|
|
|
@ -135,7 +135,8 @@ def parse(content): |
|
|
|
|
return params_list |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
base_url = 'https://libcon.bupt.edu.cn/http/77726476706e69737468656265737421f7b9569d2936695e790c88b8991b203a18454272' |
|
|
|
|
suffix = '77726476706e69737468656265737421f7b9569d2936695e790c88b8991b203a18454272' |
|
|
|
|
base_url = f'https://libcon.bupt.edu.cn/http/{suffix}' |
|
|
|
|
profession = "计算机软件与理论" |
|
|
|
|
keyword = f'(专业%3A"{profession}")' |
|
|
|
|
headers = { |
|
|
|
@ -318,7 +319,7 @@ def save(des, res, params): |
|
|
|
|
# 万方平台论文采集 |
|
|
|
|
def run(max=10, last_page=100, page_size=20): |
|
|
|
|
if max > last_page * page_size: |
|
|
|
|
writeInfo(f'采集数不能超过{last_page*page_size}') |
|
|
|
|
writeInfo(f'采集数不能超过{last_page * page_size}') |
|
|
|
|
return |
|
|
|
|
db.modify(f'delete from {sys_paper}') |
|
|
|
|
db.modify(f'delete from {sys_word}') |
|
|
|
|