diff --git a/builder/htmlprocessor/processor.sh b/builder/htmlprocessor/processor.sh
new file mode 100644
index 0000000..5fb0240
--- /dev/null
+++ b/builder/htmlprocessor/processor.sh
@@ -0,0 +1,5 @@
+
+for interval in 0 1 2 3 4 5 6 7;
+ do python strip.py $1 $2 $3 $interval 8
+ done
+
\ No newline at end of file
diff --git a/builder/htmlprocessor/strip.py b/builder/htmlprocessor/strip.py
index 73d6a53..6e1d224 100644
--- a/builder/htmlprocessor/strip.py
+++ b/builder/htmlprocessor/strip.py
@@ -1,46 +1,87 @@
import sys
+import os
+import urllib
-if len(sys.argv) == 1:
- print "Usage: " + sys.argv[0] + " [optional output file]"
- exit(1)
+reload(sys)
+sys.setdefaultencoding('utf-8')
from bs4 import BeautifulSoup
-soup = BeautifulSoup(open(sys.argv[1]))
-content = soup.find("div", {"id": "content"})
+def cleanUp(soup):
+ content = soup.find("div", {"id": "content"})
-# remove all specified tags
-[s.decompose() for s in content(['noscript'])]
+ # remove all specified tags
+ [s.decompose() for s in content(['noscript'])]
-[s.decompose() for s in content.findAll("a", {"id": "mw-mf-last-modified"})]
-[s.decompose() for s in content.findAll("span", {"class": "mw-editsection"})]
-[s.decompose() for s in content.findAll("table", {"class": "articleState"})]
-[s.decompose() for s in content.findAll("button", {"class": "languageSelector"})]
-[s.decompose() for s in content.findAll("a", {"class": "section_anchors"})]
-[s.decompose() for s in content.findAll("div", {"id": "mw-mf-language-section"})]
+ [s.decompose() for s in content.findAll("a", {"id": "mw-mf-last-modified"})]
+ [s.decompose() for s in content.findAll("span", {"class": "mw-editsection"})]
+ [s.decompose() for s in content.findAll("table", {"class": "articleState"})]
+ [s.decompose() for s in content.findAll("button", {"class": "languageSelector"})]
+ [s.decompose() for s in content.findAll("a", {"class": "section_anchors"})]
+ [s.decompose() for s in content.findAll("div", {"id": "mw-mf-language-section"})]
-# Wrap content with our own header and body
-content = content.wrap(soup.new_tag("body"))
-content = content.wrap(soup.new_tag("html"))
-# Here we add our own js and css into the
-headTag = soup.new_tag("head")
-cType = soup.new_tag("meta", content="text/html; charset=UTF-8")
-# workaround as we can't use dashes in python names
-cType["http-equiv"] = "Content-Type"
-headTag.append(cType)
-headTag.append(soup.new_tag("link", rel="stylesheet", type="text/css", href="article.css"))
-headTag.append(soup.new_tag("script", type="text/javascript", href="article.js"))
-meta1 = soup.new_tag("meta", content="yes")
-# workaround as "name" is used in python
-meta1["name"] = "apple-mobile-web-app-capable"
-headTag.append(meta1)
-meta2 = soup.new_tag("meta", content="initial-scale=1.0, user-scalable=yes, minimum-scale=0.25, maximum-scale=1.6")
-meta2["name"] = "viewport"
-headTag.append(meta2)
-content.body.insert_before(headTag)
+ # Wrap content with our own header and body
+ content = content.wrap(soup.new_tag("body"))
+ content = content.wrap(soup.new_tag("html"))
+ # Here we add our own js and css into the
+ headTag = soup.new_tag("head")
+ cType = soup.new_tag("meta", content="text/html; charset=UTF-8")
+ # workaround as we can't use dashes in python names
+ cType["http-equiv"] = "Content-Type"
+ headTag.append(cType)
+ headTag.append(soup.new_tag("link", rel="stylesheet", type="text/css", href="article.css"))
+ headTag.append(soup.new_tag("script", type="text/javascript", href="article.js"))
+ meta1 = soup.new_tag("meta", content="yes")
+ # workaround as "name" is used in python
+ meta1["name"] = "apple-mobile-web-app-capable"
+ headTag.append(meta1)
+ meta2 = soup.new_tag("meta", content="initial-scale=1.0, user-scalable=yes, minimum-scale=0.25, maximum-scale=1.6")
+ meta2["name"] = "viewport"
+ headTag.append(meta2)
+ content.body.insert_before(headTag)
+ return content
+
+def imageExist(fileName):
+ global imageFiles
+ return urllib.unquote(fileName).lower() in imageFiles
-if len(sys.argv) == 3:
- open(sys.argv[2], "w").write(content.prettify().encode('utf-8'))
-else:
- print(content.prettify().encode('utf-8'))
+def rewriteImages(soup):
+ imgTag = soup.findAll("img");
+
+ for imgElement in imgTag:
+ del imgElement['alt']
+ #todo rewrite srcset attr if we can get callback on image loading in webview
+ del imgElement['srcset']
+
+ index = -1
+ if "thumb" in imgElement['src'] and not '.pdf' in imgElement['src'].split("/")[-2]:
+ index = -2
+ imageName = imgElement['src'].split("/")[index]
+ if imageExist(imageName):
+ imgElement['src'] = "images/" + imageName
+ else:
+ [s.decompose() for s in imgElement.fetchParents("div", {"class" : "thumb tright"})]
+
+def writeHtml(content, fileName):
+ global outDir
+ open(os.path.join(outDir, fileName), "w").write(content.prettify().encode('utf-8'))
+
+##############################################################################
+if len(sys.argv) < 6:
+ print "Usage: " + sys.argv[0] + "