Spaces:
Sleeping
Sleeping
Upload utils.py
Browse files
utils.py
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import re
|
| 2 |
+
from decimal import Decimal
|
| 3 |
+
from html import unescape
|
| 4 |
+
from math import atan2, cos, radians, sin, sqrt
|
| 5 |
+
from typing import Any, Dict, List, Union
|
| 6 |
+
from urllib.parse import unquote
|
| 7 |
+
import orjson
|
| 8 |
+
|
| 9 |
+
from .exceptions import WebscoutE
|
| 10 |
+
|
| 11 |
+
REGEX_STRIP_TAGS = re.compile("<.*?>")
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
def json_dumps(obj: Any) -> str:
|
| 15 |
+
try:
|
| 16 |
+
return orjson.dumps(obj).decode("utf-8")
|
| 17 |
+
except Exception as ex:
|
| 18 |
+
raise WebscoutE(f"{type(ex).__name__}: {ex}") from ex
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
def json_loads(obj: Union[str, bytes]) -> Any:
|
| 22 |
+
try:
|
| 23 |
+
return orjson.loads(obj)
|
| 24 |
+
except Exception as ex:
|
| 25 |
+
raise WebscoutE(f"{type(ex).__name__}: {ex}") from ex
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
def _extract_vqd(html_bytes: bytes, keywords: str) -> str:
|
| 29 |
+
"""Extract vqd from html bytes."""
|
| 30 |
+
for c1, c1_len, c2 in (
|
| 31 |
+
(b'vqd="', 5, b'"'),
|
| 32 |
+
(b"vqd=", 4, b"&"),
|
| 33 |
+
(b"vqd='", 5, b"'"),
|
| 34 |
+
):
|
| 35 |
+
try:
|
| 36 |
+
start = html_bytes.index(c1) + c1_len
|
| 37 |
+
end = html_bytes.index(c2, start)
|
| 38 |
+
return html_bytes[start:end].decode()
|
| 39 |
+
except ValueError:
|
| 40 |
+
pass
|
| 41 |
+
raise WebscoutE(f"_extract_vqd() {keywords=} Could not extract vqd.")
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
def _text_extract_json(html_bytes: bytes, keywords: str) -> List[Dict[str, str]]:
|
| 45 |
+
"""text(backend="api") -> extract json from html."""
|
| 46 |
+
try:
|
| 47 |
+
start = html_bytes.index(b"DDG.pageLayout.load('d',") + 24
|
| 48 |
+
end = html_bytes.index(b");DDG.duckbar.load(", start)
|
| 49 |
+
data = html_bytes[start:end]
|
| 50 |
+
result: List[Dict[str, str]] = json_loads(data)
|
| 51 |
+
return result
|
| 52 |
+
except Exception as ex:
|
| 53 |
+
raise WebscoutE(f"_text_extract_json() {keywords=} {type(ex).__name__}: {ex}") from ex
|
| 54 |
+
raise WebscoutE(f"_text_extract_json() {keywords=} return None")
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
def _normalize(raw_html: str) -> str:
|
| 58 |
+
"""Strip HTML tags from the raw_html string."""
|
| 59 |
+
return unescape(REGEX_STRIP_TAGS.sub("", raw_html)) if raw_html else ""
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
def _normalize_url(url: str) -> str:
|
| 63 |
+
"""Unquote URL and replace spaces with '+'."""
|
| 64 |
+
return unquote(url.replace(" ", "+")) if url else ""
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
def _calculate_distance(lat1: Decimal, lon1: Decimal, lat2: Decimal, lon2: Decimal) -> float:
|
| 68 |
+
"""Calculate distance between two points in km. Haversine formula."""
|
| 69 |
+
R = 6371.0087714 # Earth's radius in km
|
| 70 |
+
rlat1, rlon1, rlat2, rlon2 = map(radians, [float(lat1), float(lon1), float(lat2), float(lon2)])
|
| 71 |
+
dlon, dlat = rlon2 - rlon1, rlat2 - rlat1
|
| 72 |
+
a = sin(dlat / 2) ** 2 + cos(rlat1) * cos(rlat2) * sin(dlon / 2) ** 2
|
| 73 |
+
c = 2 * atan2(sqrt(a), sqrt(1 - a))
|
| 74 |
+
return R * c
|