Python Regex.Regex类代码示例

class TopsyScrapper:
    isFinished = False

    def __init__(self, filename):
        self.logger = LogManager(__name__)
        self.spider = Spider()
        self.regex = Regex()
        self.utils = Utils()
        self.filename = filename
        self.url = 'http://topsy.com/s?'
        self.csvWriter = Csv('topsy.csv')
        csvDataHeader = ['Keyword', 'Tweets in last 30 days', 'Topsy Sentiment Score', ' Date of scrape']
        self.csvWriter.writeCsvRow(csvDataHeader)

    def run(self):
        self.scrapData()
        self.csvWriter.closeWriter()

    def scrapData(self):
        try:
            file = open(self.filename, 'rb')
            for line in file.readlines():
                if self.isFinished: return
                line = self.regex.replaceData('\r+', '', line)
                line = self.regex.reduceNewLine(line)
                line = self.regex.reduceBlankSpace(line)
                line = line.strip()
                if len(line) > 0:
                    params = urllib.urlencode({'q': line, 'window': 'm', 'type': 'tweet'})
                    url = self.url + params
                    self.scrapBrowserData(url, line)
        except Exception, x:
            print x

class GoogleFinanceScrapper:
    isFinished = False

    def __init__(self, filename):
        self.logger = LogManager(__name__)
        self.spider = Spider()
        self.regex = Regex()
        self.utils = Utils()
        self.filename = filename
        self.url = 'https://www.google.com/finance?'
        self.main_url = 'https://www.google.com'
        self.csvWriter = Csv('google_finance.csv')
        csvDataHeader = ['Ticker Symbol', 'Quarter End', 'Revenue', 'Total Revenue', 'Date of Scrape']
        self.csvWriter.writeCsvRow(csvDataHeader)

    def run(self):
        self.scrapData()
        self.csvWriter.closeWriter()

    def scrapData(self):
        try:
            file = open(self.filename, 'rb')
            for line in file.readlines():
                if self.isFinished: return
                line = self.regex.replaceData('\r+', '', line)
                line = self.regex.reduceNewLine(line)
                line = self.regex.reduceBlankSpace(line)
                line = line.strip()
                params = urllib.urlencode({'q': line})
                url = self.url + params
                self.scrapBykeyword(url, line)
        except Exception, x:
            print x
            self.logger.error('Error: ' + x.message)

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)

    def downloadFile(self, url, downloadPath, proxyHandler=None, notifier=None, retry=0):
        try:
            if os.path.exists(downloadPath) and os.path.getsize(downloadPath):
                if notifier is not None:
                    notifier.emit('<font color=red><b>Image file already exists. Skip downloading file.</b></font>')
                return
            notifier.emit(('<font color=blue><b>Image URL: %s</b></font>' % url))
            regex = Regex()
            opener = urllib2.build_opener(urllib2.HTTPRedirectHandler(),
                                          urllib2.HTTPHandler(debuglevel=0),
                                          urllib2.HTTPSHandler(debuglevel=0))
            opener.addheaders = [
                config.USER_AGENT,
                ('Accept', 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'),
                ('Connection', 'keep-alive')]

            if proxyHandler is not None:
                opener.add_handler(proxyHandler)
            resp = urllib2.urlopen(url, timeout=30)
            contentLength = resp.info()['Content-Length']
            contentLength = regex.getSearchedData('(?i)^(\d+)', contentLength)
            totalSize = float(contentLength)
            directory = os.path.dirname(downloadPath)
            if not os.path.exists(directory):
                os.makedirs(directory)
            dl_file = open(downloadPath, 'wb')
            currentSize = 0
            CHUNK_SIZE = 32768
            while True:
                data = resp.read(CHUNK_SIZE)
                if not data:
                    break
                currentSize += len(data)
                dl_file.write(data)
                msg = '=====> ' + str(round(float(currentSize * 100) / totalSize, 2)) + \
                      '% of ' + str(totalSize / (1024)) + ' KB'
                print('=====> ' + str(round(float(currentSize * 100) / totalSize, 2)) + '% of ' + str(
                    totalSize) + ' bytes')

                if notifier is not None:
                    notifier.emit('<font color=blue><b>%s</b></font>' % msg)
                if currentSize >= totalSize:
                    dl_file.close()
                    return True
        except Exception, x:
            print x
            notifier.emit(('<font color=red><b>Error Download Image URL: %s</b></font>' % url))
            if retry < 1:
                notifier.emit('<font color=black><b>Will retry after 5 seconds.</b></font>')
                time.sleep(5)
                notifier.emit('<font color=black><b>Retry...</b></font>')
                self.downloadFile(url, downloadPath, proxyHandler, notifier, retry + 1)
            else:
                notifier.emit('<font color=red><b>Failed to download after maximum retry.</b></font>')

class SaraivaScrapper(QThread):
    notifySaraiva = pyqtSignal(object)

    def __init__(self, urlList, category, htmlTag, replaceTag):
        QThread.__init__(self)
        self.logger = LogManager(__name__)
        self.spider = Spider()
        self.regex = Regex()
        self.utils = Utils()
        self.urlList = urlList
        self.category = category
        self.htmlTag = self.regex.replaceData('\r+', '', htmlTag)
        self.htmlTag = self.regex.replaceData('\n+', ' ', self.htmlTag)
        self.htmlTag = self.regex.replaceData('\s+', ' ', self.htmlTag)
        self.htmlTag = self.regex.replaceData(r'\"+', '\"', self.htmlTag)
        self.replaceTag = replaceTag
        self.csvWriter = Csv(category + '.csv')
        csvDataHeader = ['Link', 'Name', 'Subtitle', 'Price', 'Synopsis and Characteristics', 'Picture']
        self.csvWriter.writeCsvRow(csvDataHeader)
        self.mainUrl = 'http://busca.livrariasaraiva.com.br'
        self.scrapUrl = None
        self.dbHelper = DbHelper('saraiva.db')
        self.dbHelper.createTable(category)
        self.total = self.dbHelper.getTotalProduct(category)

    def run(self, retry=0):
        try:
            if self.urlList is not None and len(self.urlList):
                for url in self.urlList:
                    if len(url) > 0:
                        url = self.regex.replaceData('(?i)\r', '', url)
                        url = self.regex.replaceData('(?i)\n', '', url)
                        self.notifySaraiva.emit('<font color=green><b>Saraiva Main URL: %s</b></font>' % url)
                        paginationUrl, self.maxRecords = self.reformatUrl(url)
                        self.notifySaraiva.emit(
                            '<font color=black><b>Total Records: %s</b></font>' % str(self.maxRecords))
                        print 'Max records: ', self.maxRecords
                        print 'URL: ' + str(paginationUrl)
                        sortList = ['&isort=globalpop', '&isort=best', '&isort=title', '&isort=title+rev',
                                    '&isort=price+rev',
                                    '&isort=price', '&isort=date+rev']
                        for sort in sortList:
                            self.scrapResults(paginationUrl, sort)
            self.notifySaraiva.emit('<font color=red><b>Saraiva Data Scraping finished.</b></font>')
        except Exception, x:
            print x.message
            self.logger.error('Exception at run: ', x.message)
            if retry < 5:
                self.run(retry + 1)

class PaodeacucarScrapper(QThread):
    notifyPaode = pyqtSignal(object)

    def __init__(self):
        QThread.__init__(self)
        self.logger = LogManager(__name__)
        self.spider = Spider()
        self.regex = Regex()
        self.utils = Utils()
        self.mainUrl = 'http://www.paodeacucar.com.br/'
        self.url = 'http://www.paodeacucar.com.br/'
        dupCsvReader = Csv()
        self.dupCsvRows = dupCsvReader.readCsvRow('paodeacucar.csv', 4)
        self.csvWriter = Csv('paodeacucar.csv')
        csvDataHeader = ['SKU', 'Category', 'Subcategory', 'Name', 'URL', 'URL Image', 'Details',
                         'Nutrients Table html code', 'Price from, 28/abr/14', '28/abr/14']
        if 'URL' not in self.dupCsvRows:
            self.dupCsvRows.append(csvDataHeader)
            self.csvWriter.writeCsvRow(csvDataHeader)

    def run(self):
        self.scrapData()

    def scrapData(self):
        try:
            print 'Main URL: ', self.url
            self.notifyPaode.emit(('<font color=green><b>Main URL: %s</b></font>' % self.url))
            data = self.spider.fetchData(self.url)
            if data and len(data) > 0:
                data = self.regex.reduceNewLine(data)
                data = self.regex.reduceBlankSpace(data)
                soup = BeautifulSoup(data)
                categories = soup.find('nav', class_='items-wrapper').find_all('li', class_=re.compile('\s*item\s*'))
                print 'Total Categories: ', len(categories)
                self.notifyPaode.emit(('<font color=black><b>Total Categories: %s</b></font>' % str(len(categories))))
                for category in categories:
                    if category.a is not None:
                        submenu_target = self.regex.replaceData('#', '', category.a.get('data-target'))
                        sub_categories = soup.find('ul', id=submenu_target).find_all('li', class_='item')
                        print 'Total Sub Categories: ', len(sub_categories)
                        self.notifyPaode.emit(('<font color=black><b>Total Subcategories: %s</b></font>' % str(len(sub_categories))))
                        for sub_category in sub_categories:
                            sub_category_label = sub_category.find('span', class_='label').text
                            sub_category_url = sub_category.a.get('href') if sub_category.a is not None else 'N/A'
                            self.scrapItems(sub_category_url, category.text, sub_category_label)
        except Exception, x:
            self.logger.error(x.message)
            print x

 def __init__(self):
     self.logger = LogManager(__name__)
     self.spider = Spider()
     self.regex = Regex()
     self.utils = Utils()
     self.mainUrl = 'http://www.ebags.com'
     self.url = 'http://www.ebags.com/brands'

 def __init__(self, input_file, output_file):
     self.logger = LogManager(__name__)
     self.spider = Spider()
     self.regex = Regex()
     self.utils = Utils()
     self.input_file = input_file
     self.output_file = output_file

    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()

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)

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)

 def __init__(self, spider, memberList, subject, message):
     QThread.__init__(self)
     #        self.spider = Spider()
     self.spider = spider
     self.regex = Regex()
     self.memberList = memberList
     self.subject = unicode(subject)
     self.message = unicode(message)

 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)

class AmazonScrapper():
    def __init__(self, url):
        self.logger = LogManager(__name__)
        self.spider = Spider()
        self.regex = Regex()
        self.utils = Utils()
        self.url = url
        self.base_product_url = 'http://www.amazon.com/dp/'
        self.base_image_url = 'http://ecx.images-amazon.com/images/I/'
        self.csvWriter = Csv('amazon.csv')
        csvDataHeader = ['URL', 'HTML Path', 'Image URLS']
        self.csvWriter.writeCsvRow(csvDataHeader)

    def scrapData(self):
        try:
            host = ('Host', 'www.amazon.com')
            data = self.spider.fetchData(self.url, host=host)
            if data:
                data = self.regex.reduceNewLine(data)
                data = self.regex.reduceBlankSpace(data)
                searchParams = self.regex.getSearchedData('(?i)var searchParams = {([^\}]*)}', data)
                searchParams = searchParams.split(',')
                seller = ''
                marketPlaceId = ''
                useMYI = ''
                for searchParam in searchParams:
                    searchParam = self.regex.reduceBlankSpace(searchParam)
                    searchParam = self.regex.replaceData('\'', '', searchParam)

                    if searchParam.startswith('seller'):
                        seller = searchParam.split(':')[1].strip()
                        seller = seller.decode('string-escape')
                    if searchParam.startswith('marketplaceID'):
                        marketPlaceId = searchParam.split(':')[1].strip()
                        marketPlaceId = marketPlaceId.decode('string-escape')
                    if searchParam.startswith('useMYI'):
                        useMYI = searchParam.split(':')[1].strip()
                        useMYI = useMYI.decode('string-escape')
                params = {'seller': seller,
                          'marketPlaceId': marketPlaceId,
                          'useMYI': useMYI}
                ajax_url = 'http://www.amazon.com/gp/aag/ajax/productWidget.html'
                self.scrapAjaxPage(ajax_url, params, host)
        except Exception, x:
            print x

 def __init__(self, urllist):
     QThread.__init__(self)
     self.logger = LogManager(__name__)
     self.spider = Spider()
     self.regex = Regex()
     self.utils = Utils()
     print urllist
     self.urllist = urllist
     self.csv = Csv('scrapper.csv')