- 版权声明:本文为博主原创文章,未经博主允许不得转载。 https://blog.csdn.net/kun1280437633/article/details/80529586
import requests
import re
class TaobaoSpider:
def getHTMLText(self,url):
try:
r = requests.get(url, timeout=30)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
return "failed\n"
def parsePage(self,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])#eval函数将字符串转为数字
title = eval(tlt[i].split(':')[1])
ilt.append([price , title])
except:
print("")
def printGoodsList(self,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 run(self):
goods = '洋酒'
start_url = 'https://s.taobao.com/search?q=' + goods
infoList = []
for i in range(2):
i += 1
for j in range(i):
try:
url = start_url + '&s=' + str(44*i)
html = self.getHTMLText(url)
self.parsePage(infoList, html)
except:
continue
self.printGoodsList(infoList)
if __name__ == '__main__':
spider = TaobaoSpider()
spider.run()