跨境电商英文关键词拓展

这是一篇没有逼格的文章,来来去去都套路。做seo很多时候,加词等于加流量;废话不多说,下面针对一些电子商务平台来采集关键词,如阿里国际站,亚马孙,Ebay,敦煌网等,仅供学习参考!
采集阿里国际站下拉框关键词

#encoding=utf-8
import requests,re,random,time,multiprocessing

daili_list=[]
def ip():
    for x in open('E:\BaiduNetdiskDownload\daili.txt'):
        x = x.strip()
        daili_list.append(x)
    newip = random.choice(daili_list)
    return newip


def getUA():
    uaList = [
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+1.1.4322;+TencentTraveler)',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+2.0.50727;+.NET+CLR+3.0.4506.2152;+.NET+CLR+3.5.30729)',
        'Mozilla/5.0+(Windows+NT+5.1)+AppleWebKit/537.1+(KHTML,+like+Gecko)+Chrome/21.0.1180.89+Safari/537.1',
        'Mozilla/5.0 (Windows NT 6.1; rv:44.0) Gecko/20100101 Firefox/44.0',
        'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36',
        'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.82 Safari/537.36',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+1.1.4322;+TencentTraveler)',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+2.0.50727;+.NET+CLR+3.0.4506.2152;+.NET+CLR+3.5.30729)',
        'Mozilla/5.0+(Windows+NT+5.1)+AppleWebKit/537.1+(KHTML,+like+Gecko)+Chrome/21.0.1180.89+Safari/537.1',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1)',
        'Mozilla/5.0+(Windows+NT+6.1;+rv:11.0)+Gecko/20100101+Firefox/11.0',
        'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+SV1)',
        'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+GTB7.1;+.NET+CLR+2.0.50727)',
        'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+KB974489)',
        'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36',
        'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36',
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36',
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36',
    ]
    newUa = random.choice(uaList)
    return newUa



def gethtml(url,headers):
    while 1:
        try:
            newip=ip()  
            proxies={"http":"http://%s"%newip.strip()}  
            pages=requests.post(url,headers,proxies,timeout=10)
            html=pages.content
            code=pages.status_code
            if '302 Found' in html or code != 200:
                print u'代理失效重试',url
                continue
            else:
                return html
        except Exception, e:
            # print e
            continue


def getKeyword(url):

    headers={
        'Accept':'*/*',
        'Accept-Encoding':'gzip, deflate, sdch',
        'Accept-Language':'zh-CN,zh;q=0.8',
        'Connection':'keep-alive',
        'Host':'connectkeyword.alibaba.com',
        # 'Referer':'http://www.alibaba.com/trade/search?fsb=y&IndexArea=product_en&CatId=&SearchText=robot+vacuum+cleaner',
        'User-Agent':'%s'%getUA(),
    }

    html=gethtml(url,headers)

    re_data=re.compile(r"keywords:'(.*?)'")

    re_data=re.findall(re_data,html)

    for word in re_data:
        print word

urls = []
with open('word.txt') as f:
    for i in f.readlines():
        url='http://connectkeyword.alibaba.com/lenoIframeJson.htm?keyword=%s'%i.strip()
        urls.append(url)

if __name__ == '__main__':
    pool = multiprocessing.Pool(multiprocessing.cpu_count())
    for url in urls:
        pool.apply_async(getKeyword, (url, ))
    pool.close()
    pool.join()

采集阿里国际站相关关键词

#encoding=utf-8
import requests,re,time,random,threading


daili_list=[]
def ip():
    for x in open('E:\BaiduNetdiskDownload\daili.txt'):
        x = x.strip()
        daili_list.append(x)
    newip = random.choice(daili_list)
    return newip


def getUA():
    uaList = [
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+1.1.4322;+TencentTraveler)',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+2.0.50727;+.NET+CLR+3.0.4506.2152;+.NET+CLR+3.5.30729)',
        'Mozilla/5.0+(Windows+NT+5.1)+AppleWebKit/537.1+(KHTML,+like+Gecko)+Chrome/21.0.1180.89+Safari/537.1',
        'Mozilla/5.0 (Windows NT 6.1; rv:44.0) Gecko/20100101 Firefox/44.0',
        'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36',
        'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.82 Safari/537.36',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+1.1.4322;+TencentTraveler)',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+2.0.50727;+.NET+CLR+3.0.4506.2152;+.NET+CLR+3.5.30729)',
        'Mozilla/5.0+(Windows+NT+5.1)+AppleWebKit/537.1+(KHTML,+like+Gecko)+Chrome/21.0.1180.89+Safari/537.1',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1)',
        'Mozilla/5.0+(Windows+NT+6.1;+rv:11.0)+Gecko/20100101+Firefox/11.0',
        'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+SV1)',
        'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+GTB7.1;+.NET+CLR+2.0.50727)',
        'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+KB974489)',
        'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36',
        'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36',
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36',
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36',
    ]
    newUa = random.choice(uaList)
    return newUa


headers={
    'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
    'Accept-Encoding':'gzip, deflate, sdch',
    'Accept-Language':'zh-CN,zh;q=0.8',
    'Cache-Control':'max-age=0',
    'Connection':'keep-alive',
    'Host':'www.alibaba.com',
    'Referer':'http://www.alibaba.com/',
    'Upgrade-Insecure-Requests':'1',
    'User-Agent':'%s'%getUA(),
    }


def gethtml(url):
    while 1:
        try:
            newip=ip()  
            proxies={"http":"http://%s"%newip.strip()}  
            pages=requests.post(url,headers,proxies,timeout=10)
            # pages=requests.get(url,headers,timeout=10)
            html=pages.content
            code=pages.status_code
            if '302 Found' in html or code != 200:
                print u'代理失效重试',url
                continue
            else:
                return html
        except Exception, e:
            # print e
            continue


class alibaba(threading.Thread):
    def __init__(self, target):
        super(alibaba, self).__init__()
        self.target=target


    def run(self):
        self.get_data() 


    def get_data(self):
        for url in self.target:
            html=gethtml(url)

            re_data=re.compile(r"data-domdot='.*?'>(.*?)</a>")

            re_data=re.findall(re_data,html)

            for word in re_data:
                print word


target=[]
with open('word.txt') as f:
    for word in f.readlines():
        target.append('https://www.alibaba.com/products/%s.html'%word.strip())



if __name__ == '__main__':
    start_working=[]
    threads=10
    for i in range(threads):
        get_target=alibaba(target[((len(target)+threads-1)/threads) * i:((len(target)+threads-1)/threads) * (i+1)])
        start_working.append(get_target)
    for i in range(len(start_working)):
        start_working[i].start()
    for i in range(len(start_working)):
        start_working[i].join()

采集阿里国际站竞争对手对手关键词

#encoding=utf-8
import requests,re,time,random,pycurl,StringIO,multiprocessing

'''用来存放关键词的csv文件'''
op_csv=open('keyword.csv','a+')


'''构造头部headers'''
headers=[
    'authority:bairun.en.alibaba.com',
    'method:GET',
    'path:/productlist-2.html?isGallery=Y',
    'scheme:https',
    'accept:text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
    'accept-encoding:gzip, deflate, sdch, br',
    'accept-language:zh-CN,zh;q=0.8',
    # 'cookie:t=de2c15aaa52943b32f52047e5a99ca38; cna=GwWwEP55+xoCAXQVUP45eRCN; ali_apache_id=116.21.80.254.1479107002992.269078.3; xman_us_f=x_l=1; ali_beacon_id=116.21.80.254.1479107004102.167056.7; _ga=GA1.2.625111664.1480316413; _umdata=ED82BDCEC1AA6EB98C548550E8C44E0AE5F011C4983AF5532DF3387C1347EB9563BE680EE5DD1E6845CFE81BBEE63D88186BA677F30EB7AD6FF80CCC2BD4A3C798A6569850CD68BEB0973249799147735C5F1F0CC270D560F3C2D4966392052A; xman_f=vfBloadSAJR5D11GhbA21T8ukbUCuLph798C5cGdkR4CM6nJE5+SDIspmSWNAJjVpORPK888ZngYPtT+9acvoe9HNCphoIX0KhmARYzojiePaJr6eHAz7g==; history=product_selloffer%5E%0A60585412097%24%0A1821282900%24%0A60455100674; gangesweb-buckettest=116.21.80.254.1479107019387.1; ali_ab=116.21.80.254.1479107004134.0; ali_apache_track="mid=fastcleaner"; l=As/PHJMu9yY8YvH2zsyDpZ5032nZCiMW; isg=AtLSib8p3iaTwyK42wcgudK6I5jnytZ9bqvVYZwrAAVwr3KphHMmjdiPabxp
    'upgrade-insecure-requests:1',
    'user-agent:Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36',
]


'''加入代理'''
daili_list=[]
def ip():
    for x in open('E:\BaiduNetdiskDownload\daili.txt'):
        x = x.strip()
        daili_list.append(x)
    newip = random.choice(daili_list)
    return newip


'''re.search提取所需数据'''
def search(re_url,html):
    re_Data=re.search(re_url,html)
    if re_Data:
        return re_Data.group(1)
    else:
        return 'no'

'''获取html源码'''
def gethtml(url):
    while 1:
        try:
            # newip=ip()        #代理
            c = pycurl.Curl()   #通过curl方法构造一个对象
            c.setopt(pycurl.FOLLOWLOCATION, True)   #自动进行跳转抓取
            c.setopt(pycurl.MAXREDIRS,5)            #设置最多跳转多少次
            c.setopt(pycurl.CONNECTTIMEOUT, 60)     #设置链接超时
            c.setopt(pycurl.TIMEOUT,120)            #下载超时
            c.setopt(pycurl.ENCODING, 'gzip,deflate')   #处理gzip内容,有些傻逼网站,就算你给的请求没有gzip,它还是会返回一个gzip压缩后的网页
            # c.setopt(c.PROXY,newip)  # 代理
            c.fp = StringIO.StringIO()  
            c.setopt(pycurl.URL, url)   #设置要访问的URL
            c.setopt(pycurl.HTTPHEADER,headers)     #传入请求头
            # c.setopt(pycurl.POST, 1)
            # c.setopt(pycurl.POSTFIELDS, data)       #传入POST数据
            c.setopt(c.WRITEFUNCTION, c.fp.write)   #回调写入字符串缓存
            # c.setopt(pycurl.SSL_VERIFYPEER, 0)  
            # c.setopt(pycurl.SSL_VERIFYHOST, 0)  
            # c.setopt(pycurl.HEADERFUNCTION, headerCookie)  
            # c.setopt(pycurl.COOKIE,Cookie)
            c.perform()
            code = c.getinfo(c.HTTP_CODE)   #返回状态码
            html = c.fp.getvalue()  #返回源代码
            if '302 Found' in html or code != 200:
                print u'代理失效重试',url
                continue
            else:
                return html
        except Exception, e:
            # print e
            continue


'''主程序:获取标题和关键词'''
def getKeyword(url):
    html=gethtml(url)
    '''提取当前页面想要的url'''
    re_url=re.compile(r'<a href="(/product/.*?html)" target="_blank" title=".*?" data-domdot=".*?,mn:.*?,ext:.*?">[\s\S]*?</a>')

    re_url=re.findall(re_url,html)
    '''遍历url'''
    for i in re_url:
        '''构造url'''
        url='http://olinecentury.en.alibaba.com'+i.strip()
        html=gethtml(url)
        '''提取标题'''
        re_title=re.compile(r'<span class="title-text">(.*?)</span>')
        title=search(re_title,html).strip()
        '''提取关键词'''
        re_word=re.compile(r'<li><a href="http://www\.alibaba\.com/showroom/.*?html" class="qrPRskw">(.*?)</a></li>')
        keyword=search(re_word,html).strip()
        '''打印'''
        print u'标题:'+title,u'关键词:'+keyword
        op_csv.writelines('%s,%s\n'%(title,keyword))


'''拼接列表页的url,并存放到urls这个列表里'''
urls = []
for i in range(1,6):
    url='http://olinecentury.en.alibaba.com/productgrouplist-803875670-%d/vacuum_cleaner.html?isGallery=Y'%i
    urls.append(url)


'''多进程开始'''
if __name__ == '__main__':
    pool = multiprocessing.Pool(multiprocessing.cpu_count())
    for url in urls: #从urls这个列表遍历单条url
        pool.apply_async(getKeyword, (url, ))  #传入到主程序def getKeyword(url)
    pool.close()
    pool.join()

亚马逊下拉框关键词采集

#encoding=utf-8
import requests,re,random,time,multiprocessing,urllib


daili_list=[]
def ip():
    for x in open('E:\BaiduNetdiskDownload\daili.txt'):
        x = x.strip()
        daili_list.append(x)
    newip = random.choice(daili_list)
    return newip


def getUA():
    uaList = [
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+1.1.4322;+TencentTraveler)',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+2.0.50727;+.NET+CLR+3.0.4506.2152;+.NET+CLR+3.5.30729)',
        'Mozilla/5.0+(Windows+NT+5.1)+AppleWebKit/537.1+(KHTML,+like+Gecko)+Chrome/21.0.1180.89+Safari/537.1',
        'Mozilla/5.0 (Windows NT 6.1; rv:44.0) Gecko/20100101 Firefox/44.0',
        'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36',
        'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.82 Safari/537.36',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+1.1.4322;+TencentTraveler)',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+2.0.50727;+.NET+CLR+3.0.4506.2152;+.NET+CLR+3.5.30729)',
        'Mozilla/5.0+(Windows+NT+5.1)+AppleWebKit/537.1+(KHTML,+like+Gecko)+Chrome/21.0.1180.89+Safari/537.1',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1)',
        'Mozilla/5.0+(Windows+NT+6.1;+rv:11.0)+Gecko/20100101+Firefox/11.0',
        'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+SV1)',
        'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+GTB7.1;+.NET+CLR+2.0.50727)',
        'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+KB974489)',
        'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36',
        'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36',
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36',
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36',
    ]
    newUa = random.choice(uaList)
    return newUa



def gethtml(url,headers):
    while 1:
        try:
            # newip=ip()  
            # proxies={"http":"http://%s"%newip.strip()}  
            # pages=requests.post(url,headers,proxies,timeout=10)
            pages=requests.get(url,headers,timeout=10)
            html=pages.content
            code=pages.status_code
            if '302 Found' in html or code != 200:
                print u'代理失效重试',url
                continue
            else:
                return html
        except Exception, e:
            # print e
            continue


'''re.search提取所需数据'''
def search(re_url,html):
    re_Data=re.search(re_url,html)
    if re_Data:
        return re_Data.group(1)
    else:
        return 'no'


def getKeyword(url):

    headers={
        'Accept':'*/*',
        'Accept-Encoding':'gzip, deflate, sdch, br',
        'Accept-Language':'zh-CN,zh;q=0.8',
        'Connection':'keep-alive',
        'Host':'completion.amazon.com',
        # 'Referer':'http://www.alibaba.com/trade/search?fsb=y&IndexArea=product_en&CatId=&SearchText=robot+vacuum+cleaner',
        'User-Agent':'%s'%getUA(),
    }

    html=gethtml(url,headers)
    # print html

    re_data=re.compile(r'completion = (.*?)"nodes"')

    re_data=search(re_data,html)

    if re_data != 'no':

        re_word=re.compile(r'"(.*?)"')

        re_data=re.findall(re_word,re_data)

        for word in re_data:
            print word



urls = []
with open('word.txt') as f:
    for i in f.readlines():
        url='https://completion.amazon.com/search/complete?mkt=1&p=Search&x=String&search-alias=aps&q=%s'%i.strip()
        urls.append(url)

if __name__ == '__main__':
    pool = multiprocessing.Pool(multiprocessing.cpu_count())
    for url in urls:
        pool.apply_async(getKeyword, (url, ))
    pool.close()
    pool.join()

采集Ebay相关搜索词

#encoding=utf-8
import requests,re,random,time,multiprocessing,urllib


daili_list=[]
def ip():
    for x in open('E:\BaiduNetdiskDownload\daili.txt'):
        x = x.strip()
        daili_list.append(x)
    newip = random.choice(daili_list)
    return newip


def getUA():
    uaList = [
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+1.1.4322;+TencentTraveler)',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+2.0.50727;+.NET+CLR+3.0.4506.2152;+.NET+CLR+3.5.30729)',
        'Mozilla/5.0+(Windows+NT+5.1)+AppleWebKit/537.1+(KHTML,+like+Gecko)+Chrome/21.0.1180.89+Safari/537.1',
        'Mozilla/5.0 (Windows NT 6.1; rv:44.0) Gecko/20100101 Firefox/44.0',
        'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36',
        'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.82 Safari/537.36',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+1.1.4322;+TencentTraveler)',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+2.0.50727;+.NET+CLR+3.0.4506.2152;+.NET+CLR+3.5.30729)',
        'Mozilla/5.0+(Windows+NT+5.1)+AppleWebKit/537.1+(KHTML,+like+Gecko)+Chrome/21.0.1180.89+Safari/537.1',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1)',
        'Mozilla/5.0+(Windows+NT+6.1;+rv:11.0)+Gecko/20100101+Firefox/11.0',
        'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+SV1)',
        'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+GTB7.1;+.NET+CLR+2.0.50727)',
        'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+KB974489)',
        'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36',
        'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36',
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36',
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36',
    ]
    newUa = random.choice(uaList)
    return newUa



def gethtml(url,headers):
    while 1:
        try:
            # newip=ip()  
            # proxies={"http":"http://%s"%newip.strip()}  
            # pages=requests.post(url,headers,proxies,timeout=10)
            pages=requests.get(url,headers,timeout=10)
            html=pages.content
            code=pages.status_code
            if '302 Found' in html or code != 200:
                print u'代理失效重试',url
                continue
            else:
                return html
        except Exception, e:
            # print e
            continue


'''re.search提取所需数据'''
def search(re_url,html):
    re_Data=re.search(re_url,html)
    if re_Data:
        return re_Data.group(1)
    else:
        return 'no'


def getKeyword(url):

    headers={
        'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
        'Accept-Encoding':'gzip, deflate, sdch',
        'Accept-Language':'zh-CN,zh;q=0.8',
        'Connection':'keep-alive',
        'Host':'www.ebay.com',
        'Upgrade-Insecure-Requests':'1',
        # 'Referer':'http://www.alibaba.com/trade/search?fsb=y&IndexArea=product_en&CatId=&SearchText=robot+vacuum+cleaner',
        'User-Agent':'%s'%getUA(),
    }

    html=gethtml(url,headers)
    # print html

    re_data=re.compile(r'data-text="(.*?)"')

    re_data=re.findall(re_data,html)

    if re_data:
        for word in re_data:
            print word

urls = []
with open('word.txt') as f:
    for i in f.readlines():
        url='http://www.ebay.com/sch/i.html?_nkw=%s'%i.strip()
        urls.append(url)

if __name__ == '__main__':
    pool = multiprocessing.Pool(multiprocessing.cpu_count())
    for url in urls:
        pool.apply_async(getKeyword, (url, ))
    pool.close()
    pool.join()

采集敦煌网下拉框关键词

#encoding=utf-8
import requests,re,random,time,multiprocessing,urllib


daili_list=[]
def ip():
    for x in open('E:\BaiduNetdiskDownload\daili.txt'):
        x = x.strip()
        daili_list.append(x)
    newip = random.choice(daili_list)
    return newip


def getUA():
    uaList = [
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+1.1.4322;+TencentTraveler)',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+2.0.50727;+.NET+CLR+3.0.4506.2152;+.NET+CLR+3.5.30729)',
        'Mozilla/5.0+(Windows+NT+5.1)+AppleWebKit/537.1+(KHTML,+like+Gecko)+Chrome/21.0.1180.89+Safari/537.1',
        'Mozilla/5.0 (Windows NT 6.1; rv:44.0) Gecko/20100101 Firefox/44.0',
        'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36',
        'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.82 Safari/537.36',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+1.1.4322;+TencentTraveler)',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+2.0.50727;+.NET+CLR+3.0.4506.2152;+.NET+CLR+3.5.30729)',
        'Mozilla/5.0+(Windows+NT+5.1)+AppleWebKit/537.1+(KHTML,+like+Gecko)+Chrome/21.0.1180.89+Safari/537.1',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1)',
        'Mozilla/5.0+(Windows+NT+6.1;+rv:11.0)+Gecko/20100101+Firefox/11.0',
        'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+SV1)',
        'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+GTB7.1;+.NET+CLR+2.0.50727)',
        'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+KB974489)',
        'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36',
        'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36',
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36',
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36',
    ]
    newUa = random.choice(uaList)
    return newUa



def gethtml(url,headers):
    while 1:
        try:
            # newip=ip()  
            # proxies={"http":"http://%s"%newip.strip()}  
            # pages=requests.post(url,headers,proxies,timeout=10)
            pages=requests.get(url,headers,timeout=10)
            html=pages.content
            code=pages.status_code
            if '302 Found' in html or code != 200:
                print u'代理失效重试',url
                continue
            else:
                return html
        except Exception, e:
            # print e
            continue


'''re.search提取所需数据'''
def search(re_url,html):
    re_Data=re.search(re_url,html)
    if re_Data:
        return re_Data.group(1)
    else:
        return 'no'


def getKeyword(url):

    headers={
        'Accept':'*/*',
        'Accept-Encoding':'gzip, deflate, sdch, br',
        'Accept-Language':'zh-CN,zh;q=0.8',
        'Connection':'keep-alive',
        'Host':'www.dhgate.com',
        # 'Referer':'http://www.alibaba.com/trade/search?fsb=y&IndexArea=product_en&CatId=&SearchText=robot+vacuum+cleaner',
        'User-Agent':'%s'%getUA(),
        'X-Requested-With':'XMLHttpRequest',
    }

    html=gethtml(url,headers)
    # print html

    re_data=re.compile(r'<strong>(.*?)\|')

    re_data=re.findall(re_data,html)

    if re_data:
        for word in re_data:
            re_mark=re.compile(r"</strong>")
            word=re.sub(re_mark,'',word)
            print word



urls = []
with open('word.txt') as f:
    for i in f.readlines():
        url='http://www.dhgate.com/wholesale/searchTools.do?act=suggestKeywords&q=%s'%i.strip()
        urls.append(url)

if __name__ == '__main__':
    pool = multiprocessing.Pool(multiprocessing.cpu_count())
    for url in urls:
        pool.apply_async(getKeyword, (url, ))
    pool.close()
    pool.join()

采集敦煌网相关搜索词

#encoding=utf-8
import requests,re,random,time,multiprocessing,urllib


daili_list=[]
def ip():
    for x in open('E:\BaiduNetdiskDownload\daili.txt'):
        x = x.strip()
        daili_list.append(x)
    newip = random.choice(daili_list)
    return newip


def getUA():
    uaList = [
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+1.1.4322;+TencentTraveler)',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+2.0.50727;+.NET+CLR+3.0.4506.2152;+.NET+CLR+3.5.30729)',
        'Mozilla/5.0+(Windows+NT+5.1)+AppleWebKit/537.1+(KHTML,+like+Gecko)+Chrome/21.0.1180.89+Safari/537.1',
        'Mozilla/5.0 (Windows NT 6.1; rv:44.0) Gecko/20100101 Firefox/44.0',
        'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36',
        'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.82 Safari/537.36',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+1.1.4322;+TencentTraveler)',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1;+.NET+CLR+2.0.50727;+.NET+CLR+3.0.4506.2152;+.NET+CLR+3.5.30729)',
        'Mozilla/5.0+(Windows+NT+5.1)+AppleWebKit/537.1+(KHTML,+like+Gecko)+Chrome/21.0.1180.89+Safari/537.1',
        'Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.1;+SV1)',
        'Mozilla/5.0+(Windows+NT+6.1;+rv:11.0)+Gecko/20100101+Firefox/11.0',
        'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+SV1)',
        'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+GTB7.1;+.NET+CLR+2.0.50727)',
        'Mozilla/4.0+(compatible;+MSIE+8.0;+Windows+NT+5.1;+Trident/4.0;+KB974489)',
        'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36',
        'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36',
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36',
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36',
    ]
    newUa = random.choice(uaList)
    return newUa



def gethtml(url,headers):
    while 1:
        try:
            # newip=ip()  
            # proxies={"http":"http://%s"%newip.strip()}  
            # pages=requests.post(url,headers,proxies,timeout=10)
            pages=requests.get(url,headers,timeout=10)
            html=pages.content
            code=pages.status_code
            if '302 Found' in html or code != 200:
                print u'代理失效重试',url
                continue
            else:
                return html
        except Exception, e:
            # print e
            continue


'''re.search提取所需数据'''
def search(re_url,html):
    re_Data=re.search(re_url,html)
    if re_Data:
        return re_Data.group(1)
    else:
        return 'no'


def getKeyword(url):

    headers={
        'Accept':'*/*',
        'Accept-Encoding':'gzip, deflate, sdch, br',
        'Accept-Language':'zh-CN,zh;q=0.8',
        'Connection':'keep-alive',
        'Host':'www.dhgate.com',
        # 'Referer':'http://www.alibaba.com/trade/search?fsb=y&IndexArea=product_en&CatId=&SearchText=robot+vacuum+cleaner',
        'User-Agent':'%s'%getUA(),
        'X-Requested-With':'XMLHttpRequest',
    }

    html=gethtml(url,headers)
    # print html

    re_data=re.compile(r'<div class="relatesear-wrap">([\s\S]*?)</div>')

    re_data=search(re_data,html)

    if re_data != 'no':

        re_word=re.compile(r'<a href="http://www.dhgate.com/w/.*?">(.*?)</a>')

        re_data=re.findall(re_word,re_data)

        for word in re_data:
            re_mark=re.compile(r",")
            word=re.sub(re_mark,'',word)
            print word



urls = []
with open('word.txt') as f:
    for i in f.readlines():
        url='http://www.dhgate.com/wholesale/search.do?searchkey=%s'%i.strip()
        urls.append(url)

if __name__ == '__main__':
    pool = multiprocessing.Pool(multiprocessing.cpu_count())
    for url in urls:
        pool.apply_async(getKeyword, (url, ))
    pool.close()
    pool.join()

以后或许会补充更新!最后给大家送一个彩蛋给读者,居然这么认真拉到最下面!python彩蛋Zen of python!在交互模式下输入import this!
Zen of python

The Zen of Python, by Tim Peters

Beautiful is better than ugly.
# 优美胜于丑陋(Python以编写优美的代码为目标)

Explicit is better than implicit.
# 明了胜于晦涩(优美的代码应当是明了的,命名规范,风格相似)

Simple is better than complex.
# 简洁胜于复杂(优美的代码应当是简洁的,不要有复杂的内部实现)

Complex is better than complicated.
# 复杂胜于凌乱(如果复杂不可避免,那代码间也不能有难懂的关系,要保持接口简洁)

Flat is better than nested.
# 扁平胜于嵌套(优美的代码应当是扁平的,不能有太多的嵌套)

Sparse is better than dense.
# 间隔胜于紧凑(优美的代码有适当的间隔,不要奢望一行代码解决问题)

Readability counts.
# 可读性很重要(优美的代码是可读的)

Special cases aren’t special enough to break the rules.Although practicality beats purity.
# 即便假借特例的实用性之名,也不可违背这些规则(这些规则至高无上)

Errors should never pass silently.Unless explicitly silenced.
# 不要包容所有错误,除非你确定需要这样做(精准地捕获异常,不写except:pass风格的代码)

In the face of ambiguity, refuse the temptation to guess.
# 当存在多种可能,不要尝试去猜测

There should be one– and preferably only one –obvious way to do it.
# 而是尽量找一种,最好是唯一一种明显的解决方案(如果不确定,就用穷举法)

Although that way may not be obvious at first unless you’re Dutch.
# 虽然这并不容易,因为你不是 Python 之父(这里的Dutch是指Guido)

Now is better than never.Although never is often better than *right* now.
# 做也许好过不做,但不假思索就动手还不如不做(动手之前要细思量)

If the implementation is hard to explain, it’s a bad idea.If the implementation is easy to explain, it may be a good idea.
# 如果你无法向人描述你的方案,那肯定不是一个好方案;反之亦然(方案测评标准)

Namespaces are one honking great idea — let’s do more of those!
# 命名空间是一种绝妙的理念,我们应当多加利用(倡导与号召)

跨境电商英文关键词拓展》上有1条评论

发表评论

电子邮件地址不会被公开。