目标是爬取商品页面的商品名称和价格,但只能打印出表头
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(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("666")
def printGoodsList(ilt):
tplt = '{:4}\t{:8}\t{:16}'
print(tplt.format("序号","价格","名称"))
count = 0
for j in ilt:
count = count + 1
print(tplt.format(count, j[0],j[1]))
def main():
goods = '书包'
depth = 2
u = 'https://s.taobao.com/search?q=' + goods
infolist = []
for i in range(depth):
try:
url = u + '&s=' + str(44*i)
html = getHtmlText(url)
parsePage(infolist, html)
except:
continue
printGoodsList(infolist)
main()
序号 价格 名称