ScholarDataMining/FileMerger/webSearch_merge.py
2023-10-06 13:55:50 +08:00

142 lines
4.3 KiB
Python

import jwt
import json
import requests
import time
import re
from pprint import pprint
# ========== Aminer pre-set ==========
# Aminer secret key
secret_key = "81hJKrNgKkMqow=="
user_id = "650c31aa078ed986b5d526cc"
expire_time = int(time.time()) + 60 # Expire in 1 min
now_time = int(time.time())
# Aminer JWT token generator
head = {
"alg": "HS256",
"sign_type": "SIGN"
}
payload = {
"user_id": user_id,
"exp": expire_time,
"timestamp": now_time
}
jwt_token = jwt.encode(payload, secret_key, algorithm="HS256", headers=head)
# ========== Aminer API link ==========
api_author_info = "https://datacenter.aminer.cn/gateway/open_platform/api/v2/person/search"
api_article_info = "https://datacenter.aminer.cn/gateway/open_platform/api/v3/paper/list/by/publish"
api_articleDetail_info = "https://datacenter.aminer.cn/gateway/open_platform/api/v3/paper/detail/list"
# ========== Function ==========
# ---------- Get the article web-ID ----------
def aminer_article_webID(title):
headers = {
"Authorization": f"Bearer {jwt_token}"
}
params = {
"page": "",
"size": "",
"title": re.sub(r'[^a-zA-Z0-9\s]+', ' ', title).strip()
}
response = requests.post(api_article_info, headers=headers, params=params)
if response.status_code == 200:
data = response.json()
if len(data.get('data')) > 1:
print("\nERROR: Cannot find the web-ID of \'" + title + "\'")
Retry_article_title.append(title) # Add the title into retry list
return None
print('\n========== The web-ID of the article ==========')
pprint(data)
article_aminerID.append(data.get('data')[0].get('id')) # Return article_ID in website
else:
print("\nERROR: Cannot find the web-ID of \'" + title + "\'")
Retry_article_title.append(title) # Add the title into retry list
# ---------- Get the article details ----------
def aminer_article_Detail(article_id):
headers = {
"Content_Type": "application/json;charset=utf-8",
"Authorization": f"Bearer {jwt_token}"
}
request_data = {
"ids": [article_id]
}
response = requests.post(api_articleDetail_info, headers=headers, data=json.dumps(request_data))
if response.status_code == 200:
data = response.json()
print('\n========== The detail of the article ==========')
pprint(data)
authors_ID = data.get('data')[0].get('authors')
for author_ID in authors_ID:
author_ID = author_ID.get('id')
if author_ID is not None:
author_aminerID.append(author_ID)
else:
print("\nERROR: Cannot find the detail of the article \'" + article_id + "\'")
Retry_article_aminerID.append(article_id) # Add the article ID into retry list
# ---------- Get the author's article list ----------
def aminer_author_info(author_id):
headers = {
"Content-Type": "application/json;charset=utf-8",
"Authorization": f"Bearer {jwt_token}"
}
request_data = {
"ids": author_id
}
response = requests.post(api_author_info, headers=headers, data=json.dumps(request_data))
if response.status_code == 200:
data = response.json()
print("\n========== The author's information ==========")
pprint(data)
else:
print("\nERROR: Cannot find the article-list's ID of \'" + author_id + "\'")
Retry_author_aminerID.append(author_id) # Add the author ID into the retry list
# ========== Main code ==========
# ---------- Lists to store the data needed to be searched in API ----------
article_title = ['Entire solutions of the spruce budworm model'] # Test title
article_aminerID = []
author_aminerID = []
# ---------- Lists to store the data needed to be retried ----------
Retry_article_title = []
Retry_article_aminerID = []
Retry_author_aminerID = []
# ---------- Call the API ----------
for title in article_title: # Get the article web-ID
aminer_article_webID(title)
if len(article_aminerID) > 0:
for ar_id in article_aminerID: # Get the article details
aminer_article_Detail(ar_id)
if len(author_aminerID) > 0:
aminer_author_info(author_aminerID) # Get the author's article list