issue.py 文件源码

def crawl_articles(self, numbers):
        citation_loader = CitationLoader(numbers)
        entries = citation_loader.get_bibtex()
        articles = {}

        for entry in entries:
            number = entry['ID']

            try:
                article = Article.objects.get(entry_number=number)
                logger.info('Article [%s] already exists, it will be updated.' % number)
            except (DoesNotExist, ServerSelectionTimeoutError):
                article = Article()
                article.entry_number = number
                logger.info('Article [%s] is a new article.' % number)

            article.title = entry['title'] if 'title' in entry else ''
            article.author = entry['author'] if 'author' in entry else ''
            article.journal = entry['journal'] if 'journal' in entry else ''
            article.year = entry['year'] if 'year' in entry else ''
            article.volume = entry['volume'] if 'volume' in entry else ''
            article.number = entry['number'] if 'number' in entry else ''
            article.pages = entry['pages'] if 'pages' in entry else ''
            article.abstract = entry['abstract'] if 'abstract' in entry else ''
            article.keyword = entry['keyword'] if 'keyword' in entry else ''
            article.doi = entry['doi'] if 'doi' in entry else ''
            article.issn = entry['issn'] if 'issn' in entry else ''
            article.issue_reference = self.__issue

            try:
                article.save()
                logger.info('Article [%s] saved.' % number)
            except ServerSelectionTimeoutError:
                logger.info('Cannot connect to database, Article [%s] will not be saved.' % number)
            articles[number] = article

        return articles