抓取淘宝商品信息并制作商品信息比价表（以口红为例）

快速抓取淘宝上口红信息
import requests
import re
import os

def getHtmlText(url):
try:
r=requests.get(url,timeout=30)
r.raise_for_status()
r.encoding=r.apparent_encoding
return r.text
except:
raise
print(“产生异常”)

def pageParser(ilt,html):
tlt=re.findall(r’\”raw_title\”:\”.*?\”’,html)
plt=re.findall(r’\”view_price\”:\”.*?\”’,html)
for i in range(len(plt)):
title=eval(tlt[i].split(“:”)[-1])
price=eval(plt[i].split(“:”)[-1])
ilt.append([price,title])

def printGoodsList(ilt):
if not os.path.exists(“file”):
os.mkdir(“file”)
fp=open(“file/infor.txt”,”w”)
header=”\n\t\t\t\t淘宝书包商品信息比价表”
print(header)
count=1
tplt=”{:4}\t{:8}\t{:16}”
title=tplt.format(“序号”,”价格”,”名称”)
print(title)
fp.write(header)
fp.write(title)
for i in ilt:
l=tplt.format(count,i[0],i[1])
print(l)
fp.write(l)
count+=1
fp.close()

def main():
goods=’口红’
infoList=[]
depth=10
start_url=r”https://s.taobao.com/search?q=“+goods
for i in range(depth):
try:
url=start_url+’&s=’+str(i*44)
html=getHtmlText(url)
pageParser(infoList,html)
except:
continue
printGoodsList(infoList)

if name==”main“:
main()

“`