def mainProcess(self,url): raw_data = self.getSource(url) soup = BeautifulSoup.BeautifulSoup(''.join(raw_data)) papers_title = soup.findAll("a", { "class" : "gsc_a_at" }) with open('publication.json', 'w') as f: for title in papers_title: articles = gs.query(search=title.string, author='Si Chen', max_results=1) f.write(articles[0].dumps('json').encode('utf8')) print(articles[0].dumps('json'))
def get_gscholar_n_citations(self, title, wait=True): if wait: time.sleep(randint(10, 20)) return query(title)