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)