Python Regex.getAllSearchedData方法代码示例

# 需要导入模块: from utils.Regex import Regex [as 别名]
# 或者: from utils.Regex.Regex import getAllSearchedData [as 别名]
class NisbetProduct(QtCore.QThread):
    scrapProductData = QtCore.pyqtSignal(object)
    stopThread = QtCore.pyqtSignal(int)

    def __init__(self):
        QtCore.QThread.__init__(self)
        self.isExiting = False
        self.totalProducts = 0
        self.logger = LogManager(__name__)
        self.spider = Spider()
        self.regex = Regex()
        dupCsvReader = Csv()
        self.dupCsvRows = dupCsvReader.readCsvRow('nisbets.csv', 0)
        self.csvWriter = Csv('nisbets.csv')
        self.mainUrl = 'http://www.nisbets.co.uk'
        csvHeaderList = ['URL', 'Product Code', 'Product Technical Specifications', 'Product Name', 'Brand',
                         'Product Price', 'Product Short Description',
                         'Product Long Description', 'Image File Name', 'User Manual File Name',
                         'Exploded View File Name', 'Spares Code', 'Accessories', 'Product Status' 'Category1',
                         'Category2', 'Category3',
                         'Category4']
        if 'URL' not in self.dupCsvRows:
            self.csvWriter.writeCsvRow(csvHeaderList)
            self.dupCsvRows.append(csvHeaderList[0])

        self.utils = Utils()

    def run(self):
        self.scrapData()

    def stop(self):
        self.isExiting = True

    def scrapData(self):
        if self.isExiting: return
        self.scrapProductData.emit('<font color=green><b>Main URL: </b>%s</font>' % self.mainUrl)
        self.logger.debug('===== URL [' + self.mainUrl + '] =====')
        data = self.spider.fetchData(self.mainUrl)
        if data and len(str(data).strip()) > 0:
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            category1Chunk = self.regex.getAllSearchedData('(?i)<li id="li-id-\d+">(.*?)</ul> </li>', data)
            if category1Chunk and len(str(category1Chunk).strip()) > 0:
                i = 0
                for category1Data in category1Chunk:
                    category1 = self.regex.getSearchedData('(?i)<a href="[^"]*">([^<]*)</a>', category1Data)
                    category2Chunk = self.regex.getAllSearchedData('(?i)<li><a href="([^"]*)">([^<]*)</a>',
                                                                   category1Data)
                    if category2Chunk and len(str(category2Chunk).strip()) > 0:
                        for category2Data in category2Chunk:
                            try:
                                self.scrapCategory2Data(self.mainUrl + category2Data[0], category1, category2Data[1])
                            except Exception, x:
                                self.logger.error(x)
        self.scrapProductData.emit('<font color=red><b>Finish Scraping Product data from %s</b></font>' % self.mainUrl)

# 需要导入模块: from utils.Regex import Regex [as 别名]
# 或者: from utils.Regex.Regex import getAllSearchedData [as 别名]
class CsBrands(QThread):
    notifyBrand = pyqtSignal(object)

    def __init__(self):
        QThread.__init__(self)
        self.logger = LogManager(__name__)
        self.spider = Spider()
        self.regex = Regex()
        self.utils = Utils()
        dupCsvReader = Csv()
        self.dupCsvRows = dupCsvReader.readCsvRow("cs_Brands.csv")
        self.csvWriter = Csv("cs_Brands.csv")
        self.mainUrl = "http://www.cs-catering-equipment.co.uk/brands"
        self.isExiting = False
        headerData = [
            "URL",
            "Parent Category",
            "Brand Category",
            "Brand Description",
            "Image File",
            "Product Codes in this category",
        ]
        if headerData not in self.dupCsvRows:
            self.csvWriter.writeCsvRow(headerData)

    def run(self):
        self.scrapBrands()
        self.notifyBrand.emit("<font color=red><b>Finished Scraping All Brands.</b></font>")

    def scrapBrands(self):
        self.notifyBrand.emit("<font color=green><b>Main URL: %s<b></font>" % self.mainUrl)
        self.notifyBrand.emit("<b>Try To scrap All Brands.<b>")
        data = self.spider.fetchData(self.mainUrl)
        if data and len(data) > 0:
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            brandChunks = self.regex.getAllSearchedData('(?i)<div class="man-group man-group-[a-z]">(.*?)</div>', data)
            if brandChunks and len(brandChunks) > 0:
                for brandChunk in brandChunks:
                    brands = self.regex.getAllSearchedData('(?i)<a href="([^"]*)"[^>]*?>([^<]*)</a>', brandChunk)
                    self.notifyBrand.emit("<b>Total Brands Found: %s<b>" % str(len(brands)))
                    if brands and len(brands) > 0:
                        for brand in brands:
                            try:
                                self.scrapBrandInfo(brand[0], "Shop By Brand", brand[1])
                            except Exception, x:
                                self.logger.error(x)

# 需要导入模块: from utils.Regex import Regex [as 别名]
# 或者: from utils.Regex.Regex import getAllSearchedData [as 别名]
class CsTest(QThread):
    notifyProduct = pyqtSignal(object)

    def __init__(self):
        QThread.__init__(self)
        self.logger = LogManager(__name__)
        self.spider = Spider()
        self.regex = Regex()
        dupCsvReader = Csv()
        self.dupCsvRows0 = dupCsvReader.readCsvRow('cs_product.csv', 0)
        self.dupCsvRows = dupCsvReader.readCsvRow('cs_product.csv', 1)
        self.csvWriter = Csv('cs_product.csv')
        #        self.mainUrl = 'http://www.cs-catering-equipment.co.uk/'
        self.mainUrl = 'http://www.cs-catering-equipment.co.uk/brands'
        self.utils = Utils()
        if 'Product Code' not in self.dupCsvRows:
            self.csvWriter.writeCsvRow(
                ['URL', 'Product Code', 'Product Name', 'Manufacturer', 'List Price', 'Product Price', 'Discount',
                 'Product Short Description', 'Product Long Description', 'Product Technical Specifications', 'Warranty'
                    ,
                 'Delivery',
                 'Product Image',
                 'Category 1', 'Category 2', 'Category 3', 'Category 4', 'Brand Image'])
        self.totalProducts = len(self.dupCsvRows)

    def run(self):
        self.scrapBrands()
        self.notifyProduct.emit('<font color=red><b>Finished Scraping All Brands.</b></font>')

    def scrapBrands(self):
        self.notifyProduct.emit('<font color=green><b>Main URL: %s<b></font>' % self.mainUrl)
        self.notifyProduct.emit('<b>Try To scrap All Brands.<b>')
        data = self.spider.fetchData(self.mainUrl)
        if data and len(data) > 0:
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            brandChunks = self.regex.getAllSearchedData('(?i)<div class="man-group man-group-[a-z]">(.*?)</div>', data)
            if brandChunks and len(brandChunks) > 0:
                for brandChunk in brandChunks:
                    brands = self.regex.getAllSearchedData('(?i)<a href="([^"]*)"[^>]*?>([^<]*)</a>', brandChunk)
                    self.notifyProduct.emit('<b>Total Brands Found: %s<b>' % str(len(brands)))
                    if brands and len(brands) > 0:
                        for brand in brands:
                            try:
                                self.scrapBrandInfo(brand[0], 'Shop By Brand', brand[1])
                            except Exception, x:
                                self.logger.error(x)

# 需要导入模块: from utils.Regex import Regex [as 别名]
# 或者: from utils.Regex.Regex import getAllSearchedData [as 别名]
class MyLinkedInMembers(QThread):
    notifyLinkedIn = pyqtSignal(object)
    notifyMembers = pyqtSignal(object)
    cookieL = pyqtSignal(object)

    def __init__(self, spider, url, pageRange=None):
        QThread.__init__(self)
        #        self.spider = Spider()
        self.spider = spider
        self.regex = Regex()
        self.url = url
        self.startPage = None
        self.endPage = None
        if self.regex.isFoundPattern('(?i)(\d+)-(\d+)', str(pageRange).strip()):
            pageRangeFormat = self.regex.getSearchedDataGroups('(?i)(\d+)-(\d+)', str(pageRange).strip())
            self.startPage = int(pageRangeFormat.group(1))
            self.endPage = int(pageRangeFormat.group(2))
        elif self.regex.isFoundPattern('(?i)(\d+)', str(pageRange).strip()):
            pageRangeFormat = self.regex.getSearchedDataGroups('(?i)(\d+)', str(pageRange).strip())
            self.startPage = int(pageRangeFormat.group(1))
            self.endPage = self.startPage

    def run(self):
        self.getMembers(self.url)
        self.notifyLinkedIn.emit('<font color=red><b>Finish scraping members.<b></font>')

    def getMembers(self, url, pageNumber=0):
        print 'Members URL: ' + url
        self.notifyLinkedIn.emit('<font color=green><b>Start Scraping All Members.<b></font>')
        self.notifyLinkedIn.emit('<b>Wait For 15 seconds Break...<b>')
        time.sleep(15)
        self.notifyLinkedIn.emit('<b>15 seconds Break Finish.<b>')
        groupData = self.spider.fetchData(str(url).replace('&amp;', '&'))
        groupData = self.regex.reduceNewLine(groupData)
        groupData = self.regex.reduceBlankSpace(groupData)
        print groupData

        print 'page number: ' + str(pageNumber)
        if pageNumber > 0:
            harvestedMembers = []
            allMembers = self.regex.getAllSearchedData('(?i)<li class="member" id="member-[^"]*"[^>]*?>(.*?)</div>',
                groupData)
            for members in allMembers:
                memberId = self.regex.getSearchedData('(?i)data-li-memberId="([^"]*)"', members)
                memberName = self.regex.getSearchedData('(?i)data-li-fullName="([^"]*)"', members)
                memberTitle = self.regex.getSearchedData('(?i)<p class="headline">([^<]*?)</p>', members)
                memberTitle = self.regex.replaceData('(?i)&amp;', '&', memberTitle)
                harvestedMembers.append((memberId, memberName, memberTitle))
                self.notifyLinkedIn.emit('<b>Member ID: </b>%s <b>Member Name: </b>%s' % (memberId, memberName + ' (' + memberTitle + ')'))
            #            members = self.regex.getAllSearchedData(
            #                '(?i)class="send-message" data-li-memberId="([^"]*)" data-li-fullName="([^"]*)"', groupData)
            #            print members
            self.notifyMembers.emit(harvestedMembers)
            #            for member in members:
        #                print member
        #                self.notifyLinkedIn.emit('<b>Member Name: </b>%s <b>Member ID: </b>%s' % (member[1], member[0]))

        urlNext = self.regex.getSearchedData('(?i)<a href="([^"]*)"[^>]*?>\s*?<strong>\s*?next', groupData)
        if urlNext and len(urlNext) > 0:
        #            nextP = int(self.regex.getSearchedData('(?i).*?(\d+)$', urlNext.strip()))
            urlNext = self.regex.replaceData('(?i)&amp;', '&', urlNext)
            urlNext = self.regex.replaceData('(?i)split_page=\d+', 'split_page=', urlNext)
            pageNumber += 1
            if self.startPage <= pageNumber <= self.endPage:
                self.notifyLinkedIn.emit('<b>Wait for 15 second break...</b>')
                time.sleep(15)
                print 'sleep 15 s'
                self.notifyLinkedIn.emit('<b>15 second break finish!!!</b>')
                self.getMembers('http://www.linkedin.com' + urlNext + str(pageNumber), pageNumber)
            elif pageNumber < self.startPage:
                pageNumber = self.startPage
                self.notifyLinkedIn.emit('<b>Wait for 15 second break...</b>')
                time.sleep(15)
                print 'page number less 0 sleep'
                self.notifyLinkedIn.emit('<b>15 second break finish!!!</b>')
                self.getMembers('http://www.linkedin.com' + urlNext + str(pageNumber), pageNumber)

            if self.startPage is None and self.endPage is None:
                pageNumber += 1
                self.notifyLinkedIn.emit('<b>Wait for 15 second break...</b>')
                time.sleep(15)
                print 'page number less 0 sleep'
                self.notifyLinkedIn.emit('<b>15 second break finish!!!</b>')
                self.getMembers('http://www.linkedin.com' + urlNext + str(pageNumber), pageNumber)

# 需要导入模块: from utils.Regex import Regex [as 别名]
# 或者: from utils.Regex.Regex import getAllSearchedData [as 别名]
class NisbetProduct(QtCore.QThread):
    scrapProductData = QtCore.pyqtSignal(object)
    stopThread = QtCore.pyqtSignal(int)

    def __init__(self):
        QtCore.QThread.__init__(self)
        self.isExiting = False
        self.logger = LogManager(__name__)
        self.spider = Spider()
        self.regex = Regex()
        dupCsvReader = Csv()
        self.dupCsvRows = dupCsvReader.readCsvRow("nisbets.csv", 0)
        self.csvWriter = Csv("nisbets.csv")
        self.mainUrl = "http://www.nisbets.co.uk"
        csvHeaderList = [
            "URL",
            "Product Code",
            "Product Technical Specifications",
            "Product Name",
            "Brand",
            "Product Price",
            "Product Short Description",
            "Product Long Description",
            "Image File Name",
            "User Manual File Name",
            "Exploded View File Name",
            "Spares Code",
            "Accessories",
            "Product Status" "Category1",
            "Category2",
            "Category3",
            "Category4",
        ]
        if "URL" not in self.dupCsvRows:
            self.csvWriter.writeCsvRow(csvHeaderList)
            self.dupCsvRows.append(csvHeaderList[0])

        self.utils = Utils()

    def run(self):
        self.scrapData()

    def stop(self):
        self.isExiting = True

    def scrapData(self):
        if self.isExiting:
            return
        self.scrapProductData.emit("<font color=green><b>Main URL: </b>%s</font>" % self.mainUrl)
        self.logger.debug("===== URL [" + self.mainUrl + "] =====")
        data = self.spider.fetchData(self.mainUrl)
        if data:
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            category1Chunk = self.regex.getAllSearchedData('(?i)<li id="li-id-\d+">(.*?)</ul> </li>', data)
            if category1Chunk:
                for category1Data in category1Chunk:
                    category1 = self.regex.getSearchedData('(?i)<a href="[^"]*">([^<]*)</a>', category1Data)
                    category2Chunk = self.regex.getAllSearchedData(
                        '(?i)<li><a href="([^"]*)">([^<]*)</a>', category1Data
                    )
                    if category2Chunk:
                        for category2Data in category2Chunk:
                            self.scrapCategory2Data(self.mainUrl + category2Data[0], category1, category2Data[1])
        self.scrapProductData.emit("<font color=red><b>Finish Scraping Product data from %s</b></font>" % self.mainUrl)

    def scrapCategory2Data(self, url, category1, category2):
        if self.isExiting:
            return
        self.scrapProductData.emit("<b>Category 2 URL: </b>%s" % url)
        self.logger.debug("== Category 2 URL [" + url + "] ==")
        data = self.spider.fetchData(url)
        if data:
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            category3Chunks = self.regex.getSearchedData('(?i)<ul class="topCat clear-fix">(.*?)</ul>', data)
            if category3Chunks:
                category3Chunk = self.regex.getAllSearchedData('(?i)<a href="([^"]*)">([^<]*)<', category3Chunks)
                if category3Chunk:
                    for category3Data in category3Chunk:
                        self.scrapCategory3Data(self.mainUrl + category3Data[0], category1, category2, category3Data[1])

    def scrapCategory3Data(self, url, category1, category2, category3):
        if self.isExiting:
            return
        self.scrapProductData.emit("<b>Category 3 URL: </b>%s" % url)
        self.logger.debug("== Category 3 URL [" + url + "] ==")
        data = self.spider.fetchData(url)
        if data:
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            category4Chunks = self.regex.getSearchedData('(?i)<ul class="topCat clear-fix">(.*?)</ul>', data)
            if category4Chunks:
                category4Chunk = self.regex.getAllSearchedData('(?i)<a href="([^"]*)">([^<]*)<', category4Chunks)
                if category4Chunk:
                    for category4Data in category4Chunk:
                        category4Url = self.mainUrl + category4Data[0]
                        self.scrapCategory4Data(category4Url, category1, category2, category3, category4Data[1])

    def scrapCategory4Data(self, url, category1, category2, category3, category4):
#.........这里部分代码省略.........

# 需要导入模块: from utils.Regex import Regex [as 别名]
# 或者: from utils.Regex.Regex import getAllSearchedData [as 别名]
class CsCat(QThread):
    notifyCategory = pyqtSignal(object)

    def __init__(self):
        QThread.__init__(self)
        self.logger = LogManager(__name__)
        self.spider = Spider()
        self.regex = Regex()
        dupCsvReader = Csv()
        self.dupCsvRows = dupCsvReader.readCsvRow('cs_cat.csv')
        self.csvWriter = Csv('cs_cat.csv')
        dupFilterCsvReader = Csv()
        self.dupFilterCsvRows = dupFilterCsvReader.readCsvRow('filter_cat' + '.csv')
        self.csvW = Csv('filter_cat' + '.csv')
        self.mainUrl = 'http://www.cs-catering-equipment.co.uk/'
        self.totalCategory = 0

    def run(self):
        self.scrapCategories()
        self.notifyCategory.emit('<font color=red><b>Finished Scraping All Categories.</b></font>')

    def scrapCategories(self):
#        self.scrapFinalCategory('http://www.cs-catering-equipment.co.uk/kitchen-equipment/food-prep-machines/chocolate-fountains', '', '')
#        return
        self.notifyCategory.emit('<b>Start scraping Category.</b>')
        self.notifyCategory.emit('<font color=green><b>Main URL: %s</b></font>' % self.mainUrl)
        data = self.spider.fetchData(self.mainUrl)
        if data and len(data) > 0:
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            #        <a href="http://www.cs-catering-equipment.co.uk/kitchen-equipment" class="level-top" title="Kitchen Equipment"
            categories = self.regex.getAllSearchedData('(?i)<a href="([^"]*)" class="level-top" title="([^"]*)"', data)
            if categories and len(categories) > 0:
                self.totalCategory += len(categories)
                self.notifyCategory.emit(
                    '<font color=green><b>Total Category Found [%s]</b></font>' % unicode(self.totalCategory))
                for category in categories:
                    homeCategoryName = 'Home'
                    categoryName = unicode(category[1]).strip()
                    self.scrapCategory(str(category[0]).strip(), homeCategoryName, categoryName)

    def scrapCategory(self, url, rootCategoryName, categoryName):
        self.notifyCategory.emit('<font color=green><b>Start scraping URL: %s</b></font>' % url)
        data = self.spider.fetchData(url)
        if data and len(data) > 0:
            print 'category 1'
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            self.filterCategory(data, categoryName)
            categoryDesc = self.regex.getSearchedData('(?i)<div class="category-description std">([^<]*)</div>', data)
            if categoryDesc and len(categoryDesc) > 0:
                categoryDesc = unicode(categoryDesc).strip()
            csvData = [rootCategoryName, categoryName, categoryDesc]
            if csvData not in self.dupCsvRows:
                self.notifyCategory.emit('<b>Scraped Data: %s</b>' % unicode(csvData))
                self.csvWriter.writeCsvRow(csvData)
                self.dupCsvRows.append(csvData)
            else:
                self.notifyCategory.emit('<font color=green><b>Already Exits Category [%s] in csv file. Skip it.</b></font>' % categoryName)

            subCategories = self.regex.getAllSearchedData(
                '(?i)<li> <a href="([^"]*)" title="([^"]*)"[^>]*?>[^<]*?</a> </li>', data)
            if subCategories and len(subCategories) > 0:
                self.totalCategory += len(subCategories)
                self.notifyCategory.emit(
                    '<font color=green><b>Total Category Found [%s]</b></font>' % unicode(self.totalCategory))
                for subCategory in subCategories:
                    print subCategory
                    self.scrapSubCategory(subCategory[0], categoryName, subCategory[1])

    def scrapSubCategory(self, url, rootCategoryName, categoryName):
        self.notifyCategory.emit('<font color=green><b>Start scraping URL: %s</b></font>' % url)
        data = self.spider.fetchData(url)
        if data and len(data) > 0:
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            self.filterCategory(data, categoryName)
            categoryDesc = self.regex.getSearchedData('(?i)<div class="category-description std">([^<]*)</div>', data)
            categoryDesc = unicode(categoryDesc).strip()
            csvData = [rootCategoryName, categoryName, categoryDesc]
            if csvData not in self.dupCsvRows:
                self.csvWriter.writeCsvRow(csvData)
                self.dupCsvRows.append(csvData)
                self.notifyCategory.emit('<b>Scraped Data: %s</b>' % unicode(csvData))
            else:
                self.notifyCategory.emit('<font color=green><b>Already Exits Category [%s] in csv file. Skip it.</b></font>' % categoryName)

            subCategories = self.regex.getAllSearchedData(
                '(?i)<li> <a href="([^"]*)" title="([^"]*)"[^>]*?>[^<]*?</a> </li>', data)
            if subCategories and len(subCategories) > 0:
                self.totalCategory += len(subCategories)
                self.notifyCategory.emit(
                    '<font color=green><b>Total Category Found [%s]</b></font>' % unicode(self.totalCategory))
                for subCategory in subCategories:
                    self.scrapFinalCategory(subCategory[0], categoryName, subCategory[1])

    def scrapFinalCategory(self, url, rootCategoryName, categoryName):
        self.notifyCategory.emit('<font color=green><b>Start scraping URL: %s</b></font>' % url)
        data = self.spider.fetchData(url)
        if data and len(data) > 0:
#.........这里部分代码省略.........

# 需要导入模块: from utils.Regex import Regex [as 别名]
# 或者: from utils.Regex.Regex import getAllSearchedData [as 别名]
class NisbetCat(QtCore.QThread):
    scrapCategoryData = QtCore.pyqtSignal(object)
    stopThread = QtCore.pyqtSignal(int)

    def __init__(self):
        QtCore.QThread.__init__(self)
        self.isExiting = False
        self.logger = LogManager(__name__)
        self.spider = Spider()
        self.regex = Regex()
        dupCsvReader = Csv()
        self.dupCsvRows = dupCsvReader.readCsvRow('nisbetCat.csv')
        self.csvWriter = Csv('nisbetCat.csv')
        self.mainUrl = 'http://www.nisbets.co.uk'
        csvHeaderList = ['Parent Category', 'Category Name', 'Category Description']
        if csvHeaderList not in self.dupCsvRows:
            self.csvWriter.writeCsvRow(csvHeaderList)
            self.dupCsvRows.append(csvHeaderList)

    def run(self):
        self.scrapData()

    def stop(self):
        self.isExiting = True

    def scrapData(self):
        if self.isExiting: return
        self.scrapCategoryData.emit('<font color=green><b>Main URL: </b>%s</font>' % self.mainUrl)
        self.logger.debug('===== URL [' + self.mainUrl + '] =====')
        data = self.spider.fetchData(self.mainUrl)
        if data:
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            links = self.regex.getAllSearchedData('(?i)<li id="li-id-\d+"> <a href="([^"]*)">([^<]*)</a>', data)
            if links:
                for link in links:
                    self.scrapCategoryData.emit('<b>Link URL: </b>%s' % (self.mainUrl + link[0]))
                    self.logger.debug('===Link URL [' + self.mainUrl + link[0] + '] ===')
                    csvData = ['Home']
                    category = link[1]
                    csvData.append(category)

                    linkInfo = self.spider.fetchData(self.mainUrl + link[0])
                    if linkInfo:
                        linkInfo = self.regex.reduceNewLine(linkInfo)
                        linkInfo = self.regex.reduceBlankSpace(linkInfo)
                        csvData.append(
                            self.regex.getSearchedData('(?i)<p class="br5px padding10 mb0 mt10">([^<]*)</p>', linkInfo))
                        self.logger.debug('Category ' + str(csvData))
                        if csvData not in self.dupCsvRows:
                            self.csvWriter.writeCsvRow(csvData)
                            self.dupCsvRows.append(csvData)
                            self.scrapCategoryData.emit('<b>Scraped Data: </b>%s<br />' % str(csvData))
                        else:
                            self.scrapCategoryData.emit(
                                '<font color=green><b>Already Scrapped Skip This Category</b></font>')

                        ## After write first cat data
                        subUrlsChunk = self.regex.getSearchedData('(?i)<ul class="topCat clear-fix">(.*?)</ul>',
                            linkInfo)
                        if subUrlsChunk:
                            subUrls = self.regex.getAllSearchedData('(?i)<a href="([^"]*)">([^<]*)<span', subUrlsChunk)
                            if subUrls:
                                for subUrl in subUrls:
                                    self.scrapSubCat(self.mainUrl + subUrl[0], category, subUrl[1])
        self.scrapCategoryData.emit(
            '<font color=red><b>Finish Scraping Category data from %s</b></font>' % self.mainUrl)

    def scrapSubCat(self, url, parentCat, category):
        if self.isExiting: return
        self.scrapCategoryData.emit('<b>Link URL: </b>%s' % url)
        self.logger.debug('== Sub URL [' + url + '] ==')
        data = self.spider.fetchData(url)
        if data:
            csvData = [parentCat, category]
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            csvData.append(self.regex.getSearchedData('(?i)<p class="br5px padding10 mb0 mt10">([^<]*)</p>', data))
            self.logger.debug('Sub Category ' + str(csvData))
            if csvData not in self.dupCsvRows:
                self.csvWriter.writeCsvRow(csvData)
                self.dupCsvRows.append(csvData)
                self.scrapCategoryData.emit('<b>Scraped Data: </b>%s<br />' % str(csvData))
            else:
                self.scrapCategoryData.emit('<font color=green><b>Already Scrapped Skip This Category</b></font>')

            ## After write first cat data
            subUrlsChunk = self.regex.getSearchedData('(?i)<ul class="topCat clear-fix">(.*?)</ul>', data)
            if subUrlsChunk:
                subUrls = self.regex.getAllSearchedData('(?i)<a href="([^"]*)">([^<]*)<span', subUrlsChunk)
                if subUrls:
                    for subUrl in subUrls:
                        self.scrapSubSubCat(self.mainUrl + subUrl[0], category, subUrl[1])

    def scrapSubSubCat(self, url, parentCat, category):
        if self.isExiting: return
        self.scrapCategoryData.emit('<b>Link URL: </b>%s' % url)
        self.logger.debug('== SUb SUb URL [' + url + '] ==')
        data = self.spider.fetchData(url)
        if data:
#.........这里部分代码省略.........

# 需要导入模块: from utils.Regex import Regex [as 别名]
# 或者: from utils.Regex.Regex import getAllSearchedData [as 别名]
class MyLinkedIn(QThread):
    notifyLinkedIn = pyqtSignal(object)
    notifyMember = pyqtSignal(object)
    cookieL = pyqtSignal(object)

    def __init__(self, username, password):
        QThread.__init__(self)
        self.spider = Spider()
        self.regex = Regex()
        self.username = username
        self.password = password

    def run(self):
        if self.login():
            self.getAllGroups()

    def login(self):
        print "login start"
        self.notifyLinkedIn.emit("<b>Trying to login. Please wait...</b>")
        loginPageData = self.spider.fetchData("https://www.linkedin.com/uas/login?goback=&trk=hb_signin")
        loginPageData = self.regex.reduceNewLine(loginPageData)
        loginPageData = self.regex.reduceBlankSpace(loginPageData)

        ## <input type="hidden" name="session_redirect" value="" id="session_redirect-login"><input type="hidden" name="csrfToken" value="ajax:9073845200579364133" id="csrfToken-login"><input type="hidden" name="sourceAlias" value="0_7r5yezRXCiA_H0CRD8sf6DhOjTKUNps5xGTqeX8EEoi" id="sourceAlias-login">
        self.sessionRedirect = self.regex.getSearchedData(
            '(?i)<input type="hidden" name="session_redirect" value="([^"]*)"', loginPageData
        )
        self.token = self.regex.getSearchedData(
            '(?i)<input type="hidden" name="csrfToken" value="([^"]*)"', loginPageData
        )
        self.alias = self.regex.getSearchedData(
            '(?i)<input type="hidden" name="sourceAlias" value="([^"]*)"', loginPageData
        )

        loginParam = {
            "csrfToken": self.token,
            "isJsEnabled": "true",
            "session_key": self.username,
            "session_password": self.password,
            #                      'session_key': '[email protected]',
            #                      'session_password': 'ubuntu36',
            "session_redirect": self.sessionRedirect,
            "signin": "Sign In",
            "sourceAlias": self.alias,
            "source_app": "",
        }
        print loginParam
        print "start login"
        time.sleep(5)
        loginData = self.spider.login("https://www.linkedin.com/uas/login-submit", loginParam)
        loginData = self.regex.reduceNewLine(loginData)
        loginData = self.regex.reduceBlankSpace(loginData)
        #        print loginData
        isLoggedIn = self.regex.isFoundPattern('(?i)<li class="signout">', loginData)

        if isLoggedIn:
            self.notifyLinkedIn.emit("<font color=green><b>Successfully Logged In.</b></font>")
            print "login success"
            self.cookieL.emit(self.spider)
            return True
        else:
            self.notifyLinkedIn.emit(
                "<font color=red><b>Something wrong with logging in. Please try again or check manually with this username/password</b></font>"
            )
            return False

    def getAllGroups(self):
        print "start groups"
        self.notifyLinkedIn.emit("<font color=green><b>Start Scraping All Groups.</b></font>")
        self.notifyLinkedIn.emit("<b>Wait for 15 second break...</b>")
        time.sleep(15)
        self.notifyLinkedIn.emit("<b>15 second break finish!!!</b>")
        self.notifyLinkedIn.emit("<font color=green><b>Fetching data for scraping your groups.</b></font>")
        groupsUrl = "http://www.linkedin.com/myGroups?trk=hb_side_grps_top"
        groupsData = self.spider.fetchData(groupsUrl)
        self.notifyLinkedIn.emit("<font color=green><b>Data fetching complete for scraping your groups.</b></font>")
        if groupsData is not None and len(groupsData) > 0:
            print "starting groups"
            groupsData = self.regex.reduceNewLine(groupsData)
            groupsData = self.regex.reduceBlankSpace(groupsData)
            print groupsData
            ## <a href="/groups?gid=72881&amp;trk=myg_ugrp_ovr" class="private" title="This group is members only">MySQL Professionals</a>
            groupInfo = self.regex.getAllSearchedData('(?i)<a href="(/groups\?gid=[^"]*)"[^>]*>([^<]*)</a>', groupsData)
            if groupInfo is not None and len(groupInfo) > 0:
                members = []
                for group in groupInfo:
                    groupUrl = "http://www.linkedin.com" + str(group[0])
                    groupName = str(group[1])
                    self.notifyLinkedIn.emit("<b>Group Name: </b>%s <b>URL: </b>%s" % (groupName, groupUrl))
                    #                    http://www.linkedin.com/groups?members=&gid=65688&trk=anet_ug_memb
                    gid = self.regex.getSearchedData("(?i)gid=(\d+)", group[0])
                    print gid
                    groupUrl = "http://www.linkedin.com/groups?members=&gid=" + gid + "&trk=anet_ug_memb"
                    members.append((groupName, groupUrl))
                self.notifyMember.emit(members)
            self.notifyLinkedIn.emit("<font color=red><b>Finish Scraping All Groups.</b></font>")

# 需要导入模块: from utils.Regex import Regex [as 别名]
# 或者: from utils.Regex.Regex import getAllSearchedData [as 别名]
class BetrosProduct(QThread):
    notifyProduct = pyqtSignal(object)

    def __init__(self):
        QThread.__init__(self)
        self.logger = LogManager(__name__)
        self.spider = Spider()
        self.regex = Regex()
        self.mainUrl = 'http://www.bertos.com'
        self.utils = Utils()
        self.csvHeader = ['Home Category', 'Sub Category', 'Category Description', 'Category Image', 'Code',
                          'Product Code',
                          'Product Name',
                          'Product Description', 'Product Image File', 'Technical Sheet File', 'Exploded View File']
        self.totalProducts = 0

    def run(self):
        self.scrapBertos()
        self.notifyProduct.emit('<font color=red><b>Finished Scraping All products.</b></font>')

    def scrapBertos(self, retry=0):
    #        self.downloadFile('http://s900.bertos.it/download.php?file=editorcms/documentazione/schede/scheda_13722600.pdf', 'a.pdf')
    #        self.scrapSubCategory('http://s900.bertos.it/en/', '', None, None)
    #        self.scrapProducts('http://s900.bertos.it/en/pasta_cookers/', '', '', None, None)
    #        return
        self.notifyProduct.emit('<font color=green><b>Try to get all language links.</b></font>')
        self.logger.debug(self.mainUrl)
        data = self.spider.fetchData(self.mainUrl)
        if data and len(data) > 0:
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)

            languages = self.regex.getAllSearchedData(
                '(?i)<div class="[^"]*"><a href="([^"]*)"\s*?class="boxalingua">([^<]*)</a>', data)
            if languages and len(languages) > 0:
                self.logger.debug('Total languages: %s' % str(len(languages)))
                self.notifyProduct.emit('<b>Total languages found[%s]</b>' % str(len(languages)))
                for language in languages:
                    self.totalProducts = 0
                    url = language[0]
                    #                    if str(language[1]).lower() != 'en':
                    #                        continue
                    urlChunk = self.spider.fetchData(url)
                    if urlChunk and len(urlChunk) > 0:
                        urlChunk = self.regex.reduceNewLine(urlChunk)
                        urlChunk = self.regex.reduceBlankSpace(urlChunk)
                        url = self.regex.getSearchedData('(?i)<a href="([^"]*)" onmouseover="vedi_po_cat\(2\)\s*?"',
                            urlChunk)
                        csvFile = str(language[1].strip()).lower() + '_' + 'bertos.csv'
                        dupCsvReader = Csv()
                        dupCsvRows = dupCsvReader.readCsvRow(csvFile)
                        csvWriter = Csv(csvFile)
                        if self.csvHeader not in dupCsvRows:
                            dupCsvRows.append(self.csvHeader)
                            csvWriter.writeCsvRow(self.csvHeader)
                        self.notifyProduct.emit(
                            '<font color=green><b>Try to get data for language [%s].</b></font>' % language[1])
                        self.scrapCategory(url, dupCsvRows, csvWriter)
                        self.notifyProduct.emit(
                            '<font color=red><b>=====  Finish scraping data for [%s] =====</b></font><br /><br />' %
                            language[1])
        else:
            if retry < 5:
                return self.scrapBertos(retry + 1)


    def scrapCategory(self, mainUrl, dupCsvRows, csvWriter):
        url = mainUrl
        self.logger.debug('Main URL: ' + url)
        self.notifyProduct.emit('<font color=green><b>Main URL: %s</b></font>' % url)
        data = self.spider.fetchData(url)
        if data and len(data) > 0:
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            data = self.regex.reduceNbsp(data)
            self.notifyProduct.emit('<b>Try to scrap all categories.</b>')
            categoryChunk = self.regex.getSearchedData('(?i)<div id="contenuto1">(.*?)</div>\s*?</div>', data)
            if categoryChunk and len(categoryChunk) > 0:
                categories = self.regex.getAllSearchedData('(?i)<a href="([^"]*)"[^>]*?>([^<]*)</a>', categoryChunk)
                if categories and len(categories) > 0:
                    self.notifyProduct.emit('<b>Total Categories Found: %s</b>' % str(len(categories)))
                    for category in categories:
                        categoryName = category[1].strip()
                        self.scrapSubCategory(str(category[0]).strip(), categoryName, dupCsvRows, csvWriter)

    def scrapSubCategory(self, url, categoryName, dupCsvRows, csvWriter):
        self.logger.debug('Category URL: ' + url)
        self.notifyProduct.emit('<b>Try to scrap subcategories for: %s</b>' % categoryName)
        data = self.spider.fetchData(url)
        if data and len(data) > 0:
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            subCategories = self.regex.getAllSearchedData('(?i)<li\s*?><a href="([^"]*)" title="([^"]*)"', data)
            if subCategories and len(subCategories) > 0:
                self.notifyProduct.emit(
                    '<font color=green><b>Total subcategories found %s.</b></font>' % str(len(subCategories)))
                for subCategory in subCategories:
                    subCategoryName = subCategory[1].strip()
                    self.scrapProducts(subCategory[0].strip(), categoryName, subCategoryName, dupCsvRows, csvWriter)

#.........这里部分代码省略.........

# 需要导入模块: from utils.Regex import Regex [as 别名]
# 或者: from utils.Regex.Regex import getAllSearchedData [as 别名]
class CsProduct(QThread):
    notifyProduct = pyqtSignal(object)

    def __init__(self):
        QThread.__init__(self)
        self.logger = LogManager(__name__)
        self.spider = Spider()
        self.regex = Regex()
        dupCsvReader = Csv()
        self.dupCsvRows = dupCsvReader.readCsvRow('cs_product.csv', 0)
        self.csvWriter = Csv('cs_product.csv')
        self.mainUrl = 'http://www.cs-catering-equipment.co.uk/'
        self.utils = Utils()
        self.csvWriter.writeCsvRow(
            ['URL', 'Product Code', 'Product Name', 'Manufacturer', 'List Price', 'Product Price', 'Discount',
             'Product Short Description', 'Product Long Description', 'Product Technical Specifications', 'Warranty',
             'Delivery',
             'Product Image',
             'Category 1', 'Category 2', 'Category 3', 'Category 4', 'Brand Image'])
        self.totalProducts = 0

    def run(self):
        self.scrapProduct()
        self.notifyProduct.emit('<font color=red><b>Finished Scraping All products.</b></font>')

    def scrapProduct(self):
        self.logger.debug('Main URL: ' + self.mainUrl)
        self.notifyProduct.emit('<font color=green><b>Main URL: %s</b></font>' % self.mainUrl)
        data = self.spider.fetchData(self.mainUrl)
        data = self.regex.reduceNewLine(data)
        data = self.regex.reduceBlankSpace(data)
        self.notifyProduct.emit('<b>Try to scrap all categories.</b>')
        categories = self.regex.getAllSearchedData('(?i)<a href="([^"]*)" class="level-top" title="([^"]*)"', data)
        if categories and len(categories) > 0:
            self.notifyProduct.emit('<b>Total Categories Found: %s</b>' % str(len(categories)))
            for category in categories:
                category1Name = unicode(category[1]).strip()
                self.scrapCategory1Data(str(category[0]).strip(), category1Name)

    def scrapCategory1Data(self, url, category1Name):
        self.logger.debug('Category 1 URL: ' + url)
        self.notifyProduct.emit('<b>Try to scrap all categories under Category[%s]</b>' % category1Name)
        self.notifyProduct.emit('<font color=green><b>Category URL: %s</b></font>' % url)
        data = self.spider.fetchData(url)
        data = self.regex.reduceNewLine(data)
        data = self.regex.reduceBlankSpace(data)
        categories = self.regex.getAllSearchedData(
            '(?i)<li> <a href="([^"]*)" title="([^"]*)"[^>]*?>[^<]*?</a> </li>', data)
        if categories and len(categories) > 0:
            self.notifyProduct.emit('<b>Total Categories Found: %s</b>' % str(len(categories)))
            for category in categories:
                self.scrapCategory2Data(category[0], category1Name, category[1])

    def scrapCategory2Data(self, url, category1Name, category2Name):
        self.logger.debug('Category 2 URL: ' + url)
        self.notifyProduct.emit('<b>Try to scrap all categories under Category[%s]</b>' % category2Name)
        self.notifyProduct.emit('<font color=green><b>Category URL: %s</b></font>' % url)
        data = self.spider.fetchData(url)
        data = self.regex.reduceNewLine(data)
        data = self.regex.reduceBlankSpace(data)
        categories = self.regex.getAllSearchedData(
            '(?i)<li> <a href="([^"]*)" title="([^"]*)"[^>]*?>[^<]*?</a> </li>', data)
        if categories and len(categories) > 0:
            for category in categories:
                print 'category2: ' + category[0]
                self.scrapCategory3Data(category[0], category1Name, category2Name, category[1])

    def scrapCategory3Data(self, url, category1Name, category2Name, category3Name):
        self.logger.debug('Category 3 URL: ' + url)
        self.notifyProduct.emit('<b>Try to scrap all categories under Category[%s]</b>' % category3Name)
        self.notifyProduct.emit('<font color=green><b>Category URL: %s</b></font>' % url)
        data = self.spider.fetchData(url)
        if data and len(data) > 0:
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            categories = self.regex.getAllSearchedData(
                '(?i)<li> <a href="([^"]*)" title="([^"]*)"[^>]*?>[^<]*?</a> </li>', data)
            if categories and len(categories) > 0:
                for category in categories:
                    print [category1Name, category2Name, category3Name, category[1]]
                    self.scrapProductsDetails(category[0], category1Name, category2Name, category3Name, category[1])

    def scrapProductsDetails(self, url, category1Name, category2Name, category3Name, category4Name):
        self.logger.debug('Product Details URL: ' + url)
        self.notifyProduct.emit('<b>Try to scrap all products under Category[%s]</b>' % category4Name)
        self.notifyProduct.emit('<font color=green><b>Category URL: %s</b></font>' % url)
        data = self.spider.fetchData(url + '?limit=10000&mode=list')
        if data and len(data) > 0:
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            products = self.regex.getAllSearchedData('(?i)<div class="listing-item[^"]*?">(.*?)</div>', data)
            if products and len(products) > 0:
                self.totalProducts += len(products)
                self.notifyProduct.emit('<font color=green><b>Total Products Found [%s]</b></font>' % unicode(self.totalProducts))
                for product in products:
                    productDetailUrl = self.regex.getSearchedData('(?i)<a href="([^"]*)"', product)
                    if productDetailUrl not in self.dupCsvRows:
                        self.scrapProductDetails(productDetailUrl, category1Name, category2Name, category3Name,
                            category4Name)
                    else:
#.........这里部分代码省略.........

# 需要导入模块: from utils.Regex import Regex [as 别名]
# 或者: from utils.Regex.Regex import getAllSearchedData [as 别名]
class CsProduct(QThread):
    notifyProduct = pyqtSignal(object)

    def __init__(self):
        QThread.__init__(self)
        self.logger = LogManager(__name__)
        self.spider = Spider()
        self.regex = Regex()
        dupCsvReader = Csv()
        self.dupCsvRows0 = dupCsvReader.readCsvRow('cs_product.csv', 0)
        self.dupCsvRows = dupCsvReader.readCsvRow('cs_product.csv', 1)
        self.csvWriter = Csv('cs_product.csv')
        self.mainUrl = 'http://www.cs-catering-equipment.co.uk/'
        self.utils = Utils()
        if 'Product Code' not in self.dupCsvRows:
            self.csvWriter.writeCsvRow(
                ['URL', 'Product Code', 'Product Name', 'Manufacturer', 'List Price', 'Product Price', 'Discount',
                 'Product Short Description', 'Product Long Description', 'Product Technical Specifications', 'Warranty'
                    ,
                 'Delivery',
                 'Product Image',
                 'Category 1', 'Category 2', 'Category 3', 'Category 4', 'Brand Image'])
        self.totalProducts = len(self.dupCsvRows)

    def run(self):
        self.scrapProduct()
        self.notifyProduct.emit('<font color=red><b>Finished Scraping All products.</b></font>')

    def scrapProduct(self):
    #        self.logger.debug('Main URL: ' + self.mainUrl)
        self.notifyProduct.emit('<font color=green><b>Main URL: %s</b></font>' % self.mainUrl)
        data = self.spider.fetchData(self.mainUrl)
        data = self.regex.reduceNewLine(data)
        data = self.regex.reduceBlankSpace(data)
        self.notifyProduct.emit('<b>Try to scrap all categories.</b>')
        categories = self.regex.getAllSearchedData('(?i)<a href="([^"]*)" class="level-top" title="([^"]*)"', data)
        if categories and len(categories) > 0:
            self.notifyProduct.emit('<b>Total Categories Found: %s</b>' % str(len(categories)))
            for category in categories:
                category1Name = unicode(category[1]).strip()
                self.scrapCategory1Data(str(category[0]).strip(), category1Name)

    def scrapCategory1Data(self, url, category1Name):
    #        self.logger.debug('Category 1 URL: ' + url)
        self.notifyProduct.emit('<b>Try to scrap all categories under Category[%s]</b>' % category1Name)
        self.notifyProduct.emit('<font color=green><b>Category URL: %s</b></font>' % url)
        data = self.spider.fetchData(url)
        data = self.regex.reduceNewLine(data)
        data = self.regex.reduceBlankSpace(data)
        categories = self.regex.getAllSearchedData(
            '(?i)<li> <a href="([^"]*)" title="([^"]*)"[^>]*?>[^<]*?</a> </li>', data)
        if categories and len(categories) > 0:
            self.notifyProduct.emit('<b>Total Categories Found: %s</b>' % str(len(categories)))
            for category in categories:
                self.scrapCategory2Data(category[0], category1Name, category[1])

    def scrapCategory2Data(self, url, category1Name, category2Name):
    #        self.logger.debug('Category 2 URL: ' + url)
        self.notifyProduct.emit('<b>Try to scrap all categories under Category[%s]</b>' % category2Name)
        self.notifyProduct.emit('<font color=green><b>Category URL: %s</b></font>' % url)
        data = self.spider.fetchData(url)
        data = self.regex.reduceNewLine(data)
        data = self.regex.reduceBlankSpace(data)
        categories = self.regex.getAllSearchedData(
            '(?i)<li> <a href="([^"]*)" title="([^"]*)"[^>]*?>[^<]*?</a> </li>', data)
        if categories and len(categories) > 0:
            for category in categories:
                print 'category2: ' + category[0]
                self.scrapCategory3Data(category[0], category1Name, category2Name, category[1])

    def scrapCategory3Data(self, url, category1Name, category2Name, category3Name):
    #        self.logger.debug('Category 3 URL: ' + url)
        self.notifyProduct.emit('<b>Try to scrap all categories under Category[%s]</b>' % category3Name)
        self.notifyProduct.emit('<font color=green><b>Category URL: %s</b></font>' % url)
        data = self.spider.fetchData(url)
        if data and len(data) > 0:
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            categories = self.regex.getAllSearchedData(
                '(?i)<li> <a href="([^"]*)" title="([^"]*)"[^>]*?>[^<]*?</a> </li>', data)
            if categories and len(categories) > 0:
                for category in categories:
                    print [category1Name, category2Name, category3Name, category[1]]
                    self.scrapProductsDetails(category[0], category1Name, category2Name, category3Name, category[1])

    def scrapProductsDetails(self, url, category1Name, category2Name, category3Name, category4Name):
        self.logger.debug('Product Details URL: ' + url)
        self.notifyProduct.emit('<b>Try to scrap all products under Category[%s]</b>' % category4Name)
        self.notifyProduct.emit('<font color=green><b>Category URL: %s</b></font>' % url)
        maxLimit = 25
        maxLimitChunk = self.spider.fetchData(url + '?mode=list')
        if maxLimitChunk and len(maxLimitChunk):
            maxLimitChunk = self.regex.reduceNewLine(maxLimitChunk)
            maxLimitChunk = self.regex.reduceBlankSpace(maxLimitChunk)
            maxLimits = self.regex.getAllSearchedData('<option value="[^"]*limit=(\d+)[^"]*"', maxLimitChunk)
            #            print maxLimits
            if maxLimits and len(maxLimits) > 0:
                maxLimit = max(map(int, maxLimits))
                #                print maxLimit

#.........这里部分代码省略.........

# 需要导入模块: from utils.Regex import Regex [as 别名]
# 或者: from utils.Regex.Regex import getAllSearchedData [as 别名]
class Nisbets:
    def __init__(self):
        self.logger = LogManager(__name__)
        self.spider = Spider()
        self.regex = Regex()
        self.csvWriter = Csv('nisbets.csv')
        self.mainUrl = 'http://www.nisbets.co.uk'
        csvHeaderList = ['Category', 'Product Image Url', 'Product Code', 'Product Name', 'Price']
        self.csvWriter.writeCsvRow(csvHeaderList)

    def scrapData(self):
        self.logger.debug('===== URL [' + self.mainUrl + '] =====')
        data = self.spider.fetchData(self.mainUrl)
        if data:
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            data = self.regex.getSearchedData('(?i)<div class="cms-left-nav-category">(.*?)</ul>', data)
            if data:
                links = self.regex.getAllSearchedData('(?i)<a href="([^"]*)"', data)
                if links:
                    for link in links:
                        self.scrapLinkData(self.mainUrl + link)

    def scrapLinkData(self, link):
        self.logger.debug('== Link URL [' + link + '] ==')
        data = self.spider.fetchData(link)
        if data:
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            data = self.regex.getSearchedData('(?i)<h3>Brand</h3> <ul class="subCat02 clear-fix">(.*?)</ul>', data)
            if data:
                links = self.regex.getAllSearchedData('(?i)<a href="([^"]*)"', data)
                if links:
                    for link in links:
                        self.scrapInfo(self.mainUrl + link)

    def scrapInfo(self, link):
        self.logger.debug('= Info URL [' + link + '] =')
        data = self.spider.fetchData(link)
        if data:
            data = self.regex.reduceNewLine(data)
            data = self.regex.reduceBlankSpace(data)
            category = self.regex.getSearchedData('(?i)<li><h3>Category</h3></li> <li class="remCont"> <span class="block">([^<]*)</span>', data)
            allInfo = self.regex.getAllSearchedData('(?i)<div class="product-list-row clear-after">(.*?)</fieldset>', data)
            if allInfo:
                for info in allInfo:
                    csvData = []
                    csvData.append(category)
                    grpData = self.regex.getSearchedDataGroups('(?i)<img class="primaryImage" src="([^"]*)" alt="([^"]*)" />', info)
                    if grpData.group(1):
                        imageUrl = grpData.group(1)
                        imageUrl = self.regex.replaceData('(?i)medium', 'xlarge', imageUrl)
                        csvData.append(self.mainUrl + imageUrl)
                    else:
                        csvData.append('')
                    csvData.append(grpData.group(2))
                    name = self.regex.getSearchedData('(?i)<h3 class="product-name"> <a href="[^"]*">([^<]*)</a>', info)
                    csvData.append(name)
                    price = self.regex.getSearchedData(u'(?i)<div class="reduced-price"> <span class="bold">([^<]*)</span>', info)
                    csvData.append(price.strip()[1:])
                    self.logger.debug('Scraped Data ' + str(csvData))
                    self.csvWriter.writeCsvRow(csvData)