diff options
Diffstat (limited to 'gallery_dl/extractor/blogger.py')
| -rw-r--r-- | gallery_dl/extractor/blogger.py | 58 |
1 files changed, 26 insertions, 32 deletions
diff --git a/gallery_dl/extractor/blogger.py b/gallery_dl/extractor/blogger.py index ef117da..796d9d1 100644 --- a/gallery_dl/extractor/blogger.py +++ b/gallery_dl/extractor/blogger.py @@ -1,6 +1,6 @@ # -*- coding: utf-8 -*- -# Copyright 2019-2023 Mike Fährmann +# Copyright 2019-2025 Mike Fährmann # # 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 @@ -10,7 +10,12 @@ from .common import BaseExtractor, Message from .. import text, util -import re + + +def original(url): + return (util.re(r"(/|=)(?:[sw]\d+|w\d+-h\d+)(?=/|$)") + .sub(r"\1s0", url) + .replace("http:", "https:", 1)) class BloggerExtractor(BaseExtractor): @@ -33,13 +38,12 @@ class BloggerExtractor(BaseExtractor): blog["date"] = text.parse_datetime(blog["published"]) del blog["selfLink"] - sub = re.compile(r"(/|=)(?:[sw]\d+|w\d+-h\d+)(?=/|$)").sub - findall_image = re.compile( + findall_image = util.re( r'src="(https?://(?:' r'blogger\.googleusercontent\.com/img|' r'lh\d+(?:-\w+)?\.googleusercontent\.com|' r'\d+\.bp\.blogspot\.com)/[^"]+)').findall - findall_video = re.compile( + findall_video = util.re( r'src="(https?://www\.blogger\.com/video\.g\?token=[^"]+)').findall metadata = self.metadata() @@ -48,7 +52,7 @@ class BloggerExtractor(BaseExtractor): files = findall_image(content) for idx, url in enumerate(files): - files[idx] = sub(r"\1s0", url).replace("http:", "https:", 1) + files[idx] = original(url) if self.videos and 'id="BLOG_video-' in content: page = self.request(post["url"]).text @@ -98,12 +102,8 @@ class BloggerPostExtractor(BloggerExtractor): pattern = BASE_PATTERN + r"(/\d\d\d\d/\d\d/[^/?#]+\.html)" example = "https://BLOG.blogspot.com/1970/01/TITLE.html" - def __init__(self, match): - BloggerExtractor.__init__(self, match) - self.path = match.group(match.lastindex) - def posts(self, blog): - return (self.api.post_by_path(blog["id"], self.path),) + return (self.api.post_by_path(blog["id"], self.groups[-1]),) class BloggerBlogExtractor(BloggerExtractor): @@ -122,16 +122,13 @@ class BloggerSearchExtractor(BloggerExtractor): pattern = BASE_PATTERN + r"/search/?\?q=([^&#]+)" example = "https://BLOG.blogspot.com/search?q=QUERY" - def __init__(self, match): - BloggerExtractor.__init__(self, match) - self.query = text.unquote(match.group(match.lastindex)) + def metadata(self): + self.query = query = text.unquote(self.groups[-1]) + return {"query": query} def posts(self, blog): return self.api.blog_search(blog["id"], self.query) - def metadata(self): - return {"query": self.query} - class BloggerLabelExtractor(BloggerExtractor): """Extractor for Blogger posts by label""" @@ -139,21 +136,18 @@ class BloggerLabelExtractor(BloggerExtractor): pattern = BASE_PATTERN + r"/search/label/([^/?#]+)" example = "https://BLOG.blogspot.com/search/label/LABEL" - def __init__(self, match): - BloggerExtractor.__init__(self, match) - self.label = text.unquote(match.group(match.lastindex)) + def metadata(self): + self.label = label = text.unquote(self.groups[-1]) + return {"label": label} def posts(self, blog): return self.api.blog_posts(blog["id"], self.label) - def metadata(self): - return {"label": self.label} - class BloggerAPI(): - """Minimal interface for the Blogger v3 API + """Minimal interface for the Blogger API v3 - Ref: https://developers.google.com/blogger + https://developers.google.com/blogger """ API_KEY = "AIzaSyCN9ax34oMMyM07g_M-5pjeDp_312eITK8" @@ -162,27 +156,27 @@ class BloggerAPI(): self.api_key = extractor.config("api-key") or self.API_KEY def blog_by_url(self, url): - return self._call("blogs/byurl", {"url": url}, "blog") + return self._call("/blogs/byurl", {"url": url}, "blog") def blog_posts(self, blog_id, label=None): - endpoint = "blogs/{}/posts".format(blog_id) + endpoint = f"/blogs/{blog_id}/posts" params = {"labels": label} return self._pagination(endpoint, params) def blog_search(self, blog_id, query): - endpoint = "blogs/{}/posts/search".format(blog_id) + endpoint = f"/blogs/{blog_id}/posts/search" params = {"q": query} return self._pagination(endpoint, params) def post_by_path(self, blog_id, path): - endpoint = "blogs/{}/posts/bypath".format(blog_id) + endpoint = f"/blogs/{blog_id}/posts/bypath" return self._call(endpoint, {"path": path}, "post") def _call(self, endpoint, params, notfound=None): - url = "https://www.googleapis.com/blogger/v3/" + endpoint + url = "https://www.googleapis.com/blogger/v3" + endpoint params["key"] = self.api_key - return self.extractor.request( - url, params=params, notfound=notfound).json() + return self.extractor.request_json( + url, params=params, notfound=notfound) def _pagination(self, endpoint, params): while True: |