From 11e326ea7627941e440c2f5ad86ae8be6a293c48 Mon Sep 17 00:00:00 2001 From: Chenxiao Xia Date: Sun, 29 Oct 2023 15:19:40 +0800 Subject: [PATCH] Fix some bugs --- Parsers/02_EJQTDE_spider/ejqtde_main.py | 2 +- Parsers/02_EJQTDE_spider/ejqtde_scrawler.py | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/Parsers/02_EJQTDE_spider/ejqtde_main.py b/Parsers/02_EJQTDE_spider/ejqtde_main.py index 8d05b6f..d180f15 100644 --- a/Parsers/02_EJQTDE_spider/ejqtde_main.py +++ b/Parsers/02_EJQTDE_spider/ejqtde_main.py @@ -50,7 +50,7 @@ hrefs = [] # Base web urls current_year = datetime.datetime.now().year -years = range(2009, 2011) # years = range(2010, current_year + 1) +years = range(2009, current_year + 1) # years = range(2010, current_year + 1) baseWeb = 'https://www.math.u-szeged.hu/ejqtde/' url_list = ['https://www.math.u-szeged.hu/ejqtde/periodica.html?periodica=1¶mtipus_ertek=publications¶m_ertek=' diff --git a/Parsers/02_EJQTDE_spider/ejqtde_scrawler.py b/Parsers/02_EJQTDE_spider/ejqtde_scrawler.py index e27ce6a..fab605b 100644 --- a/Parsers/02_EJQTDE_spider/ejqtde_scrawler.py +++ b/Parsers/02_EJQTDE_spider/ejqtde_scrawler.py @@ -46,8 +46,8 @@ def author_detail(Data, Year, article_id, Author_list): author = author.split(',') author = [char.replace(' ', '') for char in author] - Firstname = author[0] - Lastname = author[-1] + Firstname = author[-1] + Lastname = author[0] Middlename = ''.join(author[1:-1]) if len(author[1:-1]) > 0 else None # infor @@ -59,7 +59,7 @@ def author_detail(Data, Year, article_id, Author_list): Affiliation = line[1].get_text() # Email - Email = line[0].find('a').get('href') + Email = line[0].find('a').get_text() author_data = { "author_id": str(uuid.uuid4()),