fixed examples, added documentation

This commit is contained in:
Tangent / Rose / Nebula Rosa 2024-11-05 21:48:33 -07:00
parent 180e979061
commit e14313cff0
2 changed files with 93 additions and 20 deletions

View File

@ -1,5 +1,10 @@
# .lua-files
It's like dotfiles, but no, it's just Lua scripts I find useful.
Personally convenient Lua scripts to add to my path.
## Installation
1. Put this folder somewhere.
2. Add that somewhere to your path. (On Windows, search for Environment Variables (it's "part of" Control Panel) and use the UI to add them to System variables.)
3. (On Windows) Add `.LUA` to PATHEXT.
## Scripts
- `2webm.lua`: Converts everything in the working directory to .webm files.
@ -10,7 +15,61 @@ It's like dotfiles, but no, it's just Lua scripts I find useful.
- `utility-functions.lua`: (Library) Required for many of these scripts to run.
- `video-dl.lua`: A few premade command lines for using `yt-dlp` to download what I want quicker.
## Installation
1. Put this folder somewhere.
2. Add that somewhere to your path. (On Windows, search for Environment Variables (it's "part of" Control Panel) and use the UI to add them to System variables.)
3. (On Windows) Add `.LUA` to PATHEXT.
### make-epub.lua
The JSON config spec has two major variations ("Book" and "Anthology").
The following is shared:
- `authors`: (Optional) Array of Strings: Author names. First in the list is used as a byline in the final output. (Legacy: An `author` string works as well. If this exists, it will be first.)
- `title`: (Optional) String: Title of book.
- `keywords`: Array of Strings: Keywords/Tags. (I'm not sure what the difference is in the final output so it goes in both.)
- `sections`: \! See "Book"/"Anthology" variations. (I call LitErotica's stories sections - because they are often part of a larger whole.)
- `page_counts`: Array of Integers: The number of pages on LitErotica per "story". (I call them sections because this script was made to put together story series originally.)
#### Variation: Book
- `base_url`: String: A partial URL that is the beginning of the URL used for each section (story) on LitErotica. (This script currently only works for stories that end in a padded two-digit number.)
- `first_section_url`: String: Some stories don't have the same URL structure for their first section. This allows you to specify its full URL.
- `sections`: Object defining which sections to download, and what to call them (ie. Chapters, Parts, ..).
- `start`: (Optional) Number: Where to start. (`1` is the default, since it is the most common.)
- `finish`: Number: Where to end.
- `naming`: (Optional) String: How to name sections in the final output. The result is `[naming] [#]` (using section numbers). If not specified, there will be no Table of Contents.
Example:
```json
{
"authors": ["Name"],
"title": "Book",
"keywords": ["erotica", "fantasy"],
"base_url": "https://www.literotica.com/s/title-ch-",
"first_section_url": "https://www.literotica.com/s/title",
"sections": {
"start": 1,
"finish": 4,
"naming": "Chapter"
},
"page_counts": [1, 5, 3, 3]
}
```
#### Variation: Anthology
- `manually_specified_sections`: (Optional) Boolean, must be `true`. Technically not required as the script is capable of figuring out you are using this variation, but *should be* included.
- `sections`: Array of Strings: A complete URL for each story.
- `section_titles`: (Optional) Array of Strings: The titles to be used for Table of Contents / headings. (Must be in the same order as `sections`.)
Example:
```json
{
"authors": ["Name"],
"title": "Anthology",
"keywords": ["LitErotica", "erotica"],
"manually_specified_sections": true,
"sections": [
"https://www.literotica.com/s/unique-title",
"https://www.literotica.com/s/another-title"
],
"section_titles": [
"Unique Title",
"Another Title"
],
"page_counts": [5, 2]
}
```

View File

@ -4,7 +4,7 @@ local help = [[Usage:
make-epub.lua <config (JSON file)> [action]
[action]: If not specified, all steps will be taken in order (except cleanall).
[action]: If not specified, all steps will be taken in order (except clean*).
download: All pages will be downloaded to their own HTML files.
concat: A file is created for each section out of its pages.
convert: Each section is converted to Markdown.
@ -21,23 +21,24 @@ Requirements:
Configuration example(s):
{
"authors": ["Name"], -- "author" with a single string also supported
"authors": ["Name"],
"title": "Book",
"keywords": ["erotica", "fantasy"],
"base_url": "https://www.literotica.com/s/title-ch-", -- not required if only one section
"first_section_url": "https://www.literotica.com/s/title", -- only if first section is differently-formatted
"base_url": "https://www.literotica.com/s/title-ch-",
"first_section_url": "https://www.literotica.com/s/title",
"sections": {
"start": 1,
"finish": 4,
"naming": "Chapter" -- only required for a Table of Contents (unless using anthology form below)
"naming": "Chapter"
},
"page_counts": [1, 5, 3, 3]
}
{
"authors": ["Name"], -- first author will be used as the book's primary author
"authors": ["Name"],
"title": "Anthology",
"keywords": ["erotica", "fantasy"],
"keywords": ["LitErotica", "erotica"],
"manually_specified_sections": true,
"sections": [
"https://www.literotica.com/s/unique-title",
"https://www.literotica.com/s/another-title"
@ -49,7 +50,7 @@ Configuration example(s):
"page_counts": [5, 2]
}
For an explanation of these examples, see the .lua-files ReadMe.
For an explanation of these examples, see the .lua-files README.
]]
local success, utility = pcall(function()
@ -86,12 +87,22 @@ local function get_config()
config = json.decode(file:read("*a"))
file:close()
-- authors wasn't being loaded correctly and I accidentally fixed it while trying to find what was wrong..
-- for k,v in pairs(config) do
-- print(k,v)
-- end
-- print("config done")
if not config.authors then
config.authors = {} -- at least have an empty table so it doesn't error below
end
if type(config.author) then -- old style single author will be added to authors list
table.insert(config.authors, config.author)
if config.author then -- old style single author will be prepended to authors list
table.insert(config.authors, 1, config.author)
end
if not config.keywords then
config.keywords = {} -- TODO test if it will work empty
end
-- detecting manually specified sections and flagging it to the rest of the script
@ -102,6 +113,10 @@ local function get_config()
config.base_url = "http://example.com/" -- must be defined to prevent errors; it will be manipulated and ignored in this use case
end
if not config.sections.start then
config.sections.start = 1 -- the first one can be optional since the common use case is ALL OF THEM
end
if #config.page_counts ~= config.sections.finish - config.sections.start + 1 then
error("Number of page_counts does not match number of sections.")
end
@ -226,11 +241,10 @@ local function get_base_file_name(config)
end
local function convert_sections(config)
-- the HTML I'm pulling from is often bugged in a way that breaks ebook readers, but pandoc can understand and fix in Markdown
utility.required_program("pandoc")
for section = config.sections.start, config.sections.finish do
local section_file_name = "Sections" .. path_separator .. tostring(section)
os.execute("pandoc \"" .. section_file_name .. ".html\" -o \"" .. section_file_name .. ".md\"")
os.execute("pandoc --from html --to markdown \"" .. section_file_name .. ".html\" -o \"" .. section_file_name .. ".md\"")
end
end
@ -260,7 +274,7 @@ end
local function make_epub(config)
utility.required_program("pandoc")
local base_file_name = get_base_file_name(config)
os.execute("pandoc \"" .. base_file_name .. ".md\" -o \"" .. base_file_name .. ".epub\" --toc=true")
os.execute("pandoc --from markdown --to epub \"" .. base_file_name .. ".md\" -o \"" .. base_file_name .. ".epub\" --toc=true")
end
local function rm_html_files(config)
@ -318,7 +332,7 @@ else
write_markdown_file(config)
print("\nMaking ePub...\n")
make_epub(config)
print("\nRemoving HTML files...\n")
rm_html_files(config)
-- print("\nRemoving HTML files...\n")
-- rm_html_files(config)
print("\nDone!\n")
end