Exemplo n.º 1
0
def _label_d_v(value):
    re = etree.HTML(value)
    res = re.xpath("//text()")
    string = '\n\n\n'
    for i in res:
        string = string + i
    return string
Exemplo n.º 2
0
def ResetPrefs():
    items = []
    #Log(result)
    Data.SaveObject('Started', False)

    re = XML.ElementFromURL(
        'http://127.0.0.1:32400/:/plugins/com.plexapp.plugins.dreambox/prefs',
        timeout=3)
    settings = re.xpath('//Setting')
    vals = {}
    for s in settings:
        pref = s.xpath('./@id')[0]
        vals[pref] = None
        Log(pref)
        re2 = HTTP.Request(
            'http://127.0.0.1:32400/:/plugins/com.plexapp.plugins.dreambox/prefs/set?{}='
            .format(pref),
            timeout=5)
        re2.load()

    items.append(
        DirectoryObject(
            key=Callback(MainMenu),
            title='User Prefs reset. Restart plugin to load DefaultPrefs'))
    items = check_empty_items(items)
    oc = ObjectContainer(objects=items,
                         title2='Reset user preference',
                         no_history=True)
    return oc
Exemplo n.º 3
0
    def parse_search(self,response):

        item = WeiboItem()
        results=response.xpath('//div[@class="card-wrap"]')

        from scrapy.shell import inspect_response
        inspect_response(response,self)

        for re in results:
            contents = re.xpath('./div/div/div[@class="content"]/p[@class="txt"]')
            if(len(contents) > 1):
                item['content'] = contents[1].xpath('string(.)').extract_first()
            elif (len(contents) == 1):
                item['content'] = contents[0].xpath('string(.)').extract_first()

            else:
                item['content']=''

            item['time'] = re.xpath('./div/div/div[@class="content"]/p[@class="from"]/a').xpath('string(.)').extract_first()
            item['name'] = re.xpath('./div/div/div[@class="content"]/div[@class="info"]//a[@class="name"]/@nick-name').extract_first()

            yield item
Exemplo n.º 4
0
def ResetPrefs():
    items = []
    #Log(result)
    Data.SaveObject('Started', False)

    re = XML.ElementFromURL('http://127.0.0.1:32400/:/plugins/com.plexapp.plugins.dreambox/prefs', timeout=3)
    settings = re.xpath('//Setting')
    vals ={}
    for s in settings:
        pref =s.xpath('./@id')[0]
        vals[pref] = None
        Log(pref)
        re2 = HTTP.Request('http://127.0.0.1:32400/:/plugins/com.plexapp.plugins.dreambox/prefs/set?{}='.format(pref), timeout=5)
        re2.load()


    items.append(DirectoryObject(key=Callback(MainMenu),
                                         title='User Prefs reset. Restart plugin to load DefaultPrefs'))
    items = check_empty_items(items)
    oc = ObjectContainer(objects=items, title2='Reset user preference', no_history=True)
    return oc
Exemplo n.º 5
0
import re

f = open(
    'E:/PycharmProjects/Spider/Distributed_twitter_spider/Distributed_twitter_spider/util/url.txt',
    'rb')
res = f.read()
# print(res)
f.close()

# articles_pattern = re.compile(r'<article.+?</article>')
# articles = re.findall(articles_pattern, res.decode('utf-8'))
# print('articles:',articles)
# <a href="tel:+886223113731">

tel_pattern = re.compile(r'<a href="tel:(.*?)">')
tel = re.findall(tel_pattern, res.decode('utf-8'))[0]
# print('tel:',tel)

basic_info_pattern = re.xpath('./div[@class=]')
Exemplo n.º 6
0
    def parse(self, response):

        re = response
        # print(response.text)
        # print("2222222")

        # 订单状态
        order_st = re.xpath(
            '//*[@id="order-form"]/div[1]/div[2]/div[1]/div[2]/p/text()'
        ).extract()[0]

        # 订单id
        order_id = re.xpath(
            '//*[@id="order-form"]/div[1]/div[2]/div[1]/div[1]/p/text()'
        ).extract()[0]

        if order_st == '已发货':

            print(order_id)
            # 物流单号
            tracking_number = re.xpath(
                '//*[@id="order-form"]/div[5]/div[2]/div[2]/div[1]/input/@value'
            ).extract()[0]
            # tracking_number = re.xpath('//*[@id="order-form"]/div[4]/div[2]/div[2]/div[1]/input/@value').extract()[0]
            # print(tracking_number)
            # 马帮发货时间
            expresstime = re.xpath(
                '//*[@id="order-form"]/div[1]/div[2]/div[8]/div[2]/input/@value'
            ).extract()[0]
            # 马帮订单id
            mb_orderid = re.xpath(
                '//*[@id="order-form"]/div[1]/div[1]/input[1]/@value').extract(
                )[0]
            # print(mb_orderid)
            # print(order_st)

            # 传输数据
            mb_meta = {
                'order_id': order_id,
                'tracking_number': tracking_number,
                'order_st': order_st,
                'expresstime': expresstime,
                'mb_orderid': mb_orderid
            }
            # 获取合并订单的sku
            # print(mb_meta)
            url = 'https://aamz.mabangerp.com/index.php?mod=order.findrelevantinfo'

            headers = {
                # "Accept": "application/json, text/javascript, */*; q=0.01",
                # "Accept-Encoding": "gzip, deflate, br",
                # "Accept-Language": "zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2",
                # "Cache-Control": "no-cache",
                # "Connection": "keep-alive",
                # "Content-Type": "application/json; charset=UTF-8",

                # "Host": "aamz.mabangerp.com",
                # "Content-Length": "",
                # "X-Requested-With": "XMLHttpRequest",
                # "Referer": "https://aamz.mabangerp.com/index.php?mod=order.detail&platformOrderId=0O43LJNW&orderStatus=2&orderTable=2&tableBase=2&cMKey=MABANG_ERP_PRO_MEMBERINFO_LOGIN_191565&lang=cn",

                # 注意user-agent不要出现空格
                "User-Agent":
                "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:71.0) Gecko/20100101 Firefox/71.0",
            }

            # post请求数据
            data1 = {'orderId': mb_orderid, 'type': '1', 'tableBase': '2'}
            # cookies数据
            cookies = "lang=cn; signed=222014_00f6735cc675f0abb6f483d9913f72bf; gr_user_id=63993efb-e900-472c-9e8d-4d3e5c1832b2; stock_show_product_data_cookie=ico-minus-circle; employ_rows_per_page_data_cookie=10; stock_data_js_cookie_is_change_weight=1; stock_data_js_cookie_is_change_name=1; CRAWL_KANDENG_KEY=K6uqW0ZkQEouz0n1adoI%2FWqfFs2PbJ8%2BCpQKvtnzAvWpTX174VXBmq5L9cDOSOj%2Bm2IcDf7pRauH34yzR4OEyw%3D%3D; MULTI_LANGUAGE_TYPE=%2BYjZ6oacL7xJ%2FKOcmBg9Z7cTOqi7UgOUgujRs4KQ4Ms%3D; mabang_lite_rowsPerPage=500; PHPSESSID=gbtnacjhjolnnvb3cmcijbcbp0; loginLiteCookie=a%3A2%3A%7Bs%3A8%3A%22username%22%3Bs%3A6%3A%22222014%22%3Bs%3A9%3A%22passsword%22%3Bs%3A32%3A%2282bc6a8ec7fca9d8d0d844f2882546e7%22%3B%7D; event_rember12_222014=0"
            cookies = {
                i.split("=")[0]: i.split("=")[1]
                for i in cookies.split("; ")
            }

            # yield scrapy.Request(url=url, cookies=self.cookies, headers=headers, meta=mb_meta, callback=self.parse2)
            yield scrapy.FormRequest(url=url,
                                     cookies=cookies,
                                     formdata=data1,
                                     headers=headers,
                                     meta=mb_meta,
                                     callback=self.detail_parse)
        else:
            print(order_id + "订单状态为:" + order_st)
Exemplo n.º 7
0
    def parse(self, response):

        re = response
        # print(response.text)

        # 处理数据
        # 订单id
        order_id = re.xpath(
            '//*[@id="order-form"]/div[1]/div[2]/div[1]/div[1]/p/text()'
        ).extract()[0]
        # 物流单号
        tracking_number = re.xpath(
            '//*[@id="order-form"]/div[5]/div[2]/div[2]/div[1]/input/@value'
        ).extract()[0]
        # 订单状态
        order_st = re.xpath(
            '//*[@id="order-form"]/div[1]/div[2]/div[1]/div[2]/p/text()'
        ).extract()[0]
        # 马帮发货时间
        expresstime = re.xpath(
            '//*[@id="order-form"]/div[1]/div[2]/div[8]/div[2]/input/@value'
        ).extract()[0]
        # 马帮订单id
        mb_orderid = re.xpath(
            '//*[@id="order-form"]/div[1]/div[1]/input[1]/@value').extract()[0]
        # print(mb_orderid)
        # print(order_st)

        if order_st == '已发货':
            # 传输数据
            mb_meta = {
                'order_id': order_id,
                'tracking_number': tracking_number,
                'order_st': order_st,
                'expresstime': expresstime,
                'mb_orderid': mb_orderid
            }
            # 获取合并订单的sku
            url = 'https://aamz.mabangerp.com/index.php?mod=order.findrelevantinfo'

            headers = {
                # "Accept": "application/json, text/javascript, */*; q=0.01",
                # "Accept-Encoding": "gzip, deflate, br",
                # "Accept-Language": "zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2",
                # "Cache-Control": "no-cache",
                # "Connection": "keep-alive",
                # "Content-Type": "application/json; charset=UTF-8",

                # "Host": "aamz.mabangerp.com",
                # "Content-Length": "",
                # "X-Requested-With": "XMLHttpRequest",
                # "Referer": "https://aamz.mabangerp.com/index.php?mod=order.detail&platformOrderId=0O43LJNW&orderStatus=2&orderTable=2&tableBase=2&cMKey=MABANG_ERP_PRO_MEMBERINFO_LOGIN_191565&lang=cn",

                # 注意user-agent不要出现空格
                "User-Agent":
                "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:71.0) Gecko/20100101 Firefox/71.0",
            }

            # post请求数据
            data1 = {'orderId': mb_orderid, 'type': '1', 'tableBase': '2'}
            # cookies数据
            cookies = "gr_user_id=493499a8-83fc-4e47-87c3-08b1ded6df3c; MULTI_LANGUAGE_TYPE=%2BYjZ6oacL7xJ%2FKOcmBg9Z7cTOqi7UgOUgujRs4KQ4Ms%3D; lang=cn; stock_show_product_data_cookie=ico-minus-circle; stock_data_js_cookie_is_change_weight=1; mabang_lite_rowsPerPage=500; stock_data_js_cookie_is_change_name=1; order_data_js_cookie_orderErrorbysVal=paidTime; order_data_js_cookie_orderErrorbydacname=orderByspaidTime; order_data_js_cookie_orderErrorbydacnameval=down; order_data_js_cookie_isSyn=2; employ_rows_per_page_data_cookie=50; order_data_js_cookie_isImmediately=1; signed=222014_00f6735cc675f0abb6f483d9913f72bf; PHPSESSID=gjgkl12ntct9knahgq66qtlks1; event_rember12_222014=0; CRAWL_KANDENG_KEY=K6uqW0ZkQEouz0n1adoI%2FWqfFs2PbJ8%2BCpQKvtnzAvWpTX174VXBmq5L9cDOSOj%2Bm2IcDf7pRauH34yzR4OEyw%3D%3D; loginLiteCookie=a%3A2%3A%7Bs%3A8%3A%22username%22%3Bs%3A6%3A%22222014%22%3Bs%3A9%3A%22passsword%22%3Bs%3A32%3A%22f1c7edfb07a416030a0f976bac902add%22%3B%7D"
            cookies = {
                i.split("=")[0]: i.split("=")[1]
                for i in cookies.split("; ")
            }

            # yield scrapy.Request(url=url, cookies=self.cookies, headers=headers, meta=mb_meta, callback=self.parse2)
            yield scrapy.FormRequest(url=url,
                                     cookies=cookies,
                                     formdata=data1,
                                     headers=headers,
                                     meta=mb_meta,
                                     callback=self.detail_parse)
        else:
            pass