import json import re from urllib.parse import quote, urljoin, urlparse, urlunparse from bs4 import BeautifulSoup from .decoder import base64_decode_text from .models import Category, ResolvedTrack, Track RANK_LINKS = { "\u65e5\u699c": "index-0-5.htm", "\u5468\u699c": "index-0-4.htm", "\u6708\u699c": "index-0-3.htm", } FORUM_NAMES = { "\u534e\u8bed", "\u6b27\u7f8e", "\u65e5\u97e9", "Remix", "\u7eaf\u97f3\u4e50", } def extract_categories(html: str, base_url: str) -> list[Category]: soup = BeautifulSoup(html, "html.parser") categories: list[Category] = [] seen: set[tuple[str, str]] = set() for name in ("\u65e5\u699c", "\u5468\u699c", "\u6708\u699c"): href = RANK_LINKS[name] categories.append(Category(name=name, url=urljoin(base_url, href), kind="rank")) seen.add((name, "rank")) for link in soup.select('a[href^="forum-"]'): name = link.get_text(" ", strip=True) if not name or name not in FORUM_NAMES: alt = link.select_one("img[alt]") name = (alt.get("alt", "") if alt else "").replace("\u56fe\u6807", "").strip() href = link.get("href", "") key = (name, "forum") if name in FORUM_NAMES and href and key not in seen: categories.append(Category(name=name, url=urljoin(base_url, href), kind="forum")) seen.add(key) return categories def infer_rank_page_links(url: str, base_url: str) -> tuple[str | None, str | None]: match = re.search(r"(?:^|/)index-(\d+)-([345])\.htm$", urlparse(url).path) if not match: return None, None page = int(match.group(1)) rank = match.group(2) previous_url = urljoin(base_url, f"index-{page - 1}-{rank}.htm") if page > 0 else None next_url = urljoin(base_url, f"index-{page + 1}-{rank}.htm") return previous_url, next_url def extract_tracks(html: str, base_url: str) -> list[Track]: soup = BeautifulSoup(html, "html.parser") tracks: list[Track] = [] seen: set[str] = set() for link in soup.select('a[href^="thread-"]'): href = link.get("href", "") title = link.get_text(" ", strip=True) if not href or not title or "#comments" in href: continue if not re.match(r"^thread-\d+\.htm$", href): continue url = urljoin(base_url, href) if url in seen: continue seen.add(url) container = link.find_parent(attrs={"data-tid": True}) category_link = container.select_one('a[href^="forum-"]') if container else None category = category_link.get_text(" ", strip=True) if category_link else None tracks.append(Track(title=title, url=url, category=category)) return tracks def extract_page_links(html: str, base_url: str) -> tuple[str | None, str | None]: soup = BeautifulSoup(html, "html.parser") pagination = soup.select_one(".pagination") if not pagination: return None, None active = pagination.select_one(".page-item.active .page-link") active_page = int(active.get_text(strip=True)) if active and active.get_text(strip=True).isdigit() else None numeric_pages: dict[int, str] = {} previous_url: str | None = None next_url: str | None = None for link in pagination.select("a.page-link[href]"): text = link.get_text(strip=True) href = link.get("href", "") if not href: continue absolute = urljoin(base_url, href) if text.isdigit(): numeric_pages[int(text)] = absolute elif text in {"<", "<", "\u2190", "\u25c0", "\u4e0a\u4e00\u9875"}: previous_url = absolute elif text in {">", ">", "\u2192", "\u25b6", "\u4e0b\u4e00\u9875"}: next_url = absolute if active_page is not None: previous_url = previous_url or numeric_pages.get(active_page - 1) next_url = next_url or numeric_pages.get(active_page + 1) return previous_url, next_url def extract_lyrics(html: str) -> str | None: soup = BeautifulSoup(html, "html.parser") heading = soup.find(lambda tag: tag.name in {"h4", "h5"} and "\u6b4c\u8bcd" in tag.get_text(" ", strip=True)) if not heading: return None lines: list[str] = [] for sibling in heading.find_next_siblings(): if sibling.name in {"h4", "h5"}: break text = sibling.get_text(" ", strip=True) if text: lines.append(text) return "\n".join(lines) if lines else None def extract_album(html: str) -> str | None: soup = BeautifulSoup(html, "html.parser") for label in soup.find_all(string=re.compile("\u4e13\u8f91")): parent = label.parent if parent: text = parent.get_text(" ", strip=True) match = re.search(r"\u4e13\u8f91[:?]\s*(.+)", text) if match: return match.group(1).strip() return None def _quote_url_path(url: str) -> str: parsed = urlparse(url) return urlunparse(parsed._replace(path=quote(parsed.path))) def _title_artist_from_page(html: str) -> tuple[str, str]: soup = BeautifulSoup(html, "html.parser") heading = soup.select_one("h1") raw_title = heading.get_text(" ", strip=True) if heading else "" if not raw_title and soup.title: raw_title = soup.title.get_text(" ", strip=True).split("\u4e0b\u8f7d", 1)[0] if " - " in raw_title: artist, title = raw_title.split(" - ", 1) return title.strip(), artist.strip() return raw_title.strip(), "" def extract_legacy_aplayer_track(html: str, thread_url: str) -> ResolvedTrack: match = re.search(r"url\s*:\s*base64_decode\([\"']([^\"']+)[\"']\)", html) if not match: raise ValueError("legacy APlayer url not found") decoded_url = base64_decode_text(match.group(1)) absolute_url = _quote_url_path(urljoin(thread_url, decoded_url)) pic_match = re.search(r"pic\s*:\s*[\"']([^\"']+)[\"']", html) cover = urljoin(thread_url, pic_match.group(1)) if pic_match else None title, artist = _title_artist_from_page(html) return ResolvedTrack(title=title, artist=artist, url=absolute_url, cover=cover, album=extract_album(html), lyrics=extract_lyrics(html)) def extract_music_tags(html: str) -> list[dict[str, str]]: match = re.search(r"const\s+musicTags\s*=\s*(\[[\s\S]*?\])\s*;", html) if not match: raise ValueError("musicTags not found") return json.loads(match.group(1))