实例介绍
功能描述:
目标:获取淘宝搜索页面的信息,提取其中的商品名称和价格
理解:
- 淘宝的搜索接口
- 翻页的处理
技术路线:requests‐re
爬虫可行性:https://s.taobao.com/robots.txt
User-agent: *
Disallow: /
程序的结构设计
步骤1:提交商品搜索请求,循环获取页面
步骤2:对于每个页面,提取商品名称和价格信息
步骤3:将信息输出到屏幕上
2.实例编写
淘宝设定登录后才能搜索商品 给head加上用户cookie
import requests
import re
def getHTMLText(url):
try:
kv = {
'cookie': '复制当前用户登录的cookie',
'user-agent': 'Mozilla/5.0'}
r = requests.get(url, headers = kv,timeout=30)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except Exception as e:
print(e)
return "get error"
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('parse error')
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 += 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 Exception as e:
print('main error',e)
continue
printGoodsList(infoList)
main()