File size: 6,649 Bytes
8840360 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 |
import requests
from bs4 import BeautifulSoup
import json
import os
import time
import warnings
from fastapi import FastAPI, HTTPException
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import FileResponse
from fastapi.staticfiles import StaticFiles
from pydantic import BaseModel
from typing import Dict, List, Optional
import uvicorn
warnings.filterwarnings("ignore")
app = FastAPI(title="3GPP Document Finder API",
description="API to find 3GPP documents based on TSG document IDs")
app.mount("/static", StaticFiles(directory="static"), name="static")
origins = [
"*",
]
app.add_middleware(
CORSMiddleware,
allow_origins=origins,
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
class DocRequest(BaseModel):
tsg_doc_id: str
class DocResponse(BaseModel):
tsg_doc_id: str
url: str
search_time: float
class BatchDocRequest(BaseModel):
tsg_doc_ids: List[str]
class BatchDocResponse(BaseModel):
results: Dict[str, str]
missing: List[str]
search_time: float
class TsgDocFinder:
def __init__(self):
self.main_ftp_url = "https://www.3gpp.org/ftp"
self.indexer_file = "indexed_docs.json"
self.indexer = self.load_indexer()
def load_indexer(self):
"""Load existing index if available"""
if os.path.exists(self.indexer_file):
with open(self.indexer_file, "r", encoding="utf-8") as f:
return json.load(f)
return {}
def save_indexer(self):
"""Save the updated index"""
with open(self.indexer_file, "w", encoding="utf-8") as f:
json.dump(self.indexer, f, indent=4, ensure_ascii=False)
def get_workgroup(self, tsg_doc):
main_tsg = "tsg_ct" if tsg_doc[0] == "C" else "tsg_sa" if tsg_doc[0] == "S" else None
if main_tsg is None:
return None, None, None
workgroup = f"WG{int(tsg_doc[1])}" if tsg_doc[1].isnumeric() else main_tsg.upper()
return main_tsg, workgroup, tsg_doc
def find_workgroup_url(self, main_tsg, workgroup):
"""Find the URL for the specific workgroup"""
response = requests.get(f"{self.main_ftp_url}/{main_tsg}", verify=False)
soup = BeautifulSoup(response.text, 'html.parser')
for item in soup.find_all("tr"):
link = item.find("a")
if link and workgroup in link.get_text():
return f"{self.main_ftp_url}/{main_tsg}/{link.get_text()}"
return f"{self.main_ftp_url}/{main_tsg}/{workgroup}"
def get_docs_from_url(self, url):
"""Get list of documents/directories from a URL"""
try:
response = requests.get(url, verify=False, timeout=10)
soup = BeautifulSoup(response.text, "html.parser")
return [item.get_text() for item in soup.select("tr td a")]
except Exception as e:
print(f"Error accessing {url}: {e}")
return []
def search_document(self, tsg_doc_id):
"""Search for a specific document by its ID"""
original_id = tsg_doc_id
# Check if already indexed
if original_id in self.indexer:
return self.indexer[original_id]
# Parse the document ID
main_tsg, workgroup, tsg_doc = self.get_workgroup(tsg_doc_id)
if not main_tsg:
return f"Could not parse document ID: {tsg_doc_id}"
print(f"Searching for {original_id} (parsed as {tsg_doc}) in {main_tsg}/{workgroup}...")
# Find the workgroup URL
wg_url = self.find_workgroup_url(main_tsg, workgroup)
if not wg_url:
return f"Could not find workgroup for {tsg_doc_id}"
# Search in the workgroup directories
meeting_folders = self.get_docs_from_url(wg_url)
for folder in meeting_folders:
meeting_url = f"{wg_url}/{folder}"
meeting_contents = self.get_docs_from_url(meeting_url)
if "Docs" in meeting_contents:
docs_url = f"{meeting_url}/Docs"
print(f"Checking {docs_url}...")
files = self.get_docs_from_url(docs_url)
# Check for the document in the main Docs folder
for file in files:
if tsg_doc in file.lower() or original_id in file:
doc_url = f"{docs_url}/{file}"
self.indexer[original_id] = doc_url
self.save_indexer()
return doc_url
# Check in ZIP subfolder if it exists
if "ZIP" in files:
zip_url = f"{docs_url}/ZIP"
print(f"Checking {zip_url}...")
zip_files = self.get_docs_from_url(zip_url)
for file in zip_files:
if tsg_doc in file.lower() or original_id in file:
doc_url = f"{zip_url}/{file}"
self.indexer[original_id] = doc_url
self.save_indexer()
return doc_url
return f"Document {tsg_doc_id} not found"
# Create a global instance of the finder
finder = TsgDocFinder()
@app.get("/")
async def main_menu():
return FileResponse(os.path.join("templates", "index.html"))
@app.post("/find", response_model=DocResponse)
def find_document(request: DocRequest):
start_time = time.time()
result = finder.search_document(request.tsg_doc_id)
if "not found" not in result and "Could not" not in result:
return DocResponse(
tsg_doc_id=request.tsg_doc_id,
url=result,
search_time=time.time() - start_time
)
else:
raise HTTPException(status_code=404, detail=result)
@app.post("/batch", response_model=BatchDocResponse)
def find_documents_batch(request: BatchDocRequest):
start_time = time.time()
results = {}
missing = []
for doc_id in request.tsg_doc_ids:
result = finder.search_document(doc_id)
if "not found" not in result and "Could not" not in result:
results[doc_id] = result
else:
missing.append(doc_id)
return BatchDocResponse(
results=results,
missing=missing,
search_time=time.time() - start_time
)
@app.get("/indexed", response_model=List[str])
def get_indexed_documents():
return list(finder.indexer.keys())
|