Draff/Tachiyomi-Extensions
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Improve MangaHost. (#730)

Browse Source 
Improvements for MangaHost.
This commit is contained in:
Alessandro Jean 2019-01-14 22:47:11 -02:00 committed by Carlos
parent 5c86dd7a93
commit eb9bc1971f
2 changed files with 99 additions and 108 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/pt/mangahost/build.gradle
View File

@ -5,12 +5,8 @@ ext {
appName = 'Tachiyomi: MangaHost'
pkgNameSuffix = 'pt.mangahost'
extClass = '.MangaHost'
extVersionCode = 1
extVersionCode = 2
libVersion = '1.2'
}
sourceSets {
main.java.srcDirs += 'src/eu/kanade/tachiyomi/extension/pt/mangahost'
}
apply from: "$rootDir/common.gradle"

201
src/pt/mangahost/src/eu/kanade/tachiyomi/extension/pt/mangahost/MangaHost.kt
View File

@ -1,17 +1,15 @@
package eu.kanade.tachiyomi.extension.pt.mangahost
import eu.kanade.tachiyomi.network.GET
import eu.kanade.tachiyomi.source.model.*
import eu.kanade.tachiyomi.source.online.ParsedHttpSource
import eu.kanade.tachiyomi.util.asJsoup
import okhttp3.*
import org.jsoup.nodes.Document
import org.jsoup.nodes.Element
import java.text.ParseException
import java.text.SimpleDateFormat
import java.util.*
import java.util.regex.Matcher
import java.util.regex.Pattern
import eu.kanade.tachiyomi.network.GET
import eu.kanade.tachiyomi.source.model.*
import eu.kanade.tachiyomi.source.online.ParsedHttpSource
import okhttp3.*
import org.jsoup.Jsoup
import org.jsoup.nodes.Document
import org.jsoup.nodes.Element
import java.text.ParseException
import java.text.SimpleDateFormat
import java.util.Locale
class MangaHost : ParsedHttpSource() {
@ -23,70 +21,75 @@ class MangaHost : ParsedHttpSource() {
override val supportsLatest = true
private val langRegex: String = "( )?\\(Pt-Br\\)"
private val catalogHeaders = Headers.Builder().apply {
add("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.92 Safari/537.36")
add("Host", "mangahost1.com")
add("Referer", baseUrl)
}.build()
override fun popularMangaSelector(): String = "a.pull-left"
private fun mangaFromElement(element: Element, lazy: Boolean = true): SManga = SManga.create().apply {
title = element.attr("title").replace(LANG_REGEX.toRegex(), "")
thumbnail_url = element.select("img.manga").attr(if (lazy) "data-path" else "src")
.replace(IMAGE_REGEX.toRegex(), "_large.")
setUrlWithoutDomain(element.attr("href"))
}
override fun popularMangaSelector(): String = "div.thumbnail div a.pull-left"
override fun popularMangaRequest(page: Int): Request {
val pageStr = if (page != 1) "/$page" else ""
return GET("$baseUrl/mangas/mais-visualizados$pageStr", headers)
val pageStr = if (page != 1) "/page/$page" else ""
return GET("$baseUrl/mangas/mais-visualizados$pageStr", catalogHeaders)
}
override fun popularMangaFromElement(element: Element) : SManga {
val manga = SManga.create()
element.select("a").last().let {
manga.setUrlWithoutDomain(it.attr("href"))
manga.title = element.getElementsByClass("manga").attr("alt")
}
override fun popularMangaFromElement(element: Element): SManga = mangaFromElement(element)
return manga
}
override fun popularMangaNextPageSelector() = "div.wp-pagenavi:has(a.nextpostslink)"
override fun popularMangaNextPageSelector() = ".paginador.wp-pagenavi a:contains(next)"
override fun latestUpdatesSelector() = "div.thumbnail"
override fun latestUpdatesSelector() = "table.table-lancamentos > tbody > tr > td:eq(0) > a"
override fun latestUpdatesRequest(page: Int): Request {
val pageStr = if (page != 1) "/$page" else ""
return GET("$baseUrl/mangas/novos$pageStr", headers)
}
override fun latestUpdatesFromElement(element: Element): SManga {
return popularMangaFromElement(element)
val pageStr = if (page != 1) "/page/$page" else ""
return GET("$baseUrl/lancamentos$pageStr", catalogHeaders)
}
override fun latestUpdatesNextPageSelector() = "paginador.wp-pagenavi a:contains(next)"
override fun latestUpdatesFromElement(element: Element): SManga = mangaFromElement(element, false)
override fun latestUpdatesNextPageSelector() = popularMangaNextPageSelector()
override fun searchMangaRequest(page: Int, query: String, filters: FilterList): Request {
return GET("$baseUrl"+"find/$query", headers)
// The site sometimes recognize it's a crawler and return only a
// manga called "Robot" if the "find/$query" is used directly.
return GET("$baseUrl/find/?this=$query", catalogHeaders)
}
override fun searchMangaSelector() = ".table-hover tr"
override fun searchMangaFromElement(element: Element): SManga {
return popularMangaFromElement(element)
}
override fun searchMangaSelector() = "table.table-search > tbody > tr > td:eq(0) > a"
override fun searchMangaFromElement(element: Element): SManga = mangaFromElement(element)
override fun searchMangaNextPageSelector() = null
override fun mangaDetailsParse(document: Document): SManga {
val infoElement = document.select("div.margin-bottom-20").first()
val infoElement = document.select("div#page > section > div > div.pull-left")
val manga = SManga.create()
val author = infoElement.select("li:contains(Autor: )").text()
val author = infoElement.select("li:contains(Autor:)").text()
manga.author = removeLabel(author)
val artist = infoElement.select("li:contains(Desenho (Art): )").text()
val artist = infoElement.select("li:contains(Desenho (Art):)").text()
manga.artist = removeLabel(artist)
val genre = infoElement.select("li:contains(Categoria(s): )").text()
val genre = infoElement.select("li:contains(Categoria(s):)").text()
manga.genre = removeLabel(genre)
manga.description = infoElement.select("div#divSpdInText").text()
// Some mangas like Shingeki no Kyojin have some links in description.
manga.description = infoElement.select("article").first()
?.text()?.substringBefore("Relacionados:")
manga.status = infoElement.select("li:contains(Status: )").first()?.text().orEmpty().let { parseStatus(it) }
manga.thumbnail_url = infoElement.select(".thumbnail").first()?.attr("src")
manga.status = infoElement.select("li:contains(Status:)").text()
.orEmpty().let { parseStatus(it) }
manga.thumbnail_url = document.select("div#page > section > div > img.thumbnail").attr("src")
return manga
}
@ -97,87 +100,79 @@ class MangaHost : ParsedHttpSource() {
else -> SManga.UNKNOWN
}
private fun removeLabel(text: String?): String {
return text!!.substring(text!!.indexOf(":") + 1)
}
private fun removeLabel(text: String?): String = text!!.substringAfter(":")
override fun chapterListSelector() :String {
return "section.clearfix.margin-bottom-20 ul.list_chapters li," +
"section.clearfix.margin-bottom-20 table.table-hover.table-condensed tbody tr"
}
override fun chapterListSelector(): String
= "ul.list_chapters li a," +
"table.table-hover:not(.table-mangas) > tbody > tr"
override fun chapterFromElement(element: Element): SChapter {
val isNewLayout = element.tagName() == "a"
val chapter: SChapter = SChapter.create()
if (isNewLayout) {
val content = Jsoup.parse(element.attr("data-content"))
val date = content.select("small.clearfix").text().substringAfter("Adicionado em ")
if (element.`is`("li")){
val urlChapterLong = element.select("a").toString()
val p2 = Pattern.compile("(?<=href=\\')(.+?)(?=\\')")
val p1 = Pattern.compile("(?<=Ler Online - )(.+)(?=\\[)")
val p3 = Pattern.compile("(?<=Adicionado em )(.+)(?=\\<)")
val p4 = Pattern.compile("(?<=Traduzido por \\<strong\\>\t\t\t\t\t\t)(.+)(?=\t\t\t\t\\<\\/)")
val m2 = p2.matcher(urlChapterLong)
val m1 = p1.matcher(urlChapterLong)
val m3 = p3.matcher(urlChapterLong)
val m4 = p4.matcher(urlChapterLong)
if (m2.find() && m1.find() && m3.find() && m4.find()) {
chapter.setUrlWithoutDomain(m2.group())
chapter.name = m1.group().toString()
chapter.date_upload = m3.group().let { parseChapterDate(it) }
chapter.scanlator = m4.group().toString()
return SChapter.create().apply {
name = element.attr("data-original-title").replace(LANG_REGEX.toRegex(), "")
scanlator = content.select("small.clearfix strong").text()
date_upload = parseChapterDate(date, DATE_FORMAT_NEW)
chapter_number = element.text().toFloatOrNull() ?: 1f
setUrlWithoutDomain(content.select("div.clearfix a").attr("href"))
}
}
else {
val firstColumn = element.select("td:eq(0)")
val secondColumn = element.select("td:eq(1)")
val thirdColumn = element.select("td:eq(2)")
val urlElement = element.select("a.capitulo").first()
chapter.setUrlWithoutDomain(element.select("a").first().attr("href"))
chapter.name = urlElement.text()
chapter.date_upload = element.select("td:eq(2)").text()?.let { parseChapterDate2(it) }?:0
chapter.scanlator = element.select("td:eq(1) a").attr("title")
return SChapter.create().apply {
name = firstColumn.select("a").text().replace(LANG_REGEX.toRegex(), "")
scanlator = secondColumn.text()
date_upload = parseChapterDate(thirdColumn.text(), DATE_FORMAT_OLD)
setUrlWithoutDomain(firstColumn.select("a").attr("href"))
}
return chapter
}
private fun parseChapterDate(date: String) : Long {
private fun parseChapterDate(date: String, format: String) : Long {
return try {
SimpleDateFormat("MMM d, yyyy", Locale.ENGLISH).parse(date).time
SimpleDateFormat(format, Locale.ENGLISH).parse(date).time
} catch (e: ParseException) {
0L
}
}
private fun parseChapterDate2(date: String) : Long {
return try {
SimpleDateFormat("dd/MM/yyyy", Locale.ENGLISH).parse(date).time
} catch (e: ParseException) {
0L
}
override fun pageListRequest(chapter: SChapter): Request {
// Just to prevent the detection of the crawler.
val newHeader = catalogHeaders.newBuilder()
.set("Referer", "$baseUrl${chapter.url}".substringBeforeLast("/"))
.build()
return GET(baseUrl + chapter.url, newHeader)
}
override fun pageListParse(document: Document): List<Page> {
var documentStr = document.toString()
var images = documentStr.substringAfter(SCRIPT_BEGIN).substringBefore(SCRIPT_END)
.replace(SCRIPT_REGEX.toRegex(), "")
val pages = mutableListOf<Page>()
var m : Matcher
var p : Pattern
val pageSize= mutableListOf<String>()
val links = document.select("script").toString()
document.select("div.pull-right > select.pages").first().getElementsByTag("option").forEach{
pageSize.add(it.attr("value"))
}
var newDocument = Jsoup.parse(images)
for (i in 1 until pageSize.size+1) {
p = Pattern.compile("(?<=\\'img_$i'\\ssrc=')(.+?)(?='\\s)")
m = p.matcher(links)
m.find()
pages.add(Page(i-1, "", m.group(1)))
}
return pages
return newDocument.select("a img")
.mapIndexed { i, el -> Page(i, "", el.attr("src")) }
}
override fun imageUrlParse(document: Document) = ""
companion object {
private const val LANG_REGEX = "( )?\\((PT-)?BR\\)"
private const val IMAGE_REGEX = "_(small|medium)\\."
private const val DATE_FORMAT_OLD = "dd/MM/yyyy"
private const val DATE_FORMAT_NEW = "MMM d, yyyy"
private const val SCRIPT_BEGIN = "var images = ["
private const val SCRIPT_END = "];"
private const val SCRIPT_REGEX = "\"|,"
}
}