.get_text().strip()[5:]
        score=s.get_text().strip()
        data.append([rank,name,actor,time,score])
        maodata={'rank':rank,'name':name,'actor':actor,'time':time,'score':score}
        mdata.append(maodata)
        #print('{}{}{}{}{}'.format(rank,name,actor,time,score))
            
        #保存数据
        #data=pd.DataFrame(data)

collection.insert(maodata)