- #CrowTaobaoPrice.py
- 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("")
- 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 = 3
- 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()
python编程-26:实例2-淘宝商品信息定向爬虫_彭世瑜_新浪博客
原创
©著作权归作者所有:来自51CTO博客作者彭世瑜的原创作品,请联系作者获取转载授权,否则将追究法律责任
源码:
提问和评论都可以,用心的回复会被更多人看到
评论
发布评论
相关文章