"""
We Work Remotely (weworkremotely.com) scraper — public RSS feed.
One of the largest remote job boards. Good for WFH PM roles worldwide.
RSS endpoint requires no authentication.
"""
import logging
import xml.etree.ElementTree as ET
from .base import BaseScraper, Job

log = logging.getLogger("scraper.wwr")

_RSS_NAMESPACE = {
    "content": "http://purl.org/rss/1.0/modules/content/",
}


class WeWorkRemotelyScraper(BaseScraper):
    """Scrapes We Work Remotely via their public RSS search feed."""

    RSS_URL = "https://weworkremotely.com/remote-jobs/search.rss"

    def __init__(self):
        super().__init__("WeWorkRemotely")

    def search(self, role: str, location: str, max_results: int = 25) -> list:
        """Fetch PM jobs from the WWR RSS search feed."""
        params = {"term": role or "product manager"}
        resp = self._get(self.RSS_URL, params=params)
        if not resp:
            log.warning("WWR RSS returned no response")
            return []

        jobs = []
        try:
            root = ET.fromstring(resp.content)
            channel = root.find("channel")
            if channel is None:
                return []

            for item in channel.findall("item"):
                title_raw = _text(item, "title")
                url       = _text(item, "link") or _text(item, "guid")
                pub_date  = _text(item, "pubDate") or ""
                region    = _text(item, "region") or "Worldwide"

                # WWR title format: "Company Name: Job Title"
                if ": " in title_raw:
                    company_raw, job_title = title_raw.split(": ", 1)
                elif " at " in title_raw:
                    job_title, company_raw = title_raw.rsplit(" at ", 1)
                else:
                    job_title = title_raw
                    company_raw = ""

                job_title   = job_title.strip()
                company_raw = company_raw.strip()

                if not self.is_pm_role(job_title):
                    continue

                # Location filter: skip jobs explicitly for US/Europe only
                region_l = region.lower()
                loc_lower = location.lower()
                if loc_lower not in ("remote", "worldwide"):
                    blocked = ("usa", "us only", "europe", "uk", "canada", "australia")
                    if any(b in region_l for b in blocked) and "worldwide" not in region_l:
                        continue

                # Parse description from <description> (may contain HTML)
                raw_desc = _text(item, "description") or ""
                if raw_desc and "<" in raw_desc:
                    try:
                        from bs4 import BeautifulSoup
                        raw_desc = BeautifulSoup(raw_desc, "lxml").get_text(separator="\n", strip=True)
                    except Exception:
                        pass
                raw_desc = raw_desc[:3000]

                # Normalise the URL (WWR uses <guid> for the actual job URL)
                if not url or "weworkremotely.com" not in url:
                    guid = _text(item, "guid")
                    if guid and "weworkremotely" in guid:
                        url = guid

                jobs.append(Job(
                    title=job_title,
                    company=company_raw,
                    location=region or "Remote",
                    url=url or "",
                    platform="WeWorkRemotely",
                    description=raw_desc,
                    salary="Not specified",
                    posted_date=pub_date[:16] if pub_date else "",
                    job_id=(url or "").split("/")[-1],
                ))

                if len(jobs) >= max_results:
                    break

        except ET.ParseError as e:
            log.warning(f"WWR XML parse error: {e}")
        except Exception as e:
            log.warning(f"WWR scrape error: {e}", exc_info=True)

        log.info(f"WWR: {len(jobs)} PM jobs for role={role!r}")
        return jobs

    def get_details_bulk(self, jobs: list, progress_cb=None) -> None:
        """Descriptions already parsed from RSS — nothing to fetch."""
        if progress_cb:
            progress_cb(len(jobs), len(jobs))


def _text(el, tag: str) -> str:
    child = el.find(tag)
    return (child.text or "").strip() if child is not None else ""