File size: 4,636 Bytes
e4f5c0d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
908d5c9
e4f5c0d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
import json
import os
from datetime import datetime, timezone

from fasthtml.common import *
from huggingface_hub import HfApi, hf_hub_download
from starlette.responses import FileResponse
from generate_newsletter import process_new_papers
from apscheduler.schedulers.background import BackgroundScheduler
from apscheduler.triggers.cron import CronTrigger

from fasthtml_hf import setup_hf_backup

# Initialize Hugging Face API
HF_TOKEN = os.environ.get("HF_TOKEN")
DATASET_NAME = "cmcmaster/this_week_in_rheumatology"
api = HfApi(token=HF_TOKEN)

# Initialize scheduler
scheduler = BackgroundScheduler()

# Schedule newsletter generation to run every Monday at 1 AM UTC
scheduler.add_job(process_new_papers,
                  CronTrigger(day_of_week='mon', hour=1),
                  kwargs={
                      'end_date': '{{ (execution_date - timedelta(days=1)).strftime("%Y-%m-%d") }}',
                      'test': False
                  },
                  id='generate_newsletter',
                  name='Weekly newsletter generation',
                  replace_existing=True)

css = Style("""
    body { 
        font-family: Georgia, Times, serif;
        line-height: 1.6;
        color: #333;
        max-width: 800px;
        margin: 0 auto;
        padding: 20px;
        background: #fff;
    }

    h1, h2 { 
        color: #2c3e50;
        font-family: Georgia, Times, serif;
    }

    a { 
        color: #2c3e50;
        text-decoration: none;
    }

    a:hover { 
        text-decoration: underline; 
    }

    ul { 
        list-style-type: none;
        padding: 0;
    }

    li { 
        margin-bottom: 10px;
    }

    .newsletter-content {
        margin-top: 20px;
    }

    .download-link {
        display: inline-block;
        padding: 10px 20px;
        background-color: #2c3e50;
        color: white;
        border-radius: 3px;
        margin: 10px 0;
        font-family: Georgia, Times, serif;
    }

    .download-link:hover {
        background-color: #34495e;
        text-decoration: none;
    }
""")

app = FastHTML(hdrs=(css, MarkdownJS(),
                     HighlightJS(
                         langs=['python', 'javascript', 'html', 'css'])))


# Start the scheduler when the app starts
@app.on_event("startup")
async def start_scheduler():
  scheduler.start()


# Shut down the scheduler when the app stops
@app.on_event("shutdown")
async def shutdown_scheduler():
  scheduler.shutdown()


def get_newsletter_list():
  # Fetch the list of newsletters from the Hugging Face repository
  files = api.list_repo_files(repo_id=DATASET_NAME, repo_type="dataset")
  newsletters = [f for f in files if f.endswith('newsletter.json')]
  return sorted(newsletters, reverse=True)


def get_newsletter_content(path):
  # Download and parse the newsletter content
  content = api.hf_hub_download(repo_id=DATASET_NAME,
                                filename=path,
                                repo_type="dataset")
  with open(content, 'r') as f:
    return json.load(f)


@app.get("/")
def index():
  newsletters = get_newsletter_list()
  links = [
      Li(
          A(datetime.strptime(n.split('/')[0], '%Y%m%d').strftime('%B %d, %Y'),
            href=f"/newsletter/{n.split('/')[0]}")) for n in newsletters
  ]
  return Titled("This Week in Rheumatology", H2("Available Newsletters"),
                Ul(*links))


@app.get("/newsletter/{date}")
def newsletter(date: str):
  path = f"{date}/newsletter.json"
  pdf_path = f"{date}/newsletter.pdf"
  try:
    content = get_newsletter_content(path)
    return Titled(
        f"This Week in Rheumatology - {content['date']}",
        A("Back to Index", href="/"),
        Div(
        A("Download PDF", href=f"/download/{date}", cls="download-link")
        ),
        Div(content['content'], cls="marked"))
  except Exception as e:
    return Titled("Error", H2("Newsletter not found"),
                  P(f"Unable to load newsletter for date: {date}"),
                  A("Back to Index", href="/"))


@app.get("/download/{date}")
def download_pdf(date: str):
  try:
    pdf_path = f"{date}/newsletter.pdf"
    content = api.hf_hub_download(repo_id=DATASET_NAME,
                                  filename=pdf_path,
                                  repo_type="dataset")
    return FileResponse(content,
                        media_type="application/pdf",
                        filename=f"newsletter_{date}.pdf")
  except Exception as e:
    return Titled("Error", H2("PDF not found"),
                  P(f"Unable to load PDF for date: {date}"),
                  A("Back to Index", href="/"))

setup_hf_backup(app)
serve()