2024-11-05 07:16:24 +00:00
|
|
|
#!/usr/bin/env luajit
|
|
|
|
|
|
|
|
local help = [[Usage:
|
|
|
|
|
|
|
|
make-epub.lua <config (JSON file)> [action]
|
|
|
|
|
2024-11-06 04:48:33 +00:00
|
|
|
[action]: If not specified, all steps will be taken in order (except clean*).
|
2024-11-05 08:11:37 +00:00
|
|
|
download: All pages will be downloaded to their own HTML files.
|
2024-11-06 23:12:15 +00:00
|
|
|
convert: Each page is converted to Markdown.
|
2024-11-05 08:11:37 +00:00
|
|
|
concat: A file is created for each section out of its pages.
|
|
|
|
markdown: Metadata frontmatter and Markdown section files will be
|
|
|
|
concatenated into a single Markdown file.
|
|
|
|
epub: Markdown file will be converted to an ePub using pandoc.
|
|
|
|
cleanhtml: All HTML files will be deleted, along with their extra
|
|
|
|
directories.
|
|
|
|
cleanall: Deletes everything except the ePub.
|
2024-11-05 07:16:24 +00:00
|
|
|
|
|
|
|
Requirements:
|
|
|
|
- Lua libraries: htmlparser, dkjson (or compatible)
|
|
|
|
- Binaries: pandoc, curl
|
|
|
|
|
2024-11-05 23:19:37 +00:00
|
|
|
Configuration example(s):
|
2024-11-05 07:16:24 +00:00
|
|
|
{
|
2024-11-06 04:48:33 +00:00
|
|
|
"authors": ["Name"],
|
2024-11-05 07:16:24 +00:00
|
|
|
"title": "Book",
|
2024-11-05 23:19:37 +00:00
|
|
|
"keywords": ["erotica", "fantasy"],
|
2024-11-06 04:48:33 +00:00
|
|
|
"base_url": "https://www.literotica.com/s/title-ch-",
|
|
|
|
"first_section_url": "https://www.literotica.com/s/title",
|
2024-11-05 07:16:24 +00:00
|
|
|
"sections": {
|
|
|
|
"start": 1,
|
2024-11-05 23:19:37 +00:00
|
|
|
"finish": 4,
|
2024-11-06 04:48:33 +00:00
|
|
|
"naming": "Chapter"
|
2024-11-05 07:16:24 +00:00
|
|
|
},
|
2024-11-05 23:19:37 +00:00
|
|
|
"page_counts": [1, 5, 3, 3]
|
2024-11-05 07:16:24 +00:00
|
|
|
}
|
2024-11-05 23:19:37 +00:00
|
|
|
|
|
|
|
{
|
2024-11-06 04:48:33 +00:00
|
|
|
"authors": ["Name"],
|
2024-11-05 23:19:37 +00:00
|
|
|
"title": "Anthology",
|
2024-11-06 04:48:33 +00:00
|
|
|
"keywords": ["LitErotica", "erotica"],
|
|
|
|
"manually_specified_sections": true,
|
2024-11-05 23:19:37 +00:00
|
|
|
"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]
|
|
|
|
}
|
|
|
|
|
2024-11-06 04:48:33 +00:00
|
|
|
For an explanation of these examples, see the .lua-files README.
|
2024-11-05 07:16:24 +00:00
|
|
|
]]
|
|
|
|
|
2024-11-05 07:28:21 +00:00
|
|
|
local success, utility = pcall(function()
|
2024-11-05 23:19:37 +00:00
|
|
|
return dofile((arg[0]:match("@?(.*/)") or arg[0]:match("@?(.*\\)")) .. "utility-functions.lua")
|
2024-11-05 07:28:21 +00:00
|
|
|
end)
|
|
|
|
if not success then
|
|
|
|
print("\n\n" .. tostring(utility))
|
|
|
|
error("\n\nThis script may be installed improperly. Follow instructions at:\n\thttps://github.com/TangentFoxy/.lua-files#installation\n")
|
|
|
|
end
|
|
|
|
|
2024-11-05 07:53:24 +00:00
|
|
|
local json = utility.require("json")
|
|
|
|
|
2024-11-05 23:19:37 +00:00
|
|
|
-- TODO utility.path_separator should be a thing
|
2024-11-05 07:53:24 +00:00
|
|
|
local path_separator
|
|
|
|
if utility.OS == "Windows" then
|
|
|
|
path_separator = "\\"
|
|
|
|
else
|
|
|
|
path_separator = "/"
|
|
|
|
end
|
2024-11-05 07:16:24 +00:00
|
|
|
|
|
|
|
-- also checks for errors
|
|
|
|
-- TODO make it check for required elements and error if any are missing!
|
|
|
|
local function get_config()
|
2024-11-05 23:19:37 +00:00
|
|
|
-- TODO arg checking REALLY should not be here
|
2024-11-05 07:16:24 +00:00
|
|
|
if not arg[1] then
|
|
|
|
print(help)
|
|
|
|
error("\nA config file name/path must be specified.")
|
|
|
|
elseif arg[1] == "-h" or arg[1] == "--help" then
|
2024-11-05 07:53:24 +00:00
|
|
|
error(help) -- I strongly dislike using an error to print a help message instead of gracefully exiting..
|
2024-11-05 07:16:24 +00:00
|
|
|
end
|
|
|
|
|
|
|
|
local file, err = io.open(arg[1], "r")
|
|
|
|
if not file then error(err) end
|
2024-11-05 07:28:21 +00:00
|
|
|
config = json.decode(file:read("*a"))
|
2024-11-05 07:16:24 +00:00
|
|
|
file:close()
|
|
|
|
|
2024-11-06 04:48:33 +00:00
|
|
|
-- 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")
|
|
|
|
|
2024-11-05 23:19:37 +00:00
|
|
|
if not config.authors then
|
|
|
|
config.authors = {} -- at least have an empty table so it doesn't error below
|
|
|
|
end
|
|
|
|
|
2024-11-06 04:48:33 +00:00
|
|
|
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
|
2024-11-05 23:19:37 +00:00
|
|
|
end
|
|
|
|
|
2024-11-05 09:25:50 +00:00
|
|
|
-- detecting manually specified sections and flagging it to the rest of the script
|
|
|
|
if config.sections[1] then
|
|
|
|
config.sections.start = 1
|
|
|
|
config.sections.finish = #config.sections
|
|
|
|
config.manually_specified_sections = true -- decided to make this part of the config spec, but it's set here again just in case
|
2024-11-05 16:42:00 +00:00
|
|
|
config.base_url = "http://example.com/" -- must be defined to prevent errors; it will be manipulated and ignored in this use case
|
2024-11-05 09:25:50 +00:00
|
|
|
end
|
|
|
|
|
2024-11-06 04:48:33 +00:00
|
|
|
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
|
|
|
|
|
2024-11-05 07:16:24 +00:00
|
|
|
if #config.page_counts ~= config.sections.finish - config.sections.start + 1 then
|
|
|
|
error("Number of page_counts does not match number of sections.")
|
|
|
|
end
|
|
|
|
|
2024-11-05 23:19:37 +00:00
|
|
|
if config.section_titles and #config.section_titles ~= config.sections.finish - config.sections.start + 1 then
|
|
|
|
error("Number of section_titles does not match number of sections.")
|
|
|
|
end
|
|
|
|
|
2024-11-05 07:16:24 +00:00
|
|
|
return config
|
|
|
|
end
|
|
|
|
|
|
|
|
local function format_metadata(config)
|
|
|
|
local function stringify_list(list)
|
2024-11-05 07:28:21 +00:00
|
|
|
local output = "\"" .. utility.escape_quotes(list[1]) .. "\""
|
2024-11-05 07:16:24 +00:00
|
|
|
for i = 2, #list do
|
2024-11-05 16:57:36 +00:00
|
|
|
output = output .. ", \"" .. utility.escape_quotes(list[i]) .. "\""
|
2024-11-05 07:16:24 +00:00
|
|
|
end
|
|
|
|
return output
|
|
|
|
end
|
|
|
|
|
|
|
|
local keywords_string = stringify_list(config.keywords)
|
|
|
|
local metadata = {
|
|
|
|
"---",
|
2024-11-05 07:28:21 +00:00
|
|
|
"title: \"" .. utility.escape_quotes(config.title) .. "\"",
|
2024-11-05 23:19:37 +00:00
|
|
|
"author: [" .. stringify_list(config.authors) .. "]",
|
2024-11-05 07:16:24 +00:00
|
|
|
"keywords: [" .. keywords_string .. "]",
|
|
|
|
"tags: [" .. keywords_string .. "]",
|
|
|
|
"---",
|
|
|
|
"",
|
|
|
|
}
|
|
|
|
|
|
|
|
return table.concat(metadata, "\n") .. "\n"
|
|
|
|
end
|
|
|
|
|
|
|
|
local function download_pages(config)
|
2024-11-05 07:53:24 +00:00
|
|
|
local htmlparser = utility.require("htmlparser")
|
2024-11-05 07:28:21 +00:00
|
|
|
utility.required_program("curl")
|
2024-11-05 07:16:24 +00:00
|
|
|
|
|
|
|
os.execute("mkdir Sections")
|
|
|
|
for section = config.sections.start, config.sections.finish do
|
|
|
|
local section_dir = "Sections" .. path_separator .. tostring(section) .. path_separator
|
|
|
|
os.execute("mkdir " .. section_dir:sub(1, -2))
|
|
|
|
|
|
|
|
local section_url
|
|
|
|
if section == 1 and config.first_section_url then
|
|
|
|
section_url = config.first_section_url
|
|
|
|
else
|
2024-11-05 07:28:21 +00:00
|
|
|
section_url = config.base_url .. string.format("%02i", section) -- leftpad 2 (This will eventually cause problems.)
|
2024-11-05 07:16:24 +00:00
|
|
|
end
|
|
|
|
|
2024-11-05 09:25:50 +00:00
|
|
|
if config.manually_specified_sections then
|
|
|
|
section_url = config.sections[section]
|
|
|
|
end
|
|
|
|
|
2024-11-05 07:16:24 +00:00
|
|
|
for page = 1, config.page_counts[section - (config.sections.start - 1)] do
|
|
|
|
local download_url
|
|
|
|
if page == 1 then
|
|
|
|
download_url = section_url
|
|
|
|
else
|
|
|
|
download_url = section_url .. "?page=" .. tostring(page)
|
|
|
|
end
|
|
|
|
|
|
|
|
local html_file_name = ".tmp." .. tostring(math.random()) .. ".html"
|
|
|
|
os.execute("curl \"" ..download_url .. "\" > " .. html_file_name)
|
|
|
|
|
|
|
|
local html_file, err = io.open(html_file_name, "r")
|
|
|
|
if not html_file then error("Could not download \"" .. download_url .. "\"") end
|
|
|
|
local raw_html = html_file:read("*a")
|
|
|
|
html_file:close()
|
|
|
|
os.execute("rm " .. html_file_name)
|
|
|
|
|
|
|
|
local parser = htmlparser.parse(raw_html)
|
2024-11-05 07:28:21 +00:00
|
|
|
local content_tag = parser:select(".article > div > div") -- TODO add ability to set selector in config!
|
2024-11-05 07:16:24 +00:00
|
|
|
local text = content_tag[1]:getcontent()
|
|
|
|
|
|
|
|
local page_file, err = io.open(section_dir .. page .. ".html", "w")
|
|
|
|
if not page_file then error(err) end
|
|
|
|
page_file:write(text .. "\n")
|
|
|
|
page_file:close()
|
|
|
|
|
|
|
|
os.execute("sleep " .. tostring(math.random(5))) -- avoid rate limiting
|
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2024-11-06 23:12:15 +00:00
|
|
|
local function convert_pages(config)
|
|
|
|
utility.required_program("pandoc")
|
|
|
|
for section = config.sections.start, config.sections.finish do
|
|
|
|
local section_dir = "Sections" .. path_separator .. tostring(section) .. path_separator
|
|
|
|
|
|
|
|
for page = 1, config.page_counts[section - (config.sections.start - 1)] do
|
|
|
|
local page_file_name_base = section_dir .. page
|
|
|
|
os.execute("pandoc --from html --to markdown \"" .. page_file_name_base .. ".html\" -o \"" .. page_file_name_base .. ".md\"")
|
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2024-11-05 07:16:24 +00:00
|
|
|
local function concatenate_pages(config)
|
|
|
|
for section = config.sections.start, config.sections.finish do
|
2024-11-06 23:12:15 +00:00
|
|
|
local section_dir = "Sections" .. path_separator .. tostring(section) .. path_separator
|
|
|
|
local section_file, err = io.open("Sections" .. path_separator .. tostring(section) .. ".md", "w")
|
2024-11-05 07:16:24 +00:00
|
|
|
if not section_file then error(err) end
|
|
|
|
|
|
|
|
for page = 1, config.page_counts[section - (config.sections.start - 1)] do
|
2024-11-06 23:12:15 +00:00
|
|
|
local page_file, err = io.open(section_dir .. page .. ".md", "r")
|
2024-11-05 07:16:24 +00:00
|
|
|
if not page_file then error(err) end
|
2024-11-06 23:12:15 +00:00
|
|
|
section_file:write(page_file:read("*a") .. "\n") -- the \n probably isn't needed, but does guarantee safety..
|
2024-11-05 07:16:24 +00:00
|
|
|
page_file:close()
|
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2024-11-06 23:12:15 +00:00
|
|
|
-- TODO define this earlier, use it to choose where files go (this will also require every command executed to have quotes wrapping it!)
|
2024-11-05 07:16:24 +00:00
|
|
|
local function get_base_file_name(config)
|
2024-11-06 23:12:15 +00:00
|
|
|
-- TODO move make_safe_file_name to utility
|
2024-11-05 07:16:24 +00:00
|
|
|
local function make_safe_file_name(file_name)
|
|
|
|
file_name = file_name:gsub("[%\"%:%\\%!%@%#%$%%%^%*%=%{%}%|%;%<%>%?%/]", "") -- everything except the &
|
|
|
|
file_name = file_name:gsub(" %&", ",") -- replacing & with a comma works for 99% of things
|
|
|
|
file_name = file_name:gsub("%&", ",") -- replacing & with a comma works for 99% of things
|
|
|
|
file_name = file_name:gsub("[%s+]", " ") -- more than one space in succession should be a single space
|
|
|
|
return file_name
|
|
|
|
end
|
|
|
|
|
|
|
|
local base_file_name
|
2024-11-05 23:19:37 +00:00
|
|
|
if config.title and config.authors[1] then
|
|
|
|
-- first author in list gets top billing (this is problematic in anthologies unless an editor is the first entry)
|
|
|
|
base_file_name = config.title .. " by " .. config.authors[1]
|
2024-11-05 07:16:24 +00:00
|
|
|
elseif config.title then
|
|
|
|
base_file_name = config.title
|
|
|
|
else
|
|
|
|
base_file_name = "Book"
|
|
|
|
end
|
|
|
|
|
|
|
|
return make_safe_file_name(base_file_name)
|
|
|
|
end
|
|
|
|
|
2024-11-06 23:12:15 +00:00
|
|
|
-- NOTE deprecated (order of operations had to be changed, see #25)
|
2024-11-05 07:16:24 +00:00
|
|
|
local function convert_sections(config)
|
2024-11-05 07:28:21 +00:00
|
|
|
utility.required_program("pandoc")
|
2024-11-05 07:16:24 +00:00
|
|
|
for section = config.sections.start, config.sections.finish do
|
|
|
|
local section_file_name = "Sections" .. path_separator .. tostring(section)
|
2024-11-06 04:48:33 +00:00
|
|
|
os.execute("pandoc --from html --to markdown \"" .. section_file_name .. ".html\" -o \"" .. section_file_name .. ".md\"")
|
2024-11-05 07:16:24 +00:00
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
local function write_markdown_file(config)
|
|
|
|
local markdown_file, err = io.open(get_base_file_name(config) .. ".md", "w")
|
|
|
|
if not markdown_file then error(err) end
|
|
|
|
markdown_file:write(format_metadata(config))
|
|
|
|
|
|
|
|
for section = config.sections.start, config.sections.finish do
|
2024-11-05 09:25:50 +00:00
|
|
|
if config.sections.naming then
|
2024-11-05 23:19:37 +00:00
|
|
|
markdown_file:write("\n\n# " .. config.sections.naming .. " " .. tostring(section))
|
|
|
|
elseif config.section_titles then
|
|
|
|
markdown_file:write("\n\n# " .. config.section_titles[section])
|
2024-11-05 09:25:50 +00:00
|
|
|
end
|
2024-11-05 23:19:37 +00:00
|
|
|
markdown_file:write("\n\n")
|
2024-11-05 07:16:24 +00:00
|
|
|
|
|
|
|
local section_file_name = "Sections" .. path_separator .. tostring(section)
|
|
|
|
local section_file, err = io.open(section_file_name .. ".md", "r")
|
|
|
|
if not section_file then error(err) end
|
|
|
|
markdown_file:write(section_file:read("*a"))
|
|
|
|
section_file:close()
|
|
|
|
end
|
|
|
|
|
|
|
|
markdown_file:close()
|
|
|
|
end
|
|
|
|
|
|
|
|
local function make_epub(config)
|
2024-11-05 07:28:21 +00:00
|
|
|
utility.required_program("pandoc")
|
2024-11-05 07:16:24 +00:00
|
|
|
local base_file_name = get_base_file_name(config)
|
2024-11-06 04:48:33 +00:00
|
|
|
os.execute("pandoc --from markdown --to epub \"" .. base_file_name .. ".md\" -o \"" .. base_file_name .. ".epub\" --toc=true")
|
2024-11-05 07:16:24 +00:00
|
|
|
end
|
|
|
|
|
2024-11-05 08:11:37 +00:00
|
|
|
local function rm_html_files(config)
|
2024-11-06 04:58:18 +00:00
|
|
|
os.execute("sleep 1") -- attempt to fix #14
|
|
|
|
|
2024-11-05 08:11:37 +00:00
|
|
|
for section = config.sections.start, config.sections.finish do
|
|
|
|
local section_dir = "Sections" .. path_separator .. tostring(section)
|
|
|
|
os.execute("rm " .. section_dir .. ".html")
|
|
|
|
|
|
|
|
for page = 1, config.page_counts[section - (config.sections.start - 1)] do
|
|
|
|
os.execute("rm " .. section_dir .. path_separator .. page .. ".html")
|
|
|
|
end
|
|
|
|
|
2024-11-06 23:12:15 +00:00
|
|
|
os.execute("rmdir " .. section_dir) -- NOTE this is no longer possible due to Markdown versions of each page existing
|
2024-11-05 08:11:37 +00:00
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
local function rm_all(config)
|
2024-11-06 23:12:15 +00:00
|
|
|
-- TODO use structure of rm_html_files because there's a Markdown file for every HTML file now..
|
2024-11-05 08:11:37 +00:00
|
|
|
rm_html_files(config)
|
|
|
|
|
|
|
|
for section = config.sections.start, config.sections.finish do
|
|
|
|
local section_file_name = "Sections" .. path_separator .. tostring(section) .. ".md"
|
|
|
|
os.execute("rm " .. section_file_name)
|
|
|
|
end
|
|
|
|
|
|
|
|
os.execute("rmdir Sections")
|
|
|
|
os.execute("rm \"" .. get_base_file_name(config) .. ".md\"")
|
|
|
|
end
|
|
|
|
|
2024-11-05 07:16:24 +00:00
|
|
|
local execute = {
|
|
|
|
download = download_pages,
|
2024-11-06 23:12:15 +00:00
|
|
|
convert = convert_pages,
|
2024-11-05 07:16:24 +00:00
|
|
|
concat = concatenate_pages,
|
|
|
|
markdown = write_markdown_file,
|
|
|
|
epub = make_epub,
|
2024-11-05 08:11:37 +00:00
|
|
|
cleanhtml = rm_html_files,
|
|
|
|
cleanall = rm_all,
|
2024-11-05 07:16:24 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
local config = get_config()
|
|
|
|
|
|
|
|
local action = arg[2]
|
|
|
|
if action then
|
|
|
|
if execute[action] then
|
|
|
|
execute[action](config)
|
|
|
|
else
|
|
|
|
print(help)
|
|
|
|
end
|
|
|
|
else
|
|
|
|
print("\nDownloading pages...\n")
|
|
|
|
download_pages(config)
|
2024-11-06 23:12:15 +00:00
|
|
|
print("\nConverting pages...\n")
|
|
|
|
convert_pages(config)
|
2024-11-05 07:16:24 +00:00
|
|
|
print("\nConcatenating pages...\n")
|
|
|
|
concatenate_pages(config)
|
|
|
|
print("\nWriting Markdown file...\n")
|
|
|
|
write_markdown_file(config)
|
|
|
|
print("\nMaking ePub...\n")
|
|
|
|
make_epub(config)
|
2024-11-06 04:48:33 +00:00
|
|
|
-- print("\nRemoving HTML files...\n")
|
|
|
|
-- rm_html_files(config)
|
2024-11-05 07:16:24 +00:00
|
|
|
print("\nDone!\n")
|
|
|
|
end
|