예제 #1
0
파일: pages.py 프로젝트: Konubinix/weboob
    def get_subtitle(self):
        desc = NotAvailable
        a = self.parser.select(self.document.getroot(), 'a#bt-dwl', 1)
        id = a.attrib.get('rel', '').split('/')[-1]
        m = re.match('Download \((\w+)\)', self.parser.tocleanstring(a))
        if m:
            ext = m.group(1)
        else:
            ext = u'zip'
        url = unicode('http://www.opensubtitles.org/subtitleserve/sub/%s' % id)
        link = self.parser.select(self.document.getroot(), 'link[rel=bookmark]', 1)
        title = unicode(link.attrib.get('title', ''))
        nb_cd = int(title.lower().split('cd')[0].split()[-1])
        lang = unicode(title.split('(')[1].split(')')[0])
        file_names = self.parser.select(self.document.getroot(), "img[title~=filename]")
        if len(file_names) > 0:
            file_name = file_names[0].getparent().text_content()
            file_name = ' '.join(file_name.split())
            desc = u'files :'
            for f in file_names:
                desc_line = f.getparent().text_content()
                desc += '\n'+' '.join(desc_line.split())
        name = unicode('%s (%s)' % (title, file_name))

        subtitle = Subtitle(id, name)
        subtitle.url = url
        subtitle.ext = ext
        for lshort, llong in LANGUAGE_CONV.items():
            if lang == llong:
                lang = unicode(lshort)
                break
        subtitle.language = lang
        subtitle.nb_cd = nb_cd
        subtitle.description = desc
        return subtitle
예제 #2
0
파일: pages.py 프로젝트: linura/weboob
    def get_subtitle(self):
        desc = NotAvailable
        a = self.parser.select(self.document.getroot(), 'a#bt-dwl-bt', 1)
        id = a.attrib.get('data-product-id', '')
        m = re.match('Download \((\w+)\)', self.parser.tocleanstring(a))
        if m:
            ext = m.group(1)
        else:
            ext = u'zip'
        url = unicode('http://www.opensubtitles.org/en/subtitleserve/sub/%s' %
                      id)
        link = self.parser.select(self.document.getroot(),
                                  'link[rel=bookmark]', 1)
        title = unicode(link.attrib.get('title', ''))
        nb_cd = int(title.lower().split('cd')[0].split()[-1])
        lang = unicode(title.split('(')[1].split(')')[0])
        file_names = self.parser.select(self.document.getroot(),
                                        "img[title~=filename]")
        if len(file_names) > 0:
            file_name = file_names[0].getparent().text_content()
            file_name = ' '.join(file_name.split())
            desc = u'files :'
            for f in file_names:
                desc_line = f.getparent().text_content()
                desc += '\n' + ' '.join(desc_line.split())
        name = unicode('%s (%s)' % (title, file_name))

        subtitle = Subtitle(id, name)
        subtitle.url = url
        subtitle.ext = ext
        for lshort, llong in LANGUAGE_CONV.items():
            if lang == llong:
                lang = unicode(lshort)
                break
        subtitle.language = lang
        subtitle.nb_cd = nb_cd
        subtitle.description = desc
        return subtitle
예제 #3
0
파일: pages.py 프로젝트: Konubinix/weboob
    def get_subtitle_from_line(self, line):
        cells = self.parser.select(line, 'td')
        if len(cells) > 0:
            links = self.parser.select(line, 'a')
            a = links[0]
            name = u" ".join(a.text.strip().split())
            first_cell = cells[0]
            spanlist = self.parser.select(first_cell, 'span')
            if len(spanlist) > 0:
                long_name = spanlist[0].attrib.get('title', '')
            else:
                texts = first_cell.itertext()
                long_name = texts.next()
                long_name = texts.next()
                if "Download at 25" in long_name:
                    long_name = "---"
            name = "%s (%s)" % (name, long_name)
            second_cell = cells[1]
            link = self.parser.select(second_cell, 'a', 1)
            lang = link.attrib.get('href', '').split('/')[-1].split('-')[-1]
            for lshort, llong in LANGUAGE_CONV.items():
                if lang == llong:
                    lang = unicode(lshort)
                    break
            nb_cd = int(cells[2].text.strip().lower().replace('cd', ''))
            cell_dl = cells[4]
            href = self.parser.select(cell_dl, 'a', 1).attrib.get('href', '')
            url = unicode('http://www.opensubtitles.org%s' % href)
            id = href.split('/')[-1]

            subtitle = Subtitle(id, name)
            subtitle.url = url
            subtitle.language = lang
            subtitle.nb_cd = nb_cd
            subtitle.description = NotLoaded
            return subtitle
예제 #4
0
파일: pages.py 프로젝트: lissyx/weboob
    def get_subtitle_from_line(self, line):
        cells = self.parser.select(line, 'td')
        if len(cells) > 0:
            links = self.parser.select(line, 'a')
            a = links[0]
            name = u" ".join(a.text.strip().split())
            first_cell = cells[0]
            spanlist = self.parser.select(first_cell, 'span')
            if len(spanlist) > 0:
                long_name = spanlist[0].attrib.get('title', '')
            else:
                texts = first_cell.itertext()
                long_name = texts.next()
                long_name = texts.next()
                if "Download at 25" in long_name:
                    long_name = "---"
            name = "%s (%s)" % (name, long_name)
            second_cell = cells[1]
            link = self.parser.select(second_cell, 'a', 1)
            lang = link.attrib.get('href', '').split('/')[-1].split('-')[-1]
            for lshort, llong in LANGUAGE_CONV.items():
                if lang == llong:
                    lang = unicode(lshort)
                    break
            nb_cd = int(cells[2].text.strip().lower().replace('cd', ''))
            cell_dl = cells[4]
            href = self.parser.select(cell_dl, 'a', 1).attrib.get('href', '')
            url = unicode('http://www.opensubtitles.org%s' % href)
            id = href.split('/')[-1]

            subtitle = Subtitle(id, name)
            subtitle.url = url
            subtitle.language = lang
            subtitle.nb_cd = nb_cd
            subtitle.description = NotLoaded
            return subtitle