feat: baidubaike utils
This commit is contained in:
@@ -1,6 +1,22 @@
|
|||||||
|
import os
|
||||||
|
|
||||||
url_file = "data/en_wiki_urls.txt"
|
url_file = "data/en_wiki_urls.txt"
|
||||||
|
|
||||||
if __name__ == '__main__':
|
|
||||||
|
def build_baidubaike_url_list():
|
||||||
|
file_list = []
|
||||||
|
files = os.listdir("data/baidubaike")
|
||||||
|
for file in files:
|
||||||
|
file_list.append(file)
|
||||||
|
with open("data/baidu_baike_urls.txt", "w", encoding="utf-8") as f:
|
||||||
|
for file in file_list:
|
||||||
|
with open("data/baidubaike/" + file, "r", encoding="utf-8") as g:
|
||||||
|
urls = g.readlines()
|
||||||
|
for url in urls:
|
||||||
|
f.write("https://baike.baidu.com/item/" + url)
|
||||||
|
|
||||||
|
|
||||||
|
def build_wiki_url_list():
|
||||||
line_list = []
|
line_list = []
|
||||||
with open(url_file, "r", encoding="utf-8") as f:
|
with open(url_file, "r", encoding="utf-8") as f:
|
||||||
line_list = f.readlines()
|
line_list = f.readlines()
|
||||||
@@ -12,3 +28,7 @@ if __name__ == '__main__':
|
|||||||
with open("t.txt", "w", encoding="utf-8") as f:
|
with open("t.txt", "w", encoding="utf-8") as f:
|
||||||
for r in result:
|
for r in result:
|
||||||
f.write(r)
|
f.write(r)
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == '__main__':
|
||||||
|
build_baidubaike_url_list()
|
||||||
|
|||||||
Reference in New Issue
Block a user