python处理3

import urllib.parseimport urllib.requestfrom bs4 import BeautifulSoupimport  randomimport timedef randHeader():    head_connection = ['Keep-Alive', 'close']    head_accept = ['text/html, application/xhtml+xml, */*']    head_accept_language = ['zh-CN,fr-FR;q=0.5', 'en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3']    head_user_agent = ['Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko',                       'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.95 Safari/537.36',                       'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; rv:11.0) like Gecko)',                       'Mozilla/5.0 (Windows; U; Windows NT 5.2) Gecko/2008070208 Firefox/3.0.1',                       'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070309 Firefox/2.0.0.3',                       'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070803 Firefox/1.5.0.12',                       'Opera/9.27 (Windows NT 5.2; U; zh-cn)',                       'Mozilla/5.0 (Macintosh; PPC Mac OS X; U; en) Opera 8.0',                       'Opera/8.0 (Macintosh; PPC Mac OS X; U; en)',                       'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.12) Gecko/20080219 Firefox/2.0.0.12 Navigator/9.0.0.6',                       'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Win64; x64; Trident/4.0)',                       'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0)',                       'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E)',                       'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Maxthon/4.0.6.2000 Chrome/26.0.1410.43 Safari/537.1 ',                       'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E; QQBrowser/7.3.9825.400)',                       'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:21.0) Gecko/20100101 Firefox/21.0 ',                       'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.92 Safari/537.1 LBBROWSER',                       'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; BIDUBrowser 2.x)',                       'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/3.0 Safari/536.11']    header = {        'Connection': head_connection[0],        'Accept': head_accept[0],        'Accept-Language': head_accept_language[1],        'User-Agent': head_user_agent[random.randrange(0, len(head_user_agent))]    }    return headerdef getDataById(queryId):    req = urllib.request.Request(url="https://www.amazon.com/dp/"+str(queryId) , headers=randHeader())    webpage = urllib.request.urlopen(req)    html = webpage.read()    soup = BeautifulSoup(html, 'html.parser')    content = soup.find_all("span" , id = "asTitle")    return content[0].stringif __name__ == '__main__':    qs = []    with open('asin.txt', 'r') as f:        for line in f.readlines():            qs.append(line.strip())    n = len(qs)    k = 0    file_object = open("data/amazon" + str(k) + ".txt" , 'a')    file_object.write("asin, state\n")    for i in range(n):        print("运行第" + str(i) + "个数据" )        print("asin = " + qs[i])        if i % 100 == 0 and i > 0 :            k += 1            file_object = open("data/amazon" + str(k) + ".txt" , 'a')            file_object.write("asin, state\n")        state = getDataById(qs[i])        print("状态 = " + state +"\n")        file_object.write(qs[i] + "," + state+"\n")    file_object.close()    # for q in qs:    #     state = getDataById(q)    #     file_object.write(q + "," + state+"\n")    # file_object.close()