ldy/ScholarDataMining
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix some bugs

Browse Source
This commit is contained in:
Chenxiao Xia 2023-10-29 15:19:40 +08:00
parent e37374d1e2
commit 11e326ea76
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Parsers/02_EJQTDE_spider/ejqtde_main.py
View File

@ -50,7 +50,7 @@ hrefs = []
# Base web urls # Base web urls
current_year = datetime.datetime.now().year 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/' baseWeb = 'https://www.math.u-szeged.hu/ejqtde/'
url_list = ['https://www.math.u-szeged.hu/ejqtde/periodica.html?periodica=1&paramtipus_ertek=publications&param_ertek=' url_list = ['https://www.math.u-szeged.hu/ejqtde/periodica.html?periodica=1&paramtipus_ertek=publications&param_ertek='

6
Parsers/02_EJQTDE_spider/ejqtde_scrawler.py
View File

@ -46,8 +46,8 @@ def author_detail(Data, Year, article_id, Author_list):
author = author.split(',') author = author.split(',')
author = [char.replace(' ', '') for char in author] author = [char.replace(' ', '') for char in author]
Firstname = author[0] Firstname = author[-1]
Lastname = author[-1] Lastname = author[0]
Middlename = ''.join(author[1:-1]) if len(author[1:-1]) > 0 else None Middlename = ''.join(author[1:-1]) if len(author[1:-1]) > 0 else None
# infor # infor
@ -59,7 +59,7 @@ def author_detail(Data, Year, article_id, Author_list):
Affiliation = line[1].get_text() Affiliation = line[1].get_text()
# Email # Email
Email = line[0].find('a').get('href') Email = line[0].find('a').get_text()
author_data = { author_data = {
"author_id": str(uuid.uuid4()), "author_id": str(uuid.uuid4()),