正则表达式爬虫实例

跟着mooc的课程动手做了一个简单实例

import requests
import re

def getHTMLText(url,code = 'utf-8'):
	try:
		r = requests.get(url,timeout = 20)
		r.raise_for_status()
		r.encoding = code
		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])			#eval用来去掉字符串两侧的引号
			title = eval(tlt[i].split(':')[1])
			ilt.append([title,price])
	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 i in range(len(ilt)):
		print(tplt.format(i+1,ilt[i][1],ilt[i][0]))
	#count = 0
	#for g in ilt:
	#	count += 1
	#	print(tplt.format(count,g[1],g[0]))

def main():
	goods = 'xbox'
	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()