|
1 | | -#!/usr/bin/env python3 |
2 | | -import os |
| 1 | +from scholarly import scholarly |
| 2 | +import jsonpickle |
3 | 3 | import json |
4 | | -import requests |
5 | | -from bs4 import BeautifulSoup |
6 | | - |
7 | | -# === CONFIG === |
8 | | -SCHOLAR_USER_ID = "8-IhrB0AAAAJ" # your Google Scholar user ID |
9 | | -OUT_PATH = "assets/json/citations.json" |
10 | | - |
11 | | -def fetch_total_citations(): |
12 | | - url = f"https://scholar.google.com/citations?user={SCHOLAR_USER_ID}&hl=en" |
13 | | - headers = { |
14 | | - "User-Agent": ( |
15 | | - "Mozilla/5.0 (Windows NT 10.0; Win64; x64) " |
16 | | - "AppleWebKit/537.36 (KHTML, like Gecko) " |
17 | | - "Chrome/124.0 Safari/537.36" |
18 | | - ) |
19 | | - } |
20 | | - r = requests.get(url, headers=headers, timeout=30) |
21 | | - r.raise_for_status() |
22 | | - |
23 | | - soup = BeautifulSoup(r.text, "html.parser") |
24 | | - |
25 | | - # On Scholar, the total citations is in the first cell of this table |
26 | | - table = soup.find("table", id="gsc_rsb_st") |
27 | | - if not table: |
28 | | - raise RuntimeError("Could not find citation stats table on Google Scholar page.") |
29 | | - |
30 | | - cells = table.find_all("td", class_="gsc_rsb_std") |
31 | | - if not cells: |
32 | | - raise RuntimeError("Could not find citation value cell on Google Scholar page.") |
33 | | - |
34 | | - total_citations = cells[0].get_text(strip=True) |
35 | | - return total_citations |
36 | | - |
37 | | -def main(): |
38 | | - citations = fetch_total_citations() |
39 | | - print(f"Total citations: {citations}") |
40 | | - |
41 | | - data = { |
42 | | - "schemaVersion": 1, |
43 | | - "label": "citations", |
44 | | - "message": citations, |
45 | | - "color": "9cf" |
46 | | - } |
47 | | - |
48 | | - os.makedirs(os.path.dirname(OUT_PATH), exist_ok=True) |
49 | | - with open(OUT_PATH, "w", encoding="utf-8") as f: |
50 | | - json.dump(data, f, ensure_ascii=False) |
51 | | - |
52 | | - print(f"Wrote {OUT_PATH}") |
| 4 | +from datetime import datetime |
| 5 | +import os |
53 | 6 |
|
54 | | -if __name__ == "__main__": |
55 | | - main() |
| 7 | +author: dict = scholarly.search_author_id(os.environ['GOOGLE_SCHOLAR_ID']) |
| 8 | +scholarly.fill(author, sections=['basics', 'indices', 'counts', 'publications']) |
| 9 | +name = author['name'] |
| 10 | +author['updated'] = str(datetime.now()) |
| 11 | +author['publications'] = {v['author_pub_id']:v for v in author['publications']} |
| 12 | +print(json.dumps(author, indent=2)) |
| 13 | +os.makedirs('results', exist_ok=True) |
| 14 | +with open(f'results/gs_data.json', 'w') as outfile: |
| 15 | + json.dump(author, outfile, ensure_ascii=False) |
| 16 | + |
| 17 | +shieldio_data = { |
| 18 | + "schemaVersion": 1, |
| 19 | + "label": "citations", |
| 20 | + "message": f"{author['citedby']}", |
| 21 | +} |
| 22 | +with open(f'results/gs_data_shieldsio.json', 'w') as outfile: |
| 23 | + json.dump(shieldio_data, outfile, ensure_ascii=False) |
0 commit comments