Create duckopds/main.py
Browse files- duckopds/main.py +81 -0
duckopds/main.py
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# duckopds/main.py
|
| 2 |
+
|
| 3 |
+
from fastapi import FastAPI, Query, Response
|
| 4 |
+
from fastapi.responses import XMLResponse
|
| 5 |
+
import requests
|
| 6 |
+
from bs4 import BeautifulSoup
|
| 7 |
+
from urllib.parse import urlencode, quote
|
| 8 |
+
import xml.etree.ElementTree as ET
|
| 9 |
+
import re
|
| 10 |
+
|
| 11 |
+
app = FastAPI()
|
| 12 |
+
|
| 13 |
+
# ========== FB2 Generator ==========
|
| 14 |
+
def html_to_fb2(title: str, body: str) -> str:
|
| 15 |
+
clean_text = BeautifulSoup(body, "html.parser").get_text()
|
| 16 |
+
fb2 = f"""<?xml version='1.0' encoding='utf-8'?>
|
| 17 |
+
<FictionBook xmlns:xlink='http://www.w3.org/1999/xlink'>
|
| 18 |
+
<description>
|
| 19 |
+
<title-info>
|
| 20 |
+
<genre>nonfiction</genre>
|
| 21 |
+
<author><first-name>OPDS</first-name><last-name>DuckScraper</last-name></author>
|
| 22 |
+
<book-title>{title}</book-title>
|
| 23 |
+
<lang>en</lang>
|
| 24 |
+
</title-info>
|
| 25 |
+
</description>
|
| 26 |
+
<body>
|
| 27 |
+
<section><title><p>{title}</p></title><p>{clean_text}</p></section>
|
| 28 |
+
</body>
|
| 29 |
+
</FictionBook>
|
| 30 |
+
"""
|
| 31 |
+
return fb2
|
| 32 |
+
|
| 33 |
+
# ========== DuckDuckGo Search ==========
|
| 34 |
+
def duckduckgo_search(query: str):
|
| 35 |
+
res = requests.get("https://html.duckduckgo.com/html/", data={"q": query}, headers={"User-Agent": "Mozilla/5.0"})
|
| 36 |
+
soup = BeautifulSoup(res.text, "html.parser")
|
| 37 |
+
results = []
|
| 38 |
+
for a in soup.select("a.result__a"):
|
| 39 |
+
href = a.get("href")
|
| 40 |
+
title = a.get_text()
|
| 41 |
+
if href and title:
|
| 42 |
+
results.append((title.strip(), href))
|
| 43 |
+
if len(results) >= 10:
|
| 44 |
+
break
|
| 45 |
+
return results
|
| 46 |
+
|
| 47 |
+
# ========== OPDS Feed ==========
|
| 48 |
+
def generate_opds(query: str, results):
|
| 49 |
+
ns = "http://www.w3.org/2005/Atom"
|
| 50 |
+
ET.register_namespace("", ns)
|
| 51 |
+
feed = ET.Element("feed", xmlns=ns)
|
| 52 |
+
ET.SubElement(feed, "title").text = f"Search results for '{query}'"
|
| 53 |
+
for title, url in results:
|
| 54 |
+
entry = ET.SubElement(feed, "entry")
|
| 55 |
+
ET.SubElement(entry, "title").text = title
|
| 56 |
+
ET.SubElement(entry, "id").text = url
|
| 57 |
+
ET.SubElement(entry, "updated").text = "2025-07-31T12:00:00Z"
|
| 58 |
+
ET.SubElement(entry, "link", {
|
| 59 |
+
"rel": "http://opds-spec.org/acquisition",
|
| 60 |
+
"href": f"/download?url={quote(url)}",
|
| 61 |
+
"type": "application/fb2+xml"
|
| 62 |
+
})
|
| 63 |
+
return ET.tostring(feed, encoding="utf-8", xml_declaration=True)
|
| 64 |
+
|
| 65 |
+
@app.get("/opds", response_class=XMLResponse)
|
| 66 |
+
def opds_catalog(q: str = Query(..., description="Search query")):
|
| 67 |
+
results = duckduckgo_search(q)
|
| 68 |
+
xml_data = generate_opds(q, results)
|
| 69 |
+
return Response(content=xml_data, media_type="application/atom+xml")
|
| 70 |
+
|
| 71 |
+
@app.get("/download")
|
| 72 |
+
def download_fb2(url: str):
|
| 73 |
+
try:
|
| 74 |
+
res = requests.get(url, headers={"User-Agent": "Mozilla/5.0"}, timeout=10)
|
| 75 |
+
soup = BeautifulSoup(res.text, "html.parser")
|
| 76 |
+
title = soup.title.string if soup.title else "No Title"
|
| 77 |
+
body = str(soup.body)
|
| 78 |
+
fb2 = html_to_fb2(title, body)
|
| 79 |
+
return Response(content=fb2, media_type="application/fb2+xml", headers={"Content-Disposition": f"attachment; filename={re.sub(r'[^a-zA-Z0-9]+', '_', title)[:30]}.fb2"})
|
| 80 |
+
except Exception as e:
|
| 81 |
+
return {"error": str(e)}
|