filebot/BuildData.groovy

162 lines
5.3 KiB
Groovy
Raw Normal View History

// filebot -script BuildData.groovy
2012-02-24 13:39:32 +00:00
// UPDATE release-groups.txt FROM http://scenegrouplist.com/lists_sgl.php
@Grab('org.jsoup:jsoup')
import org.jsoup.*
def sgl = []
for (def page = 0; true; page++) {
def dom = Jsoup.parse(new URL('http://scenegrouplist.com/lists_sgl.php?pageNum_RSSGL=' + page), 10000)
def table = dom.select("table[border=1] tr").collect{ it.select("td")*.text()*.trim() }.findAll{ it[2] =~ /\d{4}/ }
sgl += table
if (table.empty) break
}
sgl = sgl.findAll{ it[1] =~ /\b(DVD|DVDR|HD|TV)\b/ && it[0] =~ /\p{Alpha}/}.findResults{ it[0] }
sgl = sgl.collect{ it.before(/ - /).trim().space('.') }.collect{ it ==~ /\p{Upper}?\p{Lower}+/ ? it.toUpperCase() : it }
// append release group names
new File('website/data/release-groups.txt') << '\n' << sgl.join('\n')
// ------------------------------------------------------------------------- //
def sortRegexList(path) {
def set = new TreeSet(String.CASE_INSENSITIVE_ORDER)
2012-07-16 02:36:49 +00:00
new File(path).eachLine('UTF-8'){
// check if regex compiles
set += java.util.regex.Pattern.compile(it).pattern()
}
def out = set.join('\n').saveAs(path)
println "$out\n$out.text\n"
}
// sort and check shared regex collections
sortRegexList("website/data/release-groups.txt")
sortRegexList("website/data/query-blacklist.txt")
sortRegexList("website/data/exclude-blacklist.txt")
sortRegexList("website/data/series-mappings.txt")
// ------------------------------------------------------------------------- //
def series_out = new File("website/data/series.list.gz")
def movies_out = new File("website/data/movies.txt.gz")
def thetvdb_out = new File("website/data/thetvdb.txt.gz")
2012-02-26 17:02:54 +00:00
def gz(file, lines) {
file.withOutputStream{ out ->
2012-07-16 02:36:49 +00:00
new java.util.zip.GZIPOutputStream(out).withWriter('UTF-8'){ writer ->
2012-02-26 17:02:54 +00:00
lines.each{ writer.append(it).append('\n') }
}
}
}
// ------------------------------------------------------------------------- //
// LOAD osdb-imdb.txt (already verified data)
def imdb_tsv = new File("osdb-imdb.txt")
def imdb = [].asSynchronized() // thread-safe list
2012-02-26 17:02:54 +00:00
imdb_tsv.getText('UTF-8').eachLine{
imdb << it.split(/\t/)
}
imdb_ids = new HashSet(imdb.collect{ it[0] })
// BUILD movies.txt.gz
def osdb_tsv = new URL("http://www.opensubtitles.org/addons/export_movie.php")
def osdb = []
osdb_tsv.getText('UTF-8').eachLine{
2012-02-26 17:02:54 +00:00
def line = it.split(/\t/)*.replaceAll(/\s+/, ' ')*.trim()
if (line.size() == 4 && line[0] =~ /\d+/) {
osdb << [line[1].toInteger(), line[2], line[3].toInteger()]
2012-02-26 17:02:54 +00:00
}
}
osdb = osdb.findAll{ it[0] <= 9999999 && it[2] >= 1930 && it[1] =~ /^[A-Z0-9]/ && it[1] =~ /[\p{Alpha}]{3}/ }.collect{ [it[0].pad(7), it[1], it[2]] }
parallel(osdb.collect{ row ->
return {
// update new data
if (!imdb_ids.contains(row[0])) {
// get original title and english title
[Locale.ROOT, Locale.ENGLISH].collect{ locale -> net.sourceforge.filebot.WebServices.IMDb.getMovieDescriptor(row[0] as int, locale) }.unique{ it as String }.each { mov ->
if (mov != null && mov.name.length() > 0 && mov.year > 0) {
println "Adding $mov"
imdb << [row[0], mov.name, mov.year]
} else {
println "Blacklisting $row"
imdb << [row[0], null]
}
}
}
}
}, 20)
// save updated imdb data
2012-07-20 14:09:44 +00:00
imdb.collect{ it.join('\t') }.sort().join('\n').saveAs(imdb_tsv)
2012-02-26 17:02:54 +00:00
// save movie data
def movies = imdb.findAll{ it.size() >= 3 && !it[1].startsWith('"') }
2012-02-26 17:02:54 +00:00
def movieSorter = new TreeMap(String.CASE_INSENSITIVE_ORDER)
movies.each{ movieSorter.put([it[1], it[2], it[0]].join('\t'), it) }
movies = movieSorter.values().collect{ it.join('\t') }
gz(movies_out, movies)
2012-02-26 17:02:54 +00:00
println "Movie Count: " + movies.size()
// ------------------------------------------------------------------------- //
// BUILD thetvdb-index.gz
def thetvdb_index_url = new URL('http://thetvdb.com/?string=&searchseriesid=&tab=listseries&function=Search')
def thetvdb_index = thetvdb_index_url.fetch().getHtml('UTF-8')
.depthFirst().TABLE.find{it['@id'] == "listtable"}
.depthFirst().TR.findAll{ it.TD.size() == 3 && it.TD[1].text() == 'English' && it.TD[0].A.text() }
.findResults{ [it.TD[2].text(), it.TD[0].A.text()] }
// join and sort
def thetvdb = thetvdb_index.findResults{ [it[0].pad(6), it[1]].join('\t') }.sort()
gz(thetvdb_out, thetvdb)
println "TheTVDB Index: " + thetvdb.size()
2012-02-26 17:02:54 +00:00
// BUILD series.list.gz
2012-07-16 02:36:49 +00:00
// TheTVDB
def thetvdb_names = thetvdb_index.findResults{ it[1] }
2012-07-16 02:36:49 +00:00
// AniDB
def anidb_names = net.sourceforge.filebot.WebServices.AniDB.getAnimeTitles().findResults{ [it.getPrimaryTitle(), it.getOfficialTitle('en')] }.flatten()
/*
2012-07-16 02:36:49 +00:00
// IMDb series list
def imdb_series_names = imdb.findAll{ it.size() >= 3 && it[1].startsWith('"') }.collect{ it[1] }
// Dokuwiki list
def dokuwiki_index = new URL('http://docuwiki.net/postbot/getList.php?subject=Name')
def doku_names = []
dokuwiki_index.getText('UTF-8').eachLine{
doku_names << it.trim().replaceTrailingBrackets()
}
*/
2012-07-16 02:36:49 +00:00
def names = [thetvdb_names, anidb_names]
names.each{ if (it.size() == 0) throw new Exception("Failed to scrape series names") } // sanity check
2012-10-15 12:10:36 +00:00
names = names.flatten().findAll{ it =~ /^[A-Z0-9]/ && it =~ /[\p{Alpha}]{3}/}.findResults{ net.sourceforge.filebot.similarity.Normalization.normalizePunctuation(it) } // collect and normalize names
2012-03-20 18:18:34 +00:00
def seriesSorter = new TreeSet(String.CASE_INSENSITIVE_ORDER)
seriesSorter.addAll(names)
names = seriesSorter as List
gz(series_out, names)
println "Series Count: " + names.size()