feedparser.py

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

            if not emailmatch: return
            email = emailmatch.group(0)
            # probably a better way to do the following, but it passes all the tests
            author = author.replace(email, '')
            author = author.replace('()', '')
            author = author.strip()
            if author and (author[0] == '('):
                author = author[1:]
            if author and (author[-1] == ')'):
                author = author[:-1]
            author = author.strip()
            context.setdefault('%s_detail' % key, FeedParserDict())
            context['%s_detail' % key]['name'] = author
            context['%s_detail' % key]['email'] = email

    def _start_subtitle(self, attrsD):
        self.pushContent('subtitle', attrsD, 'text/plain', 1)
    _start_tagline = _start_subtitle
    _start_itunes_subtitle = _start_subtitle

    def _end_subtitle(self):
        self.popContent('subtitle')
    _end_tagline = _end_subtitle
    _end_itunes_subtitle = _end_subtitle
            
    def _start_rights(self, attrsD):
        self.pushContent('rights', attrsD, 'text/plain', 1)
    _start_dc_rights = _start_rights
    _start_copyright = _start_rights

    def _end_rights(self):
        self.popContent('rights')
    _end_dc_rights = _end_rights
    _end_copyright = _end_rights

    def _start_item(self, attrsD):
        self.entries.append(FeedParserDict())
        self.push('item', 0)
        self.inentry = 1
        self.guidislink = 0
        id = self._getAttribute(attrsD, 'rdf:about')
        if id:
            context = self._getContext()
            context['id'] = id
        self._cdf_common(attrsD)
    _start_entry = _start_item
    _start_product = _start_item

    def _end_item(self):
        self.pop('item')
        self.inentry = 0
    _end_entry = _end_item

    def _start_dc_language(self, attrsD):
        self.push('language', 1)
    _start_language = _start_dc_language

    def _end_dc_language(self):
        self.lang = self.pop('language')
    _end_language = _end_dc_language

    def _start_dc_publisher(self, attrsD):
        self.push('publisher', 1)
    _start_webmaster = _start_dc_publisher

    def _end_dc_publisher(self):
        self.pop('publisher')
        self._sync_author_detail('publisher')
    _end_webmaster = _end_dc_publisher

    def _start_published(self, attrsD):
        self.push('published', 1)
    _start_dcterms_issued = _start_published
    _start_issued = _start_published

    def _end_published(self):
        value = self.pop('published')
        self._save('published_parsed', _parse_date(value))
    _end_dcterms_issued = _end_published
    _end_issued = _end_published

    def _start_updated(self, attrsD):
        self.push('updated', 1)
    _start_modified = _start_updated
    _start_dcterms_modified = _start_updated
    _start_pubdate = _start_updated
    _start_dc_date = _start_updated

    def _end_updated(self):
        value = self.pop('updated')
        parsed_value = _parse_date(value)
        self._save('updated_parsed', parsed_value)
    _end_modified = _end_updated
    _end_dcterms_modified = _end_updated
    _end_pubdate = _end_updated
    _end_dc_date = _end_updated

    def _start_created(self, attrsD):
        self.push('created', 1)
    _start_dcterms_created = _start_created

    def _end_created(self):
        value = self.pop('created')
        self._save('created_parsed', _parse_date(value))
    _end_dcterms_created = _end_created

    def _start_expirationdate(self, attrsD):
        self.push('expired', 1)

    def _end_expirationdate(self):
        self._save('expired_parsed', _parse_date(self.pop('expired')))

    def _start_cc_license(self, attrsD):
        self.push('license', 1)
        value = self._getAttribute(attrsD, 'rdf:resource')
        if value:
            self.elementstack[-1][2].append(value)
        self.pop('license')
        
    def _start_creativecommons_license(self, attrsD):
        self.push('license', 1)

    def _end_creativecommons_license(self):
        self.pop('license')

    def _addTag(self, term, scheme, label):
        context = self._getContext()
        tags = context.setdefault('tags', [])
        if (not term) and (not scheme) and (not label): return
        value = FeedParserDict({'term': term, 'scheme': scheme, 'label': label})
        if value not in tags:
            tags.append(FeedParserDict({'term': term, 'scheme': scheme, 'label': label}))

    def _start_category(self, attrsD):
        if _debug: sys.stderr.write('entering _start_category with %s\n' % repr(attrsD))
        term = attrsD.get('term')
        scheme = attrsD.get('scheme', attrsD.get('domain'))
        label = attrsD.get('label')
        self._addTag(term, scheme, label)
        self.push('category', 1)
    _start_dc_subject = _start_category
    _start_keywords = _start_category
        
    def _end_itunes_keywords(self):
        for term in self.pop('itunes_keywords').split():
            self._addTag(term, 'http://www.itunes.com/', None)
        
    def _start_itunes_category(self, attrsD):
        self._addTag(attrsD.get('text'), 'http://www.itunes.com/', None)
        self.push('category', 1)
        
    def _end_category(self):
        value = self.pop('category')
        if not value: return
        context = self._getContext()
        tags = context['tags']
        if value and len(tags) and not tags[-1]['term']:
            tags[-1]['term'] = value
        else:
            self._addTag(value, None, None)
    _end_dc_subject = _end_category
    _end_keywords = _end_category
    _end_itunes_category = _end_category

    def _start_cloud(self, attrsD):
        self._getContext()['cloud'] = FeedParserDict(attrsD)
        
    def _start_link(self, attrsD):
        attrsD.setdefault('rel', 'alternate')
        attrsD.setdefault('type', 'text/html')
        attrsD = self._itsAnHrefDamnIt(attrsD)
        if attrsD.has_key('href'):
            attrsD['href'] = self.resolveURI(attrsD['href'])
        expectingText = self.infeed or self.inentry or self.insource
        context = self._getContext()
        context.setdefault('links', [])
        context['links'].append(FeedParserDict(attrsD))
        if attrsD['rel'] == 'enclosure':
            self._start_enclosure(attrsD)
        if attrsD.has_key('href'):
            expectingText = 0
            if (attrsD.get('rel') == 'alternate') and (self.mapContentType(attrsD.get('type')) in self.html_types):
                context['link'] = attrsD['href']
        else:
            self.push('link', expectingText)
    _start_producturl = _start_link

    def _end_link(self):
        value = self.pop('link')
        context = self._getContext()
        if self.intextinput:
            context['textinput']['link'] = value
        if self.inimage:
            context['image']['link'] = value
    _end_producturl = _end_link

    def _start_guid(self, attrsD):
        self.guidislink = (attrsD.get('ispermalink', 'true') == 'true')
        self.push('id', 1)

    def _end_guid(self):
        value = self.pop('id')
        self._save('guidislink', self.guidislink and not self._getContext().has_key('link'))
        if self.guidislink:
            # guid acts as link, but only if 'ispermalink' is not present or is 'true',
            # and only if the item doesn't already have a link element
            self._save('link', value)

    def _start_title(self, attrsD):
        self.pushContent('title', attrsD, 'text/plain', self.infeed or self.inentry or self.insource)
    _start_dc_title = _start_title
    _start_media_title = _start_title

    def _end_title(self):
        value = self.popContent('title')
        context = self._getContext()
        if self.intextinput:
            context['textinput']['title'] = value
        elif self.inimage:
            context['image']['title'] = value
    _end_dc_title = _end_title
    _end_media_title = _end_title

    def _start_description(self, attrsD):
        context = self._getContext()
        if context.has_key('summary'):
            self._summaryKey = 'content'
            self._start_content(attrsD)
        else:
            self.pushContent('description', attrsD, 'text/html', self.infeed or self.inentry or self.insource)

    def _start_abstract(self, attrsD):
        self.pushContent('description', attrsD, 'text/plain', self.infeed or self.inentry or self.insource)

    def _end_description(self):
        if self._summaryKey == 'content':
            self._end_content()
        else:
            value = self.popContent('description')
            context = self._getContext()
            if self.intextinput:
                context['textinput']['description'] = value
            elif self.inimage:
                context['image']['description'] = value
        self._summaryKey = None
    _end_abstract = _end_description

    def _start_info(self, attrsD):
        self.pushContent('info', attrsD, 'text/plain', 1)
    _start_feedburner_browserfriendly = _start_info

    def _end_info(self):
        self.popContent('info')
    _end_feedburner_browserfriendly = _end_info

    def _start_generator(self, attrsD):
        if attrsD:
            attrsD = self._itsAnHrefDamnIt(attrsD)
            if attrsD.has_key('href'):
                attrsD['href'] = self.resolveURI(attrsD['href'])
        self._getContext()['generator_detail'] = FeedParserDict(attrsD)
        self.push('generator', 1)

    def _end_generator(self):
        value = self.pop('generator')
        context = self._getContext()
        if context.has_key('generator_detail'):
            context['generator_detail']['name'] = value
            
    def _start_admin_generatoragent(self, attrsD):
        self.push('generator', 1)
        value = self._getAttribute(attrsD, 'rdf:resource')
        if value:
            self.elementstack[-1][2].append(value)
        self.pop('generator')
        self._getContext()['generator_detail'] = FeedParserDict({'href': value})

    def _start_admin_errorreportsto(self, attrsD):
        self.push('errorreportsto', 1)
        value = self._getAttribute(attrsD, 'rdf:resource')
        if value:
            self.elementstack[-1][2].append(value)
        self.pop('errorreportsto')
        
    def _start_summary(self, attrsD):
        context = self._getContext()
        if context.has_key('summary'):
            self._summaryKey = 'content'
            self._start_content(attrsD)
        else:
            self._summaryKey = 'summary'
            self.pushContent(self._summaryKey, attrsD, 'text/plain', 1)
    _start_itunes_summary = _start_summary

    def _end_summary(self):
        if self._summaryKey == 'content':
            self._end_content()
        else:
            self.popContent(self._summaryKey or 'summary')
        self._summaryKey = None
    _end_itunes_summary = _end_summary
        
    def _start_enclosure(self, attrsD):
        attrsD = self._itsAnHrefDamnIt(attrsD)
        self._getContext().setdefault('enclosures', []).append(FeedParserDict(attrsD))
        href = attrsD.get('href')
        if href:
            context = self._getContext()
            if not context.get('id'):
                context['id'] = href
            
    def _start_source(self, attrsD):
        self.insource = 1

    def _end_source(self):
        self.insource = 0
        self._getContext()['source'] = copy.deepcopy(self.sourcedata)
        self.sourcedata.clear()

    def _start_content(self, attrsD):
        self.pushContent('content', attrsD, 'text/plain', 1)
        src = attrsD.get('src')
        if src:
            self.contentparams['src'] = src
        self.push('content', 1)