import requests
import re
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(clist, 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])
clist.append([price, title])
except:
print('')
print(clist)
def printGoodslist(clist):
tplt = '{:4}\t{:10}\t{:16}'
print(tplt.format('序号','价格','商品名称'))
count = 0
for c in clist:
count += 1
print(tplt.format(count, c[0], c[1]))
def main():
goods = '书包'
depth = 2
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()
打印出来其中的clist列表是空的,是不是正则表达式写错了?