[Python3爬虫从入门到精通]2.淘宝信息定向爬虫实例分析

import requests
import re


def getHTMLText(url):
    """
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36',
    }
    """
    try:
        #print(url)
        r = requests.get(url, timeout=30)
        r.raise_for_status() #不小心写成r.raise_forstatus一直没结果，以为需要添加heades才行呢，醉了醉了
        #print(r.status_code)
        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.findall(r'\"raw_title\"\:\".*?\"', html)
        plt = re.findall(r'"view_price":"[\d\.]*"', html)
        # \d     数字:[0-9]
        # *      匹配前一字符0到无数次
        # []     对应位置可以是字符集中任意字符
        tlt = re.findall(r'"raw_title":".*?"', html)
        # .      匹配除换行符“/n”外的字符
        # *?     数量词后跟?变为非贪婪模式,在""内非贪婪匹配，去掉后一个引号匹配为空 "view_price":"
        for i in range(len(plt)):
            # eval()函数 list,tuple,dict和string相互转化
            price = eval(plt[i].split(':')[1])
            title = eval(tlt[i].split(':')[1])
            ilt.append([price, title])
    except:
        print('')


def printGoodsList(ilt):
    tplt = '{:4}\t{:8}\t{:16}' #格式化输出
    print(tplt.format('序号', '价格', '商品名称'))
    count = 0
    for g in ilt:
        count = count + 1
        print(tplt.format(count, g[0], g[1]))


def main():
    goods = '书包' #搜索内容
    depth = 2 # 翻页深度
    start_url = 'https://s.taobao.com/search?q=' + goods
    infoList = []
    for i in range(depth):
        try:
            url = start_url + '&s' + str(44 * i)
            html = getHTMLText(url)
            parsePage(infoList, html)
        except:
            continue
    printGoodsList(infoList)


main()

50天后终于更了下一篇，继续努力！