# -*- coding: utf-8 -*- # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License version 2 as # published by the Free Software Foundation. """Extractors for https://hatenablog.com""" from .common import Extractor, Message from .. import text BASE_PATTERN = ( r"(?:hatenablog:https?://([^/?#]+)|(?:https?://)?" r"([\w-]+\.(?:hatenablog\.(?:com|jp)" r"|hatenadiary\.com|hateblo\.jp)))" ) QUERY_RE = r"(?:\?([^#]*))?(?:#.*)?$" class HatenablogExtractor(Extractor): """Base class for HatenaBlog extractors""" category = "hatenablog" directory_fmt = ("{category}", "{domain}") filename_fmt = "{category}_{domain}_{entry}_{num:>02}.{extension}" archive_fmt = "{filename}" def __init__(self, match): Extractor.__init__(self, match) self.domain = match[1] or match[2] def _init(self): self._find_img = text.re(r']+)').finditer def _handle_article(self, article: str): extr = text.extract_from(article) date = self.parse_datetime_iso(extr('', '<')) content = extr( '

', '

') images = [] for match in self._find_img(content): attributes = match[1] if 'class="hatena-fotolife"' not in attributes: continue image = text.unescape(text.extr(attributes, 'src="', '"')) images.append(image) data = { "domain": self.domain, "date": date, "entry": entry, "title": title, "count": len(images), } yield Message.Directory, "", data for data["num"], url in enumerate(images, 1): yield Message.Url, url, text.nameext_from_url(url, data) class HatenablogEntriesExtractor(HatenablogExtractor): """Base class for a list of entries""" allowed_parameters = () def __init__(self, match): HatenablogExtractor.__init__(self, match) self.path = match[3] self.query = {key: value for key, value in text.parse_query( match[4]).items() if self._acceptable_query(key)} def _init(self): HatenablogExtractor._init(self) self._find_pager_url = text.re( r' class="pager-next">\s*') if "page-archive" in attributes: yield from self._handle_partial_articles(extr) else: yield from self._handle_full_articles(extr) match = self._find_pager_url(page) url = text.unescape(match[1]) if match else None query = None def _handle_partial_articles(self, extr): while True: section = extr('

') if not attributes: break if "no-entry" in attributes: continue article = extr('', '') yield from self._handle_article(article) def _acceptable_query(self, key): return key == "page" or key in self.allowed_parameters class HatenablogEntryExtractor(HatenablogExtractor): """Extractor for a single entry URL""" subcategory = "entry" pattern = BASE_PATTERN + r"/entry/([^?#]+)" + QUERY_RE example = "https://BLOG.hatenablog.com/entry/PATH" def __init__(self, match): HatenablogExtractor.__init__(self, match) self.path = match[3] def items(self): url = "https://" + self.domain + "/entry/" + self.path page = self.request(url).text extr = text.extract_from(page) while True: attributes = extr('

') if "no-entry" in attributes: continue article = extr('', '

') return self._handle_article(article) class HatenablogHomeExtractor(HatenablogEntriesExtractor): """Extractor for a blog's home page""" subcategory = "home" pattern = BASE_PATTERN + r"(/?)" + QUERY_RE example = "https://BLOG.hatenablog.com" class HatenablogArchiveExtractor(HatenablogEntriesExtractor): """Extractor for a blog's archive page""" subcategory = "archive" pattern = (BASE_PATTERN + r"(/archive(?:/\d+(?:/\d+(?:/\d+)?)?" r"|/category/[^?#]+)?)" + QUERY_RE) example = "https://BLOG.hatenablog.com/archive/2024" class HatenablogSearchExtractor(HatenablogEntriesExtractor): """Extractor for a blog's search results""" subcategory = "search" pattern = BASE_PATTERN + r"(/search)" + QUERY_RE example = "https://BLOG.hatenablog.com/search?q=QUERY" allowed_parameters = ("q",)