Merge pull request #163 from Techwolfy/upstream-nsfw-tagging

Fix missing NSFW tags on several comics

dosagelib/plugins/a.py

@@ -352,20 +352,17 @@ class AntiheroForHire(_ParserScraper):
     imageSearch = '//div[@class="image-wrapper"]//img[not(@class="thumb-image")]'
     multipleImagesPerStrip = True
     endOfLife = True
-    archive = []
 
     def starter(self):
         # Build list of chapters for navigation
         page = self.getPage(self.url)
-        archiveLinks = page.xpath('//ul[@class="archive-group-list"]//a[contains(@class, "archive-item-link")]')
+        self.chapters = page.xpath('//ul[@class="archive-group-list"]//a[contains(@class, "archive-item-link")]/@href')
-        for link in archiveLinks:
+        return self.chapters[0]
-            self.archive.append(link.get('href'))
-        return self.archive[0]
 
     def getPrevUrl(self, url, data):
         # Retrieve previous chapter from list
-        index = self.archive.index(url) + 1
+        index = self.chapters.index(url) + 1
-        return self.archive[index] if index < len(self.archive) else None
+        return self.chapters[index] if index < len(self.chapters) else None
 
 
 class AppleGeeks(_BasicScraper):

dosagelib/plugins/b.py

@@ -123,6 +123,7 @@ class BetterDays(_ParserScraper):
     firstStripUrl = stripUrl % '2003/04/post-2'
     imageSearch = '//img[contains(@src, "/betterdays/comic/")]'
     prevSearch = '//a[contains(text(), "Previous")]'
+    adult = True
     endOfLife = True
     help = 'Index format: yyyy/mm/<your guess>'
 

dosagelib/plugins/comicfury.py

@@ -49,7 +49,7 @@ class ComicFury(_ParserScraper):
     help = 'Index format: n'
     starter = bounceStarter
 
-    def __init__(self, name, sub, lang=None):
+    def __init__(self, name, sub, lang=None, adult=False):
         super(ComicFury, self).__init__('ComicFury/' + name)
         self.prefix = name
         self.url = 'http://%s.webcomic.ws/comics/' % sub
@@ -57,6 +57,8 @@ class ComicFury(_ParserScraper):
         self.firstStripUrl = self.stripUrl % '1'
         if lang:
             self.lang = lang
+        if adult:
+            self.adult = adult
 
     def namer(self, image_url, page_url):
         parts = page_url.split('/')
@@ -376,7 +378,7 @@ class ComicFury(_ParserScraper):
             cls('Droned', 'droned'),
             cls('DRouggs', 'drouggs'),
             cls('DrugsAndKisses', 'd-and-k'),
-            cls('Druids', 'druids'),
+            cls('Druids', 'druids', adult=True),
             cls('DubCity', 'dubcity'),
             cls('DueEast', 'dueeast'),
             cls('DuelingHeroes', 'duelingheroes'),

dosagelib/plugins/f.py

@@ -95,6 +95,7 @@ class Flipside(_ParserScraper):
     firstStripUrl = stripUrl % '1'
     imageSearch = '//img[contains(@src, "comic/")]'
     prevSearch = '//a[@rel="prev"]'
+    adult = True
     help = 'Index format: nnnn'
 
 

dosagelib/plugins/keenspot.py

@@ -10,6 +10,8 @@ class KeenSpot(_ParserScraper):
     multipleImagesPerStrip = True
     imageSearch = (
         '//img[contains(@src, "/comics/")]',
+        # Gene Catlow Alternate
+        '//img[contains(@src, "/altcomics/")]',
         # Shockwave Darkside
         '//img[contains(@src, "/comics2D/")]',
         '//img[contains(@src, "com/shockwave")]',
@@ -34,7 +36,7 @@ class KeenSpot(_ParserScraper):
     )
     help = 'Index format: yyyymmdd'
 
-    def __init__(self, name, sub, last=None, path='d/%s.html'):
+    def __init__(self, name, sub, last=None, adult=False, path='d/%s.html'):
         super(KeenSpot, self).__init__('KeenSpot/' + name)
         self.url = 'http://%s.keenspot.com/' % sub
         self.stripUrl = self.url + path
@@ -43,12 +45,16 @@ class KeenSpot(_ParserScraper):
             self.url = self.stripUrl % last
             self.endOfLife = True
 
+        if adult:
+            self.adult = adult
+
     @classmethod
     def getmodules(cls):
         return (
             # Not on frontpage...
             cls('Buzzboy', 'buzzboy'),
             cls('EveryoneLovesAdis', 'adis'),
+            cls('GeneCatlowAlternate', 'genecatlow', last='20170302', adult=True, path='altd/%s.html'),
 
             # do not edit anything below since these entries are generated from
             # scripts/update_plugins.sh

dosagelib/plugins/n.py

@@ -103,22 +103,30 @@ class Nicky510(_WPNavi):
 
 
 class Nightshift(_ParserScraper):
-    url = 'http://poecatcomix.com/comic-titles/nightshift/'
+    url = 'https://poecatcomix.com/nightshift-static/'
-    stripUrl = url + '%s/'
+    stripUrl = 'https://poecatcomix.com/comic/%s/'
-    firstStripUrl = stripUrl % 'nightshift-volume1/ns-chapter-1'
+    firstStripUrl = stripUrl % 'ns1-page-cover'
-    imageSearch = '//div[@id="gallery-1"]//img'
+    imageSearch = '//div[@class="mangapress-media-img"]/img'
-    prevSearch = ('//a[./span[text()="PAST CHAPTER"]]',
+    prevSearch = '//li[@class="link-prev"]/a'
-                  '//a[./span[text()="LAST CHAPTER"]]')
+    latestSearch = '//li[@class="link-last"]/a/@href'
-    latestSearch = '//a[./img[contains(@src, "Latest-Page")]]'
-    starter = indirectStarter
-    multipleImagesPerStrip = True
     adult = True
 
+    def starter(self):
+        # Build list of chapters for navigation
+        indexPage = self.getPage(self.url)
+        self.chapters = indexPage.xpath('//a[./img[contains(@class, "attachment-large")]]/@href')
+        chapterPage = self.getPage(self.chapters[-1])
+        return chapterPage.xpath(self.latestSearch)[0]
+
+    def getPrevUrl(self, url, data):
+        # Retrieve previous chapter from list
+        if url in self.chapters:
+            chapterPage = self.getPage(self.chapters[self.chapters.index(url) - 1])
+            return chapterPage.xpath(self.latestSearch)[0]
+        return super(Nightshift, self).getPrevUrl(url, data)
+
     def namer(self, imageUrl, pageUrl):
-        # Prepend chapter title to page filenames
+        return pageUrl.rstrip('/').rsplit('/', 1)[-1] + '.' + imageUrl.rsplit('.', 1)[-1]
-        chapter = pageUrl.rstrip('/').rsplit('/', 1)[-1].replace('ns-', 'ns1-')
-        page = imageUrl.rsplit('/', 1)[-1]
-        return chapter + '_' + page
 
 
 class Nimona(_ParserScraper):

dosagelib/plugins/o.py

@@ -133,6 +133,7 @@ class OriginalLife(_ParserScraper):
     firstStripUrl = stripUrl % '2009/06/001'
     imageSearch = '//img[contains(@src, "/originallife/comic/")]'
     prevSearch = '//a[contains(text(), "Previous")]'
+    adult = True
     help = 'Index format: yyyy/mm/<your guess>'
 
 
@@ -149,6 +150,7 @@ class OutOfPlacers(_WordPressScraper):
     url = 'http://www.valsalia.com/'
     stripUrl = url + 'comic/%s/'
     firstStripUrl = stripUrl % 'prologue/01'
+    adult = True
 
 
 class OverCompensating(_BasicScraper):

dosagelib/plugins/p.py

@@ -67,6 +67,7 @@ class PeanutBerrySundae(_ParserScraper):
                    '//img[contains(@src, "page")]')
     latestSearch = '//a[contains(@href, "peanut-berry-sundae")]'
     starter = indirectStarter
+    adult = True
 
     def getPrevUrl(self, url, data):
         # Replace missing navigation links

dosagelib/plugins/petitesymphony.py

@@ -19,19 +19,21 @@ class PetiteSymphony(_WPNavi):
     @classmethod
     def getmodules(cls):
         return (
-            cls("knuckleup"),
+            cls('knuckleup'),
-            cls("sangria"),
+            cls('sangria'),
         )
 
 
 class ComicsBreak(_WordPressScraper):
-    def __init__(self, name, archive=None):
+    def __init__(self, name, archive=None, adult=False):
         super(ComicsBreak, self).__init__('ComicsBreak/' + name)
         self.url = 'http://%s.comicsbreak.com/' % name.lower()
         if archive:
             self.url = 'https://web.archive.org/web/{}/{}'.format(
                 archive, self.url)
             self.endOfLife = True
+        if adult:
+            self.adult = adult
 
     def namer(self, imageUrl, pageUrl):
         if self.name == 'ComicsBreak/Djandora':
@@ -49,5 +51,5 @@ class ComicsBreak(_WordPressScraper):
     def getmodules(cls):
         return (
             cls('Djandora', archive='20170923062433'),
-            cls("Generation17"),
+            cls('Generation17', adult=True),
         )

dosagelib/plugins/r.py

@@ -138,6 +138,7 @@ class Ryugou(_WPWebcomic):
     stripUrl = url + 'comic/%s/'
     firstStripUrl = 'ryugou-chapter-1-cover'
     starter = bounceStarter
+    adult = True
 
     def namer(self, imageUrl, pageUrl):
         title = pageUrl.rstrip('/').rsplit('/', 1)[-1]