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("序號","價格","商品名稱"))
count = 0
for g in ilt:
count = count + 1
print(tplt.format(count,g[0],g[1]))
def main():
goods = '電腦'
depth = 1
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()
運行結果：
轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/19770.html
上一篇：unity中如何用c#腳本控制fbx模型骨骼節點的移動？求具體代碼
下一篇：關于anaconda中'FloatInterval' object has no attribute 'overlaps'的問題