def _get_nfzm_article(self, url, date, issue): medium = Medium.objects.get(pk=951) article = Article() article.medium = medium article.issue = issue article.url = url article.publication_date = date r = requests.get(url, cookies={'PHPSESSID': 'l19dgbf6ticijmo9ka9osvufk0'}) content = bs4.BeautifulSoup(r.content) article.title = content.title.string.split('-')[-1].strip() article.content = content.find('section', {'id' : 'articleContent'}).text author = content.find('span', {'class' : 'author'}).find_all('em') if author[1].text.find(u'南方周末记者') != -1: author, created = Journalist.objects.get_or_create(medium=medium, name=author[2].text.strip()) if not created: article.author = author elif author[1].text.find(u'南方周末特约撰稿') != -1: article.author_name = author[2].text.strip() elif author[1].text.find(u'南方周末编辑部') != -1: article.author_name = u'南方周末编辑部' print article.author or article.author_name return article