V0.9.0 - closes several open issues: new enrichers and bug fixes (#133)

* clean orchestrator code, add archiver cleanup logic

* improves documentation for database.py

* telethon archivers isolate sessions into copied files

* closes #127

* closes #125

* closes #84

* meta enricher applies to all media

* closes #61 adds subtitles and comments

* minor update

* minor fixes to yt-dlp subtitles and comments

* closes #17 but logic is imperfect.

* closes #85 ssl enhancer

* minimifies html, JS refactor for preview of certificates

* closes #91 adds freetsa timestamp authority

* version bump

* simplify download_url method

* skip ssl if nothing archived

* html preview improvements

* adds retrying lib

* manual download archiver improvements

* meta only runs when relevant data available

* new metadata convenience method

* html template improvements

* removes debug message

* does not close #91 yet, will need a few more certificate chaing logging

* adds verbosity config

* new instagram api archiver

* adds proxy support we

* adds proxy/end support and bug fix for yt-dlp

* proxy support for webdriver

* adds socks proxy to wacz_enricher

* refactor recursivity in inner media and display

* infinite recursive display

* foolproofing timestamping authortities

* version to 0.9.0

* minor fixes from code-review

src/auto_archiver/formatters/html_formatter.py

@@ -4,6 +4,8 @@ import mimetypes, os, pathlib
 from jinja2 import Environment, FileSystemLoader
 from urllib.parse import quote
 from loguru import logger
+import minify_html, json
+import base64
 
 from ..version import __version__
 from ..core import Metadata, Media, ArchivingContext
@@ -45,6 +47,8 @@ class HtmlFormatter(Formatter):
             metadata=item.metadata,
             version=__version__
         )
+        content = minify_html.minify(content, minify_js=False, minify_css=True)
+
         html_path = os.path.join(ArchivingContext.get_tmp_dir(), f"formatted{random_str(24)}.html")
         with open(html_path, mode="w", encoding="utf-8") as outf:
             outf.write(content)
@@ -89,3 +93,8 @@ class JinjaHelpers:
     @staticmethod
     def quote(s: str) -> str:
         return quote(s)
+
+    @staticmethod
+    def json_dump_b64(d: dict) -> str:
+        j = json.dumps(d, indent=4, default=str)
+        return base64.b64encode(j.encode()).decode()