import requests
import re
def getHTMLText(url):
kv = {'user-agent':'Mozilla/5.0'}
try:
r = requests.get(url, headers = kv, timeout = 30)
r.raise_for_status()
r.enconding = r.apparent_encoding
return r.text
except:
return '错误哦'
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 = evel(tlt[i].split(':')[1])
ilt.append([price, title])
except:
print("")
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 = '书包'
depth = 2 #页数
start_url = 'http://s.taobao.com/search?q=' + goods
infoList = [] #商品信息
for i in range(depth):
try:
url = start_url + '&s=' + str(44*i)
html = getHTMLText(url)
parsePage(infoList, html)
except:
continue #一件商品爬取失败 直接下一件
printGoodsList(infoList)
main()
难点在parsePage()函数,用了正则表达式,正则还是有点难度的 建议去这个网址学习 我看了下还是不错的
http://deerchao.net/tutorials/regex/regex.htm