python爬蟲學(xué)習(xí)之定向爬取淘寶商品價(jià)格，供大家參考，具體內(nèi)容如下

import requestsimport redef getHTMLText(url):  try:    r = requests.get(url, timeout=30)    r.raise_for_status() #如果發(fā)送了一個(gè)失敗請(qǐng)求(非200響應(yīng)),#我們可以通過 Response.raise_for_status() 來拋出異常:    r.encoding= r.apparent_encoding    return r.text  except:    return ""def parsePage(ilt,html):  try:    plt = re.findall(r'/"view_price/"/:/"[/d/.]*?/"',html) #正則表達(dá)式來匹配 "view_price":"/d/."類型的字符串    tlt = re.findall(r'/"raw_title/"/:/".*?/"',html)#正則表達(dá)式來匹配 "raw_title":".*?"類型的字符串,.*?是任意字符的最小匹配    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(hào)","價(jià)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 = '書包'  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()

以上就是本文的全部?jī)?nèi)容，希望對(duì)大家的學(xué)習(xí)有所幫助，也希望大家多多支持武林站長(zhǎng)站。