python定向爬取淘宝商品价格
python爬虫学习之定向爬取淘宝商品价格,供大家参考,具体内容如下
import requests
import re
def getHTMLText(url):
try:
r = requests.get(url, timeout=30)
r.raise_for_status() #如果发送了一个失败请求(非200响应),#我们可以通过 Response.raise_for_status() 来抛出异常:
r.encoding= r.apparent_encoding
return r.text
except:
return ""
def parsePage(ilt,html):
try:
plt = re.findall(r'\"view_price\"\:\"[\d\.]*?\"',html) #正则表达式来匹配 "view_price":"\d\."类型的字符串
tlt = re.findall(r'\"raw_title\"\:\".*?\"',html)
#正则表达式来匹配 "raw_title":".*?"类型的字符串,.*?是任意字符的最小匹配
for i in range(len(plt)):
price = eval(plt[i].split(':')[1])
title = eval(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
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() 相关推荐
hotlinhao 2020-06-14
StevenSun空间 2020-05-30
浪味仙 2020-04-30
探索世界改变世界 2019-12-28
mathchao 2018-02-23
zhangcy 2012-04-25
hehezhou 2012-12-13
happybird00 2011-08-15
fenpisong0 2011-04-22
ach 2010-11-15
遨游天下 2019-06-29
zhangmingming 2015-05-20
李蓝箫 2014-10-06
xiaocao 2014-01-13
yrfh 2010-12-07
ZSAQ00 2010-08-05
谷歌底层营销灰烬 2009-10-16
CrazyDreamer 2017-07-27
fly00love 2019-05-07