goodreads_parser.py 文件源码

def _get_book_info_from_tooltips(self, book_info):
        '''Gets books ASIN, title, authors, image url, description, and rating information'''
        if isinstance(book_info, tuple):
            book_info = [book_info]
        books_data = []
        link_pattern = 'resources[Book.{0}][type]=Book&resources[Book.{0}][id]={0}'
        tooltips_page_url = '/tooltips?' + "&".join([link_pattern.format(book_id) for book_id, image_url in book_info])
        tooltips_page_info = json.loads(open_url(self._connection, tooltips_page_url))['tooltips']

        for book_id, image_url in book_info:
            book_data = tooltips_page_info['Book.{0}'.format(book_id)]
            if not book_data:
                continue
            book_data = html.fromstring(book_data)
            parsed_data = self._parse_tooltip_info(book_data, book_id, image_url)
            if not parsed_data:
                continue
            books_data.append(parsed_data)

        return books_data