From eadc4080b1967b76b50321a85bb6cd32b0d553f1 Mon Sep 17 00:00:00 2001 From: Bel LaPointe Date: Wed, 16 Feb 2022 16:14:31 -0700 Subject: [PATCH] google slides works enough for search --- crawler/google.sh | 6 +++++- crawler/rclone.sh | 4 ++-- server/todo.yaml | 10 +++++----- 3 files changed, 12 insertions(+), 8 deletions(-) diff --git a/crawler/google.sh b/crawler/google.sh index 2c43f12..6ee73a4 100644 --- a/crawler/google.sh +++ b/crawler/google.sh @@ -1,6 +1,10 @@ #! /bin/bash google() ( + _is_slides() { + echo "$@" | grep -q 'docs.google.com.presentation' + } + _is_sheets() { echo "$@" | grep -q 'docs.google.com.spreadsheets' } @@ -10,7 +14,7 @@ google() ( } is() { - _is_sheets "$@" || _is_doc "$@" + _is_sheets "$@" || _is_doc "$@" || _is_slides "$@" } human_url() { diff --git a/crawler/rclone.sh b/crawler/rclone.sh index 5c3e0e6..5913b59 100644 --- a/crawler/rclone.sh +++ b/crawler/rclone.sh @@ -2,7 +2,7 @@ rclone() ( get_google() { - local cache_key="rclone get google $*" + local cache_key="rclone get google 2 $*" if cache get "$cache_key"; then return 0 fi @@ -13,7 +13,7 @@ rclone() ( _rate_limit local id="$1" local out="$(mktemp -d)" - _cmd backend copyid work-notes-google: --drive-export-formats=csv,html,pdf "$id" "$out/" + _cmd backend copyid work-notes-google: --drive-export-formats=csv,html,txt "$id" "$out/" find "$out" -type f } diff --git a/server/todo.yaml b/server/todo.yaml index cfe599b..b939de4 100644 --- a/server/todo.yaml +++ b/server/todo.yaml @@ -1,15 +1,15 @@ todo: -- scrape gdoc -- rewrite links if available to local - scrape odo -- scrape gsheet -- scrape gslide +- mark generated via meta so other files in the dir can be created, deleted, replaced safely +- rewrite links if available to local - table of contents - anchor per line - anchor links work - ui; last updated; 2022.02.01T12:34:56 -- mark generated via meta so other files in the dir can be created, deleted, replaced safely done: +- scrape gslide +- scrape gsheet +- scrape gdoc - alert box; https://concisecss.com/documentation/ui - hide checkbox for tree - do not rewrite .md title vs. link cause hrefs to ./gobs.md wont work