爬取直线网爬虫

运用多个模块写了一个爬取直线网ae模板的爬虫,主要用到request和bs4提取数据,base64将百度云地址解码,多线程threading和queue生产与消费关系(异步)访问抓取,并用pymysql将数据导入到mysql数据库中

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Date    : 2018-02-25 00:21:54
# @Author  : bb ([email protected])
# @Word    : python can change world!
# @Version : python3.6

import  requests
from bs4 import BeautifulSoup
import base64
from queue import Queue
from threading import Thread
from time import sleep
import sys
import pymysql


header={'Accept':'text/html,application/xhtml+xm…plication/xml;q=0.9,*/*;q=0.8',
'Accept-Encoding':'gzip, deflate',
'Accept-Language':'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
'Connection':'keep-alive',
'Cookie':'Hm_lvt_e6d53931d3c448a0325f4c2…a0325f4c254adbf071=1519469796',
'Host':'www.newcger.com',
'Upgrade-Insecure-Requests':'1',
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; …) Gecko/20100101 Firefox/58.0'}
q=Queue()

def base64encode(str2):
    encodestr = base64.b64encode(str2.encode('utf-8'))
    print(str(encodestr,'utf-8'))
#base64encode('abcr34r344r')

def basedecode(str2):
    str2=str2+'=='
    a=bytes(str2,'utf-8')
    url=str(base64.b64decode(a),'utf-8')
    print(url)
    return url
#basedecode('aHR0cHM6Ly9wYW4uYmFpZHUuY29tL3MvMWk2WVBoWHo')

def geturl(url2,header):
    conn=pymysql.connect(host='127.0.0.1',port=3306,db='dbname',user='yourname',passwd='yourpassword',charset='utf8')
    cur=conn.cursor()
    sleep(1)
    url="http://www.linecg.com/ae_content_52366.html"
    res=requests.get(url2,params=header).content
    soup=BeautifulSoup(res,"html.parser")
    html=soup.find_all('a')
    name=soup.title.string
    print(name)                     ###名称
    tag_list=set()
    data=soup.find_all('button')
    for i in html:
        #print(i.attrs['href'])
        try:
            tag=i.attrs['href'].split('/')[1]
            if tag =='search':
                tag_list.add(i.string)
        except:
            continue
    for i in data:
        zz=i.attrs['data-url']
        try:   
            zz=basedecode(zz)                 ##云盘地址
            #print(zz)
        except:
            continue
    print(tag_list)                        ##标签

    try:
        print(tag_list)                  #标签
        sql="insert into ae(ae_name,ae_html,ae_zz,ae_tag,web_name) values(%s,%s,%s,%s,%s)"
        cur.execute(sql,(str(name),str(url2),str(zz),str(tag_list),'直线网'))
        conn.commit()
        #new_id = cur.lastrowid
        #print(new_id)
    except Exception as e:
        print(e)
    finally:
        cur.close()
        conn.close()

def gethtml(page,header):
    url='http://www.linecg.com/ae_list_'+str(page)+'_0_0.html#c1'
    res=requests.get(url,params=header).content
    soup=BeautifulSoup(res,"html.parser")
    html=soup.find_all('h2')
    for i in html:
        html2='http://www.linecg.com'+str(i.a.attrs['href'])
        print(html2)
        q.put(html2)


def work():
    #print(q.qsize())
    while q.qsize()>0:
        html2=q.get()
        geturl(html2,header)

def main():
    for i in range(601,670):
        try:
            gethtml(i,header)
        except:
            continue
    for i in range(10):
        sleep(0.1)
        t=Thread(target=work)
        t.start()
        


if __name__ == '__main__':
    main()

你可能感兴趣的:(爬取直线网爬虫)