diff options
Diffstat (limited to 'gallery_dl/extractor/hatenablog.py')
| -rw-r--r-- | gallery_dl/extractor/hatenablog.py | 20 |
1 files changed, 10 insertions, 10 deletions
diff --git a/gallery_dl/extractor/hatenablog.py b/gallery_dl/extractor/hatenablog.py index 8e350d6..7065d7b 100644 --- a/gallery_dl/extractor/hatenablog.py +++ b/gallery_dl/extractor/hatenablog.py @@ -7,7 +7,7 @@ """Extractors for https://hatenablog.com""" from .common import Extractor, Message -from .. import text, util +from .. import text BASE_PATTERN = ( @@ -30,11 +30,11 @@ class HatenablogExtractor(Extractor): self.domain = match[1] or match[2] def _init(self): - self._find_img = util.re(r'<img +([^>]+)').finditer + self._find_img = text.re(r'<img +([^>]+)').finditer def _handle_article(self, article: str): extr = text.extract_from(article) - date = text.parse_datetime(extr('<time datetime="', '"')) + date = self.parse_datetime_iso(extr('<time datetime="', '"')) entry_link = text.unescape(extr('<a href="', '"')) entry = entry_link.partition("/entry/")[2] title = text.unescape(extr('>', '<')) @@ -56,7 +56,7 @@ class HatenablogExtractor(Extractor): "title": title, "count": len(images), } - yield Message.Directory, data + yield Message.Directory, "", data for data["num"], url in enumerate(images, 1): yield Message.Url, url, text.nameext_from_url(url, data) @@ -73,7 +73,7 @@ class HatenablogEntriesExtractor(HatenablogExtractor): def _init(self): HatenablogExtractor._init(self) - self._find_pager_url = util.re( + self._find_pager_url = text.re( r' class="pager-next">\s*<a href="([^"]+)').search def items(self): @@ -123,7 +123,7 @@ class HatenablogEntriesExtractor(HatenablogExtractor): class HatenablogEntryExtractor(HatenablogExtractor): """Extractor for a single entry URL""" subcategory = "entry" - pattern = BASE_PATTERN + r"/entry/([^?#]+)" + QUERY_RE + pattern = rf"{BASE_PATTERN}/entry/([^?#]+){QUERY_RE}" example = "https://BLOG.hatenablog.com/entry/PATH" def __init__(self, match): @@ -146,21 +146,21 @@ class HatenablogEntryExtractor(HatenablogExtractor): class HatenablogHomeExtractor(HatenablogEntriesExtractor): """Extractor for a blog's home page""" subcategory = "home" - pattern = BASE_PATTERN + r"(/?)" + QUERY_RE + pattern = rf"{BASE_PATTERN}(/?){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) + pattern = (rf"{BASE_PATTERN}(/archive(?:/\d+(?:/\d+(?:/\d+)?)?" + rf"|/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 + pattern = rf"{BASE_PATTERN}(/search){QUERY_RE}" example = "https://BLOG.hatenablog.com/search?q=QUERY" allowed_parameters = ("q",) |