File size: 4,386 Bytes
5be97e9
638e4b7
7e4c8eb
 
638e4b7
 
41829e6
89e8c7a
638e4b7
 
 
 
8893ef9
 
 
638e4b7
5be97e9
528d174
638e4b7
 
 
 
 
 
 
 
 
 
7e4c8eb
 
5be97e9
 
638e4b7
40d72d0
638e4b7
8893ef9
638e4b7
8893ef9
 
 
 
 
 
 
 
5be97e9
8893ef9
638e4b7
8893ef9
 
 
 
 
 
 
 
638e4b7
8893ef9
 
41829e6
b93b826
41829e6
b93b826
 
41829e6
7ada18c
41829e6
 
40d72d0
b93b826
 
 
 
 
 
 
 
528d174
638e4b7
528d174
 
 
 
b93b826
 
40d72d0
638e4b7
 
41829e6
8893ef9
 
528d174
b93b826
528d174
 
 
 
 
 
 
 
 
 
 
 
 
8893ef9
528d174
b93b826
89e8c7a
638e4b7
7e4c8eb
5be97e9
 
 
 
528d174
5be97e9
 
 
 
 
eae8220
33f6f2c
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
# File: main.py

from fastapi import FastAPI, Query
from fastapi.responses import Response
import requests
import xml.etree.ElementTree as ET
from datetime import datetime
from typing import Optional

app = FastAPI()

# ========== FB2 Generator ==========
from bs4 import BeautifulSoup
from urllib.parse import quote

def html_to_fb2(title: str, body: str) -> str:
    clean_text = BeautifulSoup(body, "html.parser").get_text(separator="\n")
    return f"""<?xml version='1.0' encoding='utf-8'?>
<FictionBook xmlns:xlink='http://www.w3.org/1999/xlink'>
  <description>
    <title-info>
      <genre>nonfiction</genre>
      <author><first-name>OPDS</first-name><last-name>DuckScraper</last-name></author>
      <book-title>{title}</book-title>
      <lang>en</lang>
    </title-info>
  </description>
  <body>
    <section>
      <title><p>{title}</p></title>
      <p>{clean_text}</p>
    </section>
  </body>
</FictionBook>"""

# ========== DuckDuckGo JSON Search ==========
def duckduckgo_search(query: str):
    api_url = "https://api.duckduckgo.com/"
    params = {
        "q": query,
        "format": "json",
        "no_html": 1,
        "skip_disambig": 1
    }
    res = requests.get(api_url, params=params, headers={"User-Agent": "Mozilla/5.0"}, timeout=10)
    res.raise_for_status()
    data = res.json()
    results = []
    def extract_topics(topics):
        for item in topics:
            if "FirstURL" in item and "Text" in item:
                results.append((item["Text"], item["FirstURL"]))
            elif "Topics" in item:
                extract_topics(item["Topics"])
    extract_topics(data.get("RelatedTopics", []))
    return results[:10]

# ========== OPDS Feed Generator ==========
def create_feed(entries: list, q: Optional[str]) -> bytes:
    ns = "http://www.w3.org/2005/Atom"
    opds_ns = "http://opds-spec.org/2010/catalog"
    ET.register_namespace("", ns)
    ET.register_namespace("opds", opds_ns)

    feed = ET.Element("feed", xmlns=ns)
    ET.SubElement(feed, "id").text = "urn:uuid:duckopds-catalog"
    ET.SubElement(feed, "title").text = "DuckDuckGo OPDS Catalog"
    ET.SubElement(feed, "updated").text = datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ")

    if not q:
        ET.SubElement(feed, "link", {
            "rel": "search",
            "type": "application/atom+xml",
            "href": "/opds?q={searchTerms}",
            "templated": "true"
        })
    
    for entry_info in entries:
        entry = ET.SubElement(feed, "entry")
        ET.SubElement(entry, "id").text = entry_info['id']
        ET.SubElement(entry, "title").text = entry_info['title']
        ET.SubElement(entry, "updated").text = entry_info['updated']
        ET.SubElement(entry, "link", entry_info['link'])
        ET.SubElement(entry, "content", {"type": "text"}).text = entry_info['title']
        ET.SubElement(entry, "author").append(ET.Element("name", text="DuckOPDS"))

    return ET.tostring(feed, encoding="utf-8", xml_declaration=True)

# ========== Routes ==========
@app.get("/opds")
def opds(q: Optional[str] = Query(None, description="Search query")) -> Response:
    entries = []
    kind = "acquisition"
    if q:
        results = duckduckgo_search(q)
        for title, url in results:
            entries.append({
                'id': url,
                'title': title,
                'updated': datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ"),
                'link': {
                    'rel': 'http://opds-spec.org/acquisition',
                    'href': f"/download?url={quote(url, safe='')}",
                    'type': 'application/fb2+xml'
                }
            })
    xml_data = create_feed(entries, q)
    return Response(content=xml_data,
                    media_type="application/atom+xml;charset=utf-8")

@app.get("/download")
def download_fb2(url: str) -> Response:
    res = requests.get(url, headers={"User-Agent": "Mozilla/5.0"}, timeout=10)
    res.raise_for_status()
    soup = BeautifulSoup(res.text, "html.parser")
    title = soup.title.string.strip() if soup.title and soup.title.string else "article"
    fb2 = html_to_fb2(title, str(soup.body))
    filename = f"{quote(title, safe='').replace('%20','_')[:30]}.fb2"
    return Response(
        content=fb2,
        media_type="application/fb2+xml",
        headers={"Content-Disposition": f"attachment; filename={filename}"}
    )