feedparser.py

来自「Harvestman-最新版本」· Python 代码 · 共 1,630 行 · 第 1/5 页

        # categories/tags/keywords/whatever are handled in _end_category
        if element == 'category':
            return output
        
        # store output in appropriate place(s)
        if self.inentry and not self.insource:
            if element == 'content':
                self.entries[-1].setdefault(element, [])
                contentparams = copy.deepcopy(self.contentparams)
                contentparams['value'] = output
                self.entries[-1][element].append(contentparams)
            elif element == 'link':
                self.entries[-1][element] = output
                if output:
                    self.entries[-1]['links'][-1]['href'] = output
            else:
                if element == 'description':
                    element = 'summary'
                self.entries[-1][element] = output
                if self.incontent:
                    contentparams = copy.deepcopy(self.contentparams)
                    contentparams['value'] = output
                    self.entries[-1][element + '_detail'] = contentparams
        elif (self.infeed or self.insource) and (not self.intextinput) and (not self.inimage):
            context = self._getContext()
            if element == 'description':
                element = 'subtitle'
            context[element] = output
            if element == 'link':
                context['links'][-1]['href'] = output
            elif self.incontent:
                contentparams = copy.deepcopy(self.contentparams)
                contentparams['value'] = output
                context[element + '_detail'] = contentparams
        return output

    def pushContent(self, tag, attrsD, defaultContentType, expectingText):
        self.incontent += 1
        self.contentparams = FeedParserDict({
            'type': self.mapContentType(attrsD.get('type', defaultContentType)),
            'language': self.lang,
            'base': self.baseuri})
        self.contentparams['base64'] = self._isBase64(attrsD, self.contentparams)
        self.push(tag, expectingText)

    def popContent(self, tag):
        value = self.pop(tag)
        self.incontent -= 1
        self.contentparams.clear()
        return value
        
    def _mapToStandardPrefix(self, name):
        colonpos = name.find(':')
        if colonpos <> -1:
            prefix = name[:colonpos]
            suffix = name[colonpos+1:]
            prefix = self.namespacemap.get(prefix, prefix)
            name = prefix + ':' + suffix
        return name
        
    def _getAttribute(self, attrsD, name):
        return attrsD.get(self._mapToStandardPrefix(name))

    def _isBase64(self, attrsD, contentparams):
        if attrsD.get('mode', '') == 'base64':
            return 1
        if self.contentparams['type'].startswith('text/'):
            return 0
        if self.contentparams['type'].endswith('+xml'):
            return 0
        if self.contentparams['type'].endswith('/xml'):
            return 0
        return 1

    def _itsAnHrefDamnIt(self, attrsD):
        href = attrsD.get('url', attrsD.get('uri', attrsD.get('href', None)))
        if href:
            try:
                del attrsD['url']
            except KeyError:
                pass
            try:
                del attrsD['uri']
            except KeyError:
                pass
            attrsD['href'] = href
        return attrsD
    
    def _save(self, key, value):
        context = self._getContext()
        context.setdefault(key, value)

    def _start_rss(self, attrsD):
        versionmap = {'0.91': 'rss091u',
                      '0.92': 'rss092',
                      '0.93': 'rss093',
                      '0.94': 'rss094'}
        if not self.version:
            attr_version = attrsD.get('version', '')
            version = versionmap.get(attr_version)
            if version:
                self.version = version
            elif attr_version.startswith('2.'):
                self.version = 'rss20'
            else:
                self.version = 'rss'
    
    def _start_dlhottitles(self, attrsD):
        self.version = 'hotrss'

    def _start_channel(self, attrsD):
        self.infeed = 1
        self._cdf_common(attrsD)
    _start_feedinfo = _start_channel

    def _cdf_common(self, attrsD):
        if attrsD.has_key('lastmod'):
            self._start_modified({})
            self.elementstack[-1][-1] = attrsD['lastmod']
            self._end_modified()
        if attrsD.has_key('href'):
            self._start_link({})
            self.elementstack[-1][-1] = attrsD['href']
            self._end_link()
    
    def _start_feed(self, attrsD):
        self.infeed = 1
        versionmap = {'0.1': 'atom01',
                      '0.2': 'atom02',
                      '0.3': 'atom03'}
        if not self.version:
            attr_version = attrsD.get('version')
            version = versionmap.get(attr_version)
            if version:
                self.version = version
            else:
                self.version = 'atom'

    def _end_channel(self):
        self.infeed = 0
    _end_feed = _end_channel
    
    def _start_image(self, attrsD):
        self.inimage = 1
        self.push('image', 0)
        context = self._getContext()
        context.setdefault('image', FeedParserDict())
            
    def _end_image(self):
        self.pop('image')
        self.inimage = 0

    def _start_textinput(self, attrsD):
        self.intextinput = 1
        self.push('textinput', 0)
        context = self._getContext()
        context.setdefault('textinput', FeedParserDict())
    _start_textInput = _start_textinput
    
    def _end_textinput(self):
        self.pop('textinput')
        self.intextinput = 0
    _end_textInput = _end_textinput

    def _start_author(self, attrsD):
        self.inauthor = 1
        self.push('author', 1)
    _start_managingeditor = _start_author
    _start_dc_author = _start_author
    _start_dc_creator = _start_author
    _start_itunes_author = _start_author

    def _end_author(self):
        self.pop('author')
        self.inauthor = 0
        self._sync_author_detail()
    _end_managingeditor = _end_author
    _end_dc_author = _end_author
    _end_dc_creator = _end_author
    _end_itunes_author = _end_author

    def _start_itunes_owner(self, attrsD):
        self.inpublisher = 1
        self.push('publisher', 0)

    def _end_itunes_owner(self):
        self.pop('publisher')
        self.inpublisher = 0
        self._sync_author_detail('publisher')

    def _start_contributor(self, attrsD):
        self.incontributor = 1
        context = self._getContext()
        context.setdefault('contributors', [])
        context['contributors'].append(FeedParserDict())
        self.push('contributor', 0)

    def _end_contributor(self):
        self.pop('contributor')
        self.incontributor = 0

    def _start_dc_contributor(self, attrsD):
        self.incontributor = 1
        context = self._getContext()
        context.setdefault('contributors', [])
        context['contributors'].append(FeedParserDict())
        self.push('name', 0)

    def _end_dc_contributor(self):
        self._end_name()
        self.incontributor = 0

    def _start_name(self, attrsD):
        self.push('name', 0)
    _start_itunes_name = _start_name

    def _end_name(self):
        value = self.pop('name')
        if self.inpublisher:
            self._save_author('name', value, 'publisher')
        elif self.inauthor:
            self._save_author('name', value)
        elif self.incontributor:
            self._save_contributor('name', value)
        elif self.intextinput:
            context = self._getContext()
            context['textinput']['name'] = value
    _end_itunes_name = _end_name

    def _start_width(self, attrsD):
        self.push('width', 0)

    def _end_width(self):
        value = self.pop('width')
        try:
            value = int(value)
        except:
            value = 0
        if self.inimage:
            context = self._getContext()
            context['image']['width'] = value

    def _start_height(self, attrsD):
        self.push('height', 0)

    def _end_height(self):
        value = self.pop('height')
        try:
            value = int(value)
        except:
            value = 0
        if self.inimage:
            context = self._getContext()
            context['image']['height'] = value

    def _start_url(self, attrsD):
        self.push('href', 1)
    _start_homepage = _start_url
    _start_uri = _start_url

    def _end_url(self):
        value = self.pop('href')
        if self.inauthor:
            self._save_author('href', value)
        elif self.incontributor:
            self._save_contributor('href', value)
        elif self.inimage:
            context = self._getContext()
            context['image']['href'] = value
        elif self.intextinput:
            context = self._getContext()
            context['textinput']['link'] = value
    _end_homepage = _end_url
    _end_uri = _end_url

    def _start_email(self, attrsD):
        self.push('email', 0)
    _start_itunes_email = _start_email

    def _end_email(self):
        value = self.pop('email')
        if self.inpublisher:
            self._save_author('email', value, 'publisher')
        elif self.inauthor:
            self._save_author('email', value)
        elif self.incontributor:
            self._save_contributor('email', value)
    _end_itunes_email = _end_email

    def _getContext(self):
        if self.insource:
            context = self.sourcedata
        elif self.inentry:
            context = self.entries[-1]
        else:
            context = self.feeddata
        return context

    def _save_author(self, key, value, prefix='author'):
        context = self._getContext()
        context.setdefault(prefix + '_detail', FeedParserDict())
        context[prefix + '_detail'][key] = value
        self._sync_author_detail()

    def _save_contributor(self, key, value):
        context = self._getContext()
        context.setdefault('contributors', [FeedParserDict()])
        context['contributors'][-1][key] = value

    def _sync_author_detail(self, key='author'):
        context = self._getContext()
        detail = context.get('%s_detail' % key)
        if detail:
            name = detail.get('name')
            email = detail.get('email')
            if name and email:
                context[key] = '%s (%s)' % (name, email)
            elif name:
                context[key] = name
            elif email:
                context[key] = email
        else:
            author = context.get(key)
            if not author: return
            emailmatch = re.search(r'''(([a-zA-Z0-9\_\-\.\+]+)@((\[[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.)|(([a-zA-Z0-9\-]+\.)+))([a-zA-Z]{2,4}|[0-9]{1,3})(\]?))''', author)