166a885fb9
- macro_thai.py scrapes bot.or.th/en/thai-economy.html (server-rendered, no auth) - private consumption +4.9%, private investment +18.1%, mfg -3.1%, headline inflation 1.95%, core 1.34%, unemployment 0.93%, tourists YTD 16.2mn - 3 tests; live verified; macro backdrop layer (req #6)
133 lines
4.8 KiB
Python
133 lines
4.8 KiB
Python
"""Thai macro backdrop factor — BOT Thai Economy overview page.
|
|
|
|
Source: https://www.bot.or.th/en/thai-economy.html (server-rendered HTML).
|
|
Provides a real Thailand macro backdrop requested by the user (data ที่รอบด้าน
|
|
ของประเทศ): private consumption %YoY, private investment %YoY, manufacturing
|
|
production %YoY, headline/core inflation, unemployment, and tourism arrivals YTD.
|
|
|
|
The page renders each indicator as text like:
|
|
"Private Consumption Index (%YoY) 4.9% Jun 2026"
|
|
so we locate the label and grab the following percent + period.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import html
|
|
import re
|
|
from dataclasses import dataclass, field
|
|
from typing import Optional
|
|
from urllib.request import Request, urlopen
|
|
|
|
_USER_AGENT = (
|
|
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 "
|
|
"(KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
|
|
)
|
|
_URL = "https://www.bot.or.th/en/thai-economy.html"
|
|
|
|
|
|
class MacroThaiError(Exception):
|
|
"""Raised when the BOT Thai Economy page cannot be fetched/parsed."""
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class MacroThaiSnapshot:
|
|
private_consumption_yoy: Optional[float] = None
|
|
private_investment_yoy: Optional[float] = None
|
|
manufacturing_yoy: Optional[float] = None
|
|
headline_inflation_yoy: Optional[float] = None
|
|
core_inflation_yoy: Optional[float] = None
|
|
unemployment_pct: Optional[float] = None
|
|
tourists_ytd_mn: Optional[float] = None
|
|
periods: dict = field(default_factory=dict)
|
|
source: str = "bot.thai-economy"
|
|
|
|
def to_dict(self) -> dict:
|
|
return {
|
|
"source": self.source,
|
|
"private_consumption_yoy": self.private_consumption_yoy,
|
|
"private_investment_yoy": self.private_investment_yoy,
|
|
"manufacturing_yoy": self.manufacturing_yoy,
|
|
"headline_inflation_yoy": self.headline_inflation_yoy,
|
|
"core_inflation_yoy": self.core_inflation_yoy,
|
|
"unemployment_pct": self.unemployment_pct,
|
|
"tourists_ytd_mn": self.tourists_ytd_mn,
|
|
"periods": self.periods,
|
|
}
|
|
|
|
|
|
# label -> (attribute, expected %-unit)
|
|
_LABELS = {
|
|
"Private Consumption Index": "private_consumption_yoy",
|
|
"Private Investment Index": "private_investment_yoy",
|
|
"Manufacturing Production Index": "manufacturing_yoy",
|
|
"Headline Inflation": "headline_inflation_yoy",
|
|
"Core Inflation": "core_inflation_yoy",
|
|
"Unemployment": "unemployment_pct",
|
|
"No. of tourists year-to-date": "tourists_ytd_mn",
|
|
}
|
|
|
|
|
|
def _fetch(url: str = _URL, timeout: float = 30.0) -> str:
|
|
req = Request(url, headers={"User-Agent": _USER_AGENT, "Accept": "text/html"})
|
|
try:
|
|
with urlopen(req, timeout=timeout) as resp:
|
|
raw = resp.read()
|
|
except Exception as exc:
|
|
raise MacroThaiError(f"failed to fetch {url}: {exc}") from exc
|
|
try:
|
|
return raw.decode("utf-8")
|
|
except UnicodeDecodeError:
|
|
return raw.decode("latin-1", "ignore")
|
|
|
|
|
|
def _plain(text: str) -> str:
|
|
return re.sub(r"\s+", " ", html.unescape(re.sub(r"<[^>]+>", "", text))).strip()
|
|
|
|
|
|
def _to_pct(text: str) -> Optional[float]:
|
|
m = re.search(r"([-+]?\d+(?:\.\d+)?)\s*%", text)
|
|
return float(m.group(1)) if m else None
|
|
|
|
|
|
def _has_number(text: str) -> bool:
|
|
return bool(re.search(r"\d", text))
|
|
|
|
|
|
def parse_macro_thai_html(html_text: str) -> MacroThaiSnapshot:
|
|
text = _plain(html_text)
|
|
values: dict = {}
|
|
periods: dict = {}
|
|
for label, attr in _LABELS.items():
|
|
idx = text.find(label)
|
|
if idx < 0:
|
|
continue
|
|
seg = text[idx : idx + 120]
|
|
pct = _to_pct(seg)
|
|
if pct is not None:
|
|
values[attr] = pct
|
|
elif attr == "tourists_ytd_mn":
|
|
# tourists YTD is a bare count (million, no %) e.g. "16.2"
|
|
m = re.search(r"([-+]?\d+(?:\.\d+)?)", seg)
|
|
if m:
|
|
values[attr] = float(m.group(1))
|
|
# period: e.g. "Jun 2026" / "Q1/2026" following the number
|
|
m = re.search(r"(?:\d+(?:\.\d+)?\s*%?\s*)?([A-Z][a-z]{2}/\d{4}|[A-Z][a-z]{2}\s\d{4}|Q\d/\d{4})", seg)
|
|
if m:
|
|
periods[attr] = m.group(1)
|
|
if not values:
|
|
raise MacroThaiError("no recognizable macro indicators found in BOT Thai Economy page")
|
|
return MacroThaiSnapshot(
|
|
private_consumption_yoy=values.get("private_consumption_yoy"),
|
|
private_investment_yoy=values.get("private_investment_yoy"),
|
|
manufacturing_yoy=values.get("manufacturing_yoy"),
|
|
headline_inflation_yoy=values.get("headline_inflation_yoy"),
|
|
core_inflation_yoy=values.get("core_inflation_yoy"),
|
|
unemployment_pct=values.get("unemployment_pct"),
|
|
tourists_ytd_mn=values.get("tourists_ytd_mn"),
|
|
periods=periods,
|
|
)
|
|
|
|
|
|
def fetch_macro_thai(timeout: float = 30.0) -> MacroThaiSnapshot:
|
|
return parse_macro_thai_html(_fetch(timeout=timeout))
|