Python爬虫练习之淘宝定价

转载于 2018-07-21 17:09:14 发布 · 343 阅读

文章标签：

#Python #爬虫

Python爬虫专栏收录该内容

6 篇文章

订阅专栏

本文介绍了一个使用Python进行的简单爬虫项目，旨在抓取淘宝网站上特定关键词搜索结果的商品价格和名称信息。通过发送HTTP请求获取网页内容，并利用正则表达式解析页面数据。

Python学习过程中的一个小练习，Python版本为3.7

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):
	plt = re.findall(r'"view_price":"[\d.]*"', html)
	tlt = re.findall(r'"raw_title":".*?"', html)
	for i in range(len(plt)):
		try:
			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("Index", "Price", "Name"))
	count = 0
	for g in ilt:
		count = count + 1
		print(tplt.format(count, g[0], g[1]))

def main():
	goods = '游戏'
	start_url = "https://s.taobao.com/search?q=" + goods
	infoList = []
	depth = 3
	for i in range(depth):
		try:
			url = start_url + '&s=' + str(44*i)
			html = getHTMLText(url)
			parsePage(infoList, html)
		except:
			continue
	printGoodsList(infoList)