示例#1
0
    def _metadata(self, baike):
        from calibre.ebooks.metadata.book.base import Metadata

        info = baike.get_info()
        logging.debug("\n".join("%s:\t%s" % v for v in info.items()))

        mi = Metadata(info['title'])
        plat = "网络小说平台"
        plat = info.get(u'首发状态', plat)
        plat = info.get(u'首发网站', plat)
        plat = plat.replace(u'首发', '')
        mi.publisher = info.get(u'连载平台', plat)
        mi.authors = [info.get(u'作者', u'佚名')]
        mi.author_sort = mi.authors[0]
        mi.isbn = BAIKE_ISBN
        mi.tags = baike.get_tags()
        mi.pubdate = datetime.datetime.now()
        mi.timestamp = datetime.datetime.now()
        mi.cover_url = baike.get_image()
        mi.comments = re.sub(r'\[\d+\]$', "", baike.get_summary())
        mi.website = baike.http.url
        mi.source = u'百度百科'
        mi.provider_key = KEY
        mi.provider_value = baike.get_id()

        if self.copy_image and mi.cover_url:
            logging.debug("fetching cover: %s", mi.cover_url)
            img = io.BytesIO(urlopen(mi.cover_url).read())
            img_fmt = mi.cover_url.split(".")[-1]
            mi.cover_data = (img_fmt, img)

        if u'完结' in info.get(u'连载状态', ""):
            day = re.findall('\d*-\d*-\d*', info[u'连载状态'])
            try:
                mi.pubdate = datetime.datetime.strptime(day[0], '%Y-%m-%d')
            except:
                pass
        return mi
示例#2
0
    def _metadata(self, book):
        authors = []
        if book['author']:
            for author in book['author']:
                for r in REMOVES:
                    author = r.sub("", author)
                authors.append(author)
        if not authors: authors = [u'佚名']

        from calibre.ebooks.metadata.book.base import Metadata
        mi = Metadata(book['title'])
        mi.authors = authors
        mi.author_sort = mi.authors[0]
        mi.publisher = book['publisher']
        mi.comments = book['summary']
        mi.isbn = book.get('isbn13', None)
        mi.series = book.get('serials', None)
        mi.tags = [t['name'] for t in book['tags']][:8]
        mi.rating = int(float(book['rating']['average']))
        mi.pubdate = self.str2date(book['pubdate'])
        mi.timestamp = datetime.datetime.now()
        mi.douban_author_intro = book['author_intro']
        mi.douban_subtitle = book.get('subtitle', None)
        mi.website = "https://book.douban.com/isbn/%s" % mi.isbn
        mi.source = u'豆瓣'
        mi.provider_key = KEY
        mi.provider_value = book['id']

        mi.cover_url = book['images']['large']
        if self.copy_image:
            img = io.BytesIO(
                urlopen(Request(mi.cover_url, headers=CHROME_HEADERS)).read())
            img_fmt = mi.cover_url.split(".")[-1]
            mi.cover_data = (img_fmt, img)

        logging.debug("=================\ndouban metadata:\n%s" % mi)
        return mi