From af2e57d85042b314b6b66dd062b560244f3ad5d8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Damjan=20Ko=C5=A1ir?= <damjan.kosir@gmail.com>
Date: Fri, 6 Nov 2015 23:47:24 +1300
Subject: [PATCH] Added comic ScurryAndCover...

- Yay, funky JavaScript parsing!
- Start page isn't latest comic...

Updated-by: Tobias Gruetzmacher <tobias-git@23.gs>
---
 dosagelib/plugins/s.py | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/dosagelib/plugins/s.py b/dosagelib/plugins/s.py
index 7e7c422a2..3b884dffe 100644
--- a/dosagelib/plugins/s.py
+++ b/dosagelib/plugins/s.py
@@ -144,6 +144,40 @@ class Science(_BasicScraper):
     help = 'Index format: stripname'
 
 
+class ScurryAndCover(_ParserScraper):
+    url = 'http://scurry.ink'
+    prevSearch = '//div[@id="prevpage"]/..'
+    nextSearch = '//div[@id="nextpage"]/..'
+    imageSearch = 'MARKER'
+
+    @classmethod
+    def fetchUrls(cls, url, data, urlSearch):
+        if urlSearch != cls.imageSearch:
+            return super(ScurryAndCover, cls).fetchUrls(url, data, urlSearch)
+
+        # get javascript element and parse a variable value
+        scripts = data.xpath('//body/script[@type="text/javascript"]')
+
+        regex = compile("var fileRoot = '([^']+)")
+        for script in scripts:
+            images = regex.findall(script.text)
+            if len(images) > 0:
+                image = images[0]
+                return [cls.url + '/images/pages/' + image + '-xsmall.png']
+
+    @classmethod
+    def starter(cls):
+        """Go forward as far as possibe, then start."""
+        url = cls.url
+        while True:
+            data = cls.getPage(url)
+            try:
+                url = cls.fetchUrl(url, data, cls.nextSearch)
+            except ValueError:
+                break
+        return url
+
+
 class SequentialArt(_BasicScraper):
     url = 'http://www.collectedcurios.com/sequentialart.php'
     stripUrl = url + '?s=%s'