Exemplo n.º 1
0
 def parse_search_result(self, node):
     r = SearchResult()
     r.detail_item = text(node, '(.//a)[1]', '', '/@href')
     r.title       = text(node, './/h3', 'title')
     r.author      = text(node, './/*', 'name')
     r.price       = text(node, './/*[@class="product-price-wrapper"]//*', 'price')
     r.cover_url   = text(node, './/img', '', '/@data-src')
     return r
Exemplo n.º 2
0
 def parse_search_result(self, node):
     r = SearchResult()
     r.detail_item = text(node, '(.//a)[1]', '', '/@href')
     r.title = text(node, './/*', 'book__title', '/text()')
     r.author = text(node, './/*', 'book__authorname')
     r.price = text(node, './/*', 'book__price')
     r.cover_url = text(node, './/*', 'book__cover', '//img/@src')
     return r
Exemplo n.º 3
0
 def parse_book_details(self, node):
     r = SearchResult()
     r.title     = text(node, './/*[@itemprop="name"]')
     r.author    = text(node, './/*[@itemprop="author"]')
     r.price     = text(node, './/*', 'price ')
     r.cover_url = text(node, './/img[@itemprop="image"]', '', '/@src')
     r.formats   = text(node, '//th[contains(., "Mediatyp")]/following-sibling::td[1]')
     r.drm       = r.formats
     return r
 def parse_book_details(self, node):
     r = SearchResult()
     r.title = text(node, './/*[@itemprop="name"]')
     r.author = text(node, './/*[@itemprop="author"]')
     r.price = text(node, './/*', 'current-price')
     r.cover_url = text(node, './/img[@itemprop="image"]', '', '/@src')
     r.formats = text(node, './/li[contains(., "elektroniska format:")]/*',
                      'product-info-panel__attributes__value', '/text()')
     r.drm = r.formats
     return r
Exemplo n.º 5
0
 def get_info(self):
     self.get_soup()
     name = self.soup.find('span', attrs={
         'id': 'productTitle'
     }).text.strip()
     seller = self.soup.find('div',
                             attrs={
                                 'data-feature-name': 'bylineInfo'
                             }).find('a').text
     price = lib.text(
         self.soup.find('span', attrs={'id': 'priceblock_ourprice'}))
     try:
         asin = lib.parent(self.soup.find(text='ASIN'),
                           level=3).text.split(': ')[-1]
     except:
         try:
             asin = list(
                 self.soup.find(
                     text=
                     '\n                          ASIN\n                          '
                 ).parent.parent.children)[-2].text.strip()
         except:
             try:
                 asin = soup.find(text='ASIN:\n                    '
                                  ).parent.parent.text.split(
                                      '                    ')[-1].strip()
             except:
                 asin = None
     return [{'name': name, 'seller': seller, 'price': price, 'asin': asin}]
Exemplo n.º 6
0
def text():
    url = request.args.get('url', '')
    if url:
        x = lib.text(url)
        return x, 200, {'Content-Type': 'text/plain; charset=utf-8'}
    else:
        return ''
Exemplo n.º 7
0
 def parse_search_result(self, node):
     r = SearchResult()
     r.detail_item = text(node, './/*', 'Item__title', '/a/@href')
     r.title       = text(node, './/*', 'Item__title', '/a/text()')
     r.author      = text(node, './/*', 'Item__authors')
     r.price       = text(node, './/*', 'pricing__price') + ' kr'
     r.formats     = text(node, './/*', 'Item__format-as-link')
     r.cover_url   = text(node, './/img', 'Item__image', '/@data-src')
     return r
Exemplo n.º 8
0
 def parse_book_details(self, node):
     r = SearchResult()
     r.title = text(node, './/*[@itemprop="name"]')
     r.author = text(node, './/*', 'bookdetails__authorname')
     r.price = text(node, './/*', 'bookdetails__price')
     r.cover_url = text(node, './/img[@itemprop="image"]', '', '/@src')
     r.formats = text(node, './/*', 'book_info__format', '/span[2]/text()')
     r.drm = text(node, './/*', 'book_info__drm', '/span[2]/text()')
     return r
 def parse_search_result(self, node):
     r = SearchResult()
     r.detail_item = text(node, './/*', 'item-info', '/a/@href')
     r.title = text(node, './/*[@itemprop="name"]')
     r.author = text(node, './/*[@itemprop="author"]')
     r.price = text(node, './/*', 'current-price')
     r.formats = text(node, './/*', 'format ')
     r.cover_url = text(node, './/img[@itemprop="image"]', '',
                        '/@data-original')
     return r
Exemplo n.º 10
0
 def parse_book_details(self, node):
     r = SearchResult()
     r.title     = text(node, '//*', 'product-page__title', '/text[1]')
     r.author    = text(node, '//*', 'u-m-t--1 deci')
     r.price     = text(node, '//*', 'product-page__pricing') + ' kr'
     r.cover_url = text(node, '//div', 'product-image', '/img/@src')
     details     = xpath(node, '//dl', 'product-page__facts')[0]
     for item in xpath(details, './dt'):
         name = text(item, '.')
         if 'Filformat' == name:
             r.formats = text(item, './following-sibling::dd[1]')
             r.drm     = r.formats
     return r