Felipe Marinho
455f734c8a
* chg: feat: clean known patterns from title * chg: refactor: remove duplicated code, and improve maintainability * chg: feat: add audio tagging post-processor * chg: refactor: add generic parallelMap function * chg: refactor: move more function to common locations * chg: docs: add func docs
98 lines
1.8 KiB
Go
98 lines
1.8 KiB
Go
package utils
|
|
|
|
import (
|
|
"fmt"
|
|
"regexp"
|
|
"strings"
|
|
"sync"
|
|
)
|
|
|
|
var commonTLDs = []string{
|
|
".com",
|
|
".net",
|
|
".org",
|
|
".info",
|
|
".biz",
|
|
".co",
|
|
".io",
|
|
".xyz",
|
|
".me",
|
|
".tv",
|
|
".cc",
|
|
".us",
|
|
".online",
|
|
".site",
|
|
".la",
|
|
".se",
|
|
".to",
|
|
}
|
|
|
|
var commonSubdomains = []string{
|
|
"", // no prefix
|
|
"www.",
|
|
}
|
|
|
|
var commonWebsiteSLDs = []string{
|
|
"bludv",
|
|
"torrentdosfilmes",
|
|
"comando",
|
|
"comandotorrents",
|
|
"comandohds",
|
|
"redetorrent",
|
|
"torrenting",
|
|
"baixarfilmesdubladosviatorrent",
|
|
"hidratorrents",
|
|
"wolverdonfilmes",
|
|
"starckfilmes",
|
|
"rapidotorrents",
|
|
"sitedetorrents",
|
|
"vamostorrent",
|
|
"AZTORRENTS",
|
|
}
|
|
|
|
var websitePatterns = []string{
|
|
`\[\s*ACESSE\s+%s\s*\]`,
|
|
`\[?\s*%s(\s*\])?`,
|
|
}
|
|
|
|
var regexesOnce sync.Once
|
|
var regexes []*regexp.Regexp
|
|
|
|
func getRegexes() []*regexp.Regexp {
|
|
regexesOnce.Do(func() {
|
|
var websites strings.Builder
|
|
websites.WriteString("(?i)(")
|
|
for _, prefix := range commonSubdomains {
|
|
for _, name := range commonWebsiteSLDs {
|
|
for _, tld := range commonTLDs {
|
|
websites.WriteString(fmt.Sprintf("%s%s%s|", prefix, name, tld))
|
|
}
|
|
}
|
|
}
|
|
// remove the last pipe character
|
|
websites.WriteString(")")
|
|
|
|
websitesStr := websites.String()
|
|
websitesStr = strings.Replace(websitesStr, "|)", ")", 1)
|
|
|
|
for _, pattern := range websitePatterns {
|
|
regexes = append(regexes, regexp.MustCompile(fmt.Sprintf(pattern, websitesStr)))
|
|
}
|
|
})
|
|
return regexes
|
|
}
|
|
|
|
// RemoveKnownWebsites removes known website patterns from the title.
|
|
// It uses a set of common prefixes, names, and TLDs to identify and remove
|
|
// website references from the title.
|
|
// It also removes any common patterns like "[ ACESSE bludv.com ]" or
|
|
// "[ bludv.se ]" or "bludv.xyz".
|
|
func RemoveKnownWebsites(title string) string {
|
|
regexes := getRegexes()
|
|
for _, re := range regexes {
|
|
title = re.ReplaceAllString(title, "")
|
|
}
|
|
title = strings.TrimSpace(title)
|
|
return title
|
|
}
|