"""Baidu HTML scraping engine — free, fastest in China, best Chinese results."""
from __future__ import annotations
import time
import logging
from urllib.parse import quote_plus
import httpx
from bs4 import BeautifulSoup
from scripts.engines.base import BaseEngine, EngineResult
logger = logging.getLogger(__name__)
HEADERS = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
"(KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
"Accept-Language": "zh-CN,zh;q=0.9",
}
class BaiduScraper(BaseEngine):
"""Baidu web scraping — fastest in China, best Chinese content."""
name = "baidu"
async def search(self, query: str, max_results: int = 10,
**kwargs) -> list[EngineResult]:
t0 = time.time()
url = f"https://www.baidu.com/s?wd={quote_plus(query)}&rn={max_results}"
try:
async with httpx.AsyncClient(timeout=self.timeout, follow_redirects=True) as client:
resp = await client.get(url, headers=HEADERS)
resp.raise_for_status()
elapsed = time.time() - t0
results = self._parse(resp.text, max_results)
logger.info(f"[baidu] {len(results)} results in {elapsed:.2f}s")
return results
except Exception as e:
logger.warning(f"[baidu] failed: {e}")
return []
def _parse(self, html: str, max_results: int) -> list[EngineResult]:
soup = BeautifulSoup(html, "html.parser")
results = []
for item in soup.select("div.result, div.c-container"):
title_el = item.select_one("h3 a")
if not title_el:
continue
title = title_el.get_text(strip=True)
href = title_el.get("href", "")
snippet_el = item.select_one(
"span.content-right_8Zs40, div.c-abstract, "
"span[class*='content'], div[class*='abstract']"
)
snippet = snippet_el.get_text(strip=True) if snippet_el else ""
if title and href:
results.append(EngineResult(
title=title, url=href, snippet=snippet, source="baidu",
))
if len(results) >= max_results:
break
return results