import requests
import re
这篇是学习网课,主要使用的是正则表达式匹配。
def getHTMLText(url):
try:
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:59.0) Gecko/20100101 Firefox/59.0'}
r=requests.get(url,headers=headers,timeout=30)
r.raise_for_status()
r.encoding=r.apparent_encoding
return r.text
except:
return "no"
def parsePage(ilt,html):
try:
plt = re.findall(r'\"view_price\"\:\"[\d\.]*\"',html)
tlt = re.findall(r'\"raw_title\"\:\".*?\"',html)
for i in range(len(plt)):
price = eval(plt[i].split(':')[1])
title = eval(tlt[i].split(':')[1])
ilt.append([price,title])
except:
print("no")
def printGoodslist(ilt):
tplt = "{:4}\t{:8}\t{:16}"
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 printGoodslist(ilt):
tplt = "{:4}\t{:8}\t{:16}"
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 = 'XXX' //通过改变goods值来检索
depth = 2
start_url = 'https://s.taobao.com/search?q='+goods
infolist = []#输出结果
for i in range(depth):
try:
url = start_url+'&s='+str(48*i)#48是一页的商品数
html = getHTMLText(url)
parsePage(infolist,html)
except:
continue
printGoodslist(infolist)
main()