python3_网页爬取_框架

学习实例淘宝页面爬取

#程序的结构设计
步骤1：提交商品搜索请求，循环获取页面
步骤2：对于每个页面，提取商品名称和价格信息
步骤3：将信息输出到屏幕上
步骤4：将数据存入数据库

#实例

import requests
import re
from sqlalchemy import create_engine

def gethtmltext(url):
    try:
        r=requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        return r.text
    except:
        return ''

def parsepage(ilt,html):
    try:
        plt=re.findall(r'\"view_price\"\:\"[\d\.]*\"',html)
        tlt=re.re.findall(r'\"raw_title\"\:\".*?\"',html)
        for i in range(len(plt)):
            price=eval(plt[i].split(':')[1])
            title=eval(tit[i].split(':')[1])
            ilt.append([price,title])
    except:
        print('')

def printgoodslist(ilt):
    tplt="{:4}\t{:8}\t{:16}"
    print(tplt.format('NO','price','name'))
    count=0
    for g in ilt:
        count=count+1
        print(tplt.format(count,g[0],g[1]))

    print('')

def main():
    goods='书包'
    depth=2
    start_url='https://s.taobao.com/search?q='+goods
    infolist=[]
    for i in range(depth):
        try:
            print('***geturl***')
            url=start_url+'&s='+str(i*44)
            print(url)
            print('***gethtml***')
            html=gethtmltext(url)
            print(len(html))
            print(html)
            print('***findhtml***')
            parsepage(infolist,html)
            printgoodslist(infolist)
        except:
            continue

main()