72 lines
2.7 KiB
Python
72 lines
2.7 KiB
Python
import os
|
||
import json
|
||
from pprint import pprint
|
||
|
||
'''
|
||
========== fileReader =========
|
||
1. 本程序用于读取作者信息后获取来源文章的标题，并且将其存储到新的字典当中
|
||
2. 通过检索作者信息获取 author_id 和 from_article，并且返回作者信息中检索来源文章的 title，
|
||
将作者信息和标题一并存储到新字典
|
||
3. 将新字典存储到 json 文件中
|
||
'''
|
||
|
||
|
||
# Function to find the author data which does not have "email" information
|
||
def Read(author_path, article_path):
|
||
# Read data list
|
||
def au_read(path, list):
|
||
with open(path, 'r', encoding='utf-8') as file:
|
||
data = json.load(file)
|
||
for Dict in range(len(data)-1, -1, -1):
|
||
list.append(data[Dict])
|
||
|
||
return list
|
||
|
||
def ar_read(path, file_name, ar_id, au_data, num):
|
||
file_path = os.path.join(path, file_name)
|
||
with open(file_path, 'r', encoding='utf-8') as file:
|
||
data = json.load(file)
|
||
for Dict in data:
|
||
if Dict.get('article_id') == ar_id[0]:
|
||
# A new dictionary to stored information
|
||
au_data['from_article_title'] = Dict.get('title')
|
||
num[0] += 1
|
||
|
||
# ========== Main code ==========
|
||
au_list = [] # List for author data
|
||
num = [0] # Data number counter
|
||
|
||
# Read the file
|
||
ar_names = os.listdir(article_path)
|
||
|
||
# Stored the author data which has no "email" information
|
||
au_list = au_read(author_path, au_list)
|
||
|
||
# Search the articles where the authors from
|
||
for au_MergeList in au_list:
|
||
for au_data in au_MergeList:
|
||
if num[0] % 100 == 0 and num[0] != 0:
|
||
print(str(num[0]) + " copies of data have been done.")
|
||
|
||
if int(au_data.get('affiliation', [{}])[0].get('year', 0)) <= 2009:
|
||
ar_read(article_path, ar_names[3], au_data.get('from_article'), au_data, num)
|
||
|
||
elif int(au_data.get('affiliation', [{}])[0].get('year', 0)) <= 2010:
|
||
ar_read(article_path, ar_names[0], au_data.get('from_article'), au_data, num)
|
||
|
||
elif int(au_data.get('affiliation', [{}])[0].get('year', 0)) <= 2020:
|
||
ar_read(article_path, ar_names[1], au_data.get('from_article'), au_data, num)
|
||
|
||
else:
|
||
ar_read(article_path, ar_names[2], au_data.get('from_article'), au_data, num)
|
||
|
||
with open('./Author_data(merged)/Author_data(info_supplementary).json', 'w', encoding='utf-8') as file:
|
||
json.dump(au_list, file, indent=4)
|
||
|
||
print('All data have been stored into ./Author_data(merged)/Author_data(info_supplementary).json')
|
||
|
||
# ========== Test code ==========
|
||
Read('./Author_data(merged)/Author_data(merged).json', './test_buffer/Article_output')
|
||
|
||
|