Update main.py
Browse files
main.py
CHANGED
@@ -14,7 +14,7 @@ app = FastAPI()
|
|
14 |
# ========== FB2 Generator ==========
|
15 |
def html_to_fb2(title: str, body: str) -> str:
|
16 |
clean_text = BeautifulSoup(body, "html.parser").get_text(separator="\n")
|
17 |
-
|
18 |
<FictionBook xmlns:xlink='http://www.w3.org/1999/xlink'>
|
19 |
<description>
|
20 |
<title-info>
|
@@ -30,8 +30,7 @@ def html_to_fb2(title: str, body: str) -> str:
|
|
30 |
<p>{clean_text}</p>
|
31 |
</section>
|
32 |
</body>
|
33 |
-
</FictionBook>"""
|
34 |
-
return fb2
|
35 |
|
36 |
# ========== DuckDuckGo Search ==========
|
37 |
def duckduckgo_search(query: str):
|
@@ -53,114 +52,71 @@ def duckduckgo_search(query: str):
|
|
53 |
break
|
54 |
return results
|
55 |
|
56 |
-
# ========== OPDS Feed
|
57 |
-
def
|
58 |
ns = "http://www.w3.org/2005/Atom"
|
59 |
ET.register_namespace("", ns)
|
60 |
feed = ET.Element("feed", xmlns=ns)
|
61 |
ET.SubElement(feed, "id").text = "urn:uuid:duckopds-catalog"
|
62 |
ET.SubElement(feed, "title").text = "DuckDuckGo OPDS Catalog"
|
63 |
ET.SubElement(feed, "updated").text = datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ")
|
64 |
-
|
65 |
-
# Entry: Search Section
|
66 |
-
entry_search = ET.SubElement(feed, "entry")
|
67 |
-
ET.SubElement(entry_search, "id").text = "urn:uuid:duckopds-search-section"
|
68 |
-
ET.SubElement(entry_search, "title").text = "Search"
|
69 |
-
ET.SubElement(entry_search, "updated").text = datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ")
|
70 |
-
ET.SubElement(entry_search, "link", {
|
71 |
-
"rel": "subsection",
|
72 |
-
"href": "/opds/search",
|
73 |
-
"type": "application/atom+xml;profile=opds-catalog;kind=acquisition"
|
74 |
-
})
|
75 |
-
|
76 |
-
# Entry: Cached Section
|
77 |
-
entry_cached = ET.SubElement(feed, "entry")
|
78 |
-
ET.SubElement(entry_cached, "id").text = "urn:uuid:duckopds-cached-section"
|
79 |
-
ET.SubElement(entry_cached, "title").text = "Cached"
|
80 |
-
ET.SubElement(entry_cached, "updated").text = datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ")
|
81 |
-
ET.SubElement(entry_cached, "link", {
|
82 |
-
"rel": "subsection",
|
83 |
-
"href": "/opds/cached",
|
84 |
-
"type": "application/atom+xml;profile=opds-catalog;kind=navigation"
|
85 |
-
})
|
86 |
-
|
87 |
-
return ET.tostring(feed, encoding="utf-8", xml_declaration=True)
|
88 |
-
|
89 |
-
|
90 |
-
def generate_search_form_feed():
|
91 |
-
ns = "http://www.w3.org/2005/Atom"
|
92 |
-
ET.register_namespace("", ns)
|
93 |
-
feed = ET.Element("feed", xmlns=ns)
|
94 |
-
ET.SubElement(feed, "id").text = "urn:uuid:duckopds-search-form"
|
95 |
-
ET.SubElement(feed, "title").text = "Search"
|
96 |
-
ET.SubElement(feed, "updated").text = datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ")
|
97 |
-
# Templated search link
|
98 |
-
feed.append(ET.Element("link", {
|
99 |
-
"rel": "search",
|
100 |
-
"type": "application/atom+xml;profile=opds-catalog;kind=acquisition",
|
101 |
-
"href": "/opds/search?q={searchTerms}",
|
102 |
-
"templated": "true"
|
103 |
-
}))
|
104 |
-
return ET.tostring(feed, encoding="utf-8", xml_declaration=True)
|
105 |
-
|
106 |
-
|
107 |
-
def generate_search_results_feed(query: str, results):
|
108 |
-
ns = "http://www.w3.org/2005/Atom"
|
109 |
-
ET.register_namespace("", ns)
|
110 |
-
feed = ET.Element("feed", xmlns=ns)
|
111 |
-
ET.SubElement(feed, "id").text = f"urn:uuid:duckopds-search-{quote(query)}"
|
112 |
-
ET.SubElement(feed, "title").text = f"Search results for '{query}'"
|
113 |
-
ET.SubElement(feed, "updated").text = datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ")
|
114 |
-
for title, url in results:
|
115 |
entry = ET.SubElement(feed, "entry")
|
116 |
-
ET.SubElement(entry, "id").text =
|
117 |
-
ET.SubElement(entry, "title").text = title
|
118 |
-
ET.SubElement(entry, "updated").text =
|
119 |
-
ET.SubElement(entry, "link",
|
120 |
-
"rel": "http://opds-spec.org/acquisition",
|
121 |
-
"href": f"/download?url={quote(url, safe='')}",
|
122 |
-
"type": "application/fb2+xml"
|
123 |
-
})
|
124 |
return ET.tostring(feed, encoding="utf-8", xml_declaration=True)
|
125 |
|
126 |
# ========== Routes ==========
|
127 |
@app.get("/opds", include_in_schema=False)
|
128 |
-
def
|
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 |
@app.get("/download")
|
166 |
def download_fb2(url: str) -> Response:
|
@@ -168,8 +124,7 @@ def download_fb2(url: str) -> Response:
|
|
168 |
res.raise_for_status()
|
169 |
soup = BeautifulSoup(res.text, "html.parser")
|
170 |
title = soup.title.string.strip() if soup.title and soup.title.string else "article"
|
171 |
-
|
172 |
-
fb2 = html_to_fb2(title, body)
|
173 |
filename = f"{quote(title, safe='').replace('%20','_')[:30]}.fb2"
|
174 |
return Response(
|
175 |
content=fb2,
|
|
|
14 |
# ========== FB2 Generator ==========
|
15 |
def html_to_fb2(title: str, body: str) -> str:
|
16 |
clean_text = BeautifulSoup(body, "html.parser").get_text(separator="\n")
|
17 |
+
return f"""<?xml version='1.0' encoding='utf-8'?>
|
18 |
<FictionBook xmlns:xlink='http://www.w3.org/1999/xlink'>
|
19 |
<description>
|
20 |
<title-info>
|
|
|
30 |
<p>{clean_text}</p>
|
31 |
</section>
|
32 |
</body>
|
33 |
+
</FictionBook>"""
|
|
|
34 |
|
35 |
# ========== DuckDuckGo Search ==========
|
36 |
def duckduckgo_search(query: str):
|
|
|
52 |
break
|
53 |
return results
|
54 |
|
55 |
+
# ========== OPDS Feed Generator ==========
|
56 |
+
def generate_feed(entries):
|
57 |
ns = "http://www.w3.org/2005/Atom"
|
58 |
ET.register_namespace("", ns)
|
59 |
feed = ET.Element("feed", xmlns=ns)
|
60 |
ET.SubElement(feed, "id").text = "urn:uuid:duckopds-catalog"
|
61 |
ET.SubElement(feed, "title").text = "DuckDuckGo OPDS Catalog"
|
62 |
ET.SubElement(feed, "updated").text = datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ")
|
63 |
+
for entry_info in entries:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
64 |
entry = ET.SubElement(feed, "entry")
|
65 |
+
ET.SubElement(entry, "id").text = entry_info['id']
|
66 |
+
ET.SubElement(entry, "title").text = entry_info['title']
|
67 |
+
ET.SubElement(entry, "updated").text = entry_info['updated']
|
68 |
+
ET.SubElement(entry, "link", entry_info['link'])
|
|
|
|
|
|
|
|
|
69 |
return ET.tostring(feed, encoding="utf-8", xml_declaration=True)
|
70 |
|
71 |
# ========== Routes ==========
|
72 |
@app.get("/opds", include_in_schema=False)
|
73 |
+
def root_opds() -> Response:
|
74 |
+
# Only search section
|
75 |
+
entries = [{
|
76 |
+
'id': 'urn:uuid:duckopds-search-section',
|
77 |
+
'title': 'Search',
|
78 |
+
'updated': datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ"),
|
79 |
+
'link': {
|
80 |
+
'rel': 'subsection',
|
81 |
+
'href': '/opds', # self endpoint handles search form if no q
|
82 |
+
'type': 'application/atom+xml;profile=opds-catalog;kind=search'
|
83 |
+
}
|
84 |
+
}]
|
85 |
+
xml_data = generate_feed(entries)
|
86 |
+
return Response(content=xml_data,
|
87 |
+
media_type="application/atom+xml;profile=opds-catalog;kind=navigation")
|
88 |
+
|
89 |
+
@app.get("/opds")
|
90 |
+
def opds_search(q: Optional[str] = Query(None, description="Search query")) -> Response:
|
91 |
+
entries = []
|
92 |
+
# Always include search entry at top
|
93 |
+
entries.append({
|
94 |
+
'id': 'urn:uuid:duckopds-search-section',
|
95 |
+
'title': 'Search',
|
96 |
+
'updated': datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ"),
|
97 |
+
'link': {
|
98 |
+
'rel': 'subsection',
|
99 |
+
'href': '/opds',
|
100 |
+
'type': 'application/atom+xml;profile=opds-catalog;kind=search'
|
101 |
+
}
|
102 |
+
})
|
103 |
+
if q:
|
104 |
+
results = duckduckgo_search(q)
|
105 |
+
for title, url in results:
|
106 |
+
entries.append({
|
107 |
+
'id': url,
|
108 |
+
'title': title,
|
109 |
+
'updated': datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ"),
|
110 |
+
'link': {
|
111 |
+
'rel': 'http://opds-spec.org/acquisition',
|
112 |
+
'href': f"/download?url={quote(url, safe='')}",
|
113 |
+
'type': 'application/fb2+xml'
|
114 |
+
}
|
115 |
+
})
|
116 |
+
xml_data = generate_feed(entries)
|
117 |
+
kind = 'acquisition' if q else 'search'
|
118 |
+
return Response(content=xml_data,
|
119 |
+
media_type=f"application/atom+xml;profile=opds-catalog;kind={kind}")
|
120 |
|
121 |
@app.get("/download")
|
122 |
def download_fb2(url: str) -> Response:
|
|
|
124 |
res.raise_for_status()
|
125 |
soup = BeautifulSoup(res.text, "html.parser")
|
126 |
title = soup.title.string.strip() if soup.title and soup.title.string else "article"
|
127 |
+
fb2 = html_to_fb2(title, str(soup.body))
|
|
|
128 |
filename = f"{quote(title, safe='').replace('%20','_')[:30]}.fb2"
|
129 |
return Response(
|
130 |
content=fb2,
|