Created AltTextEPUB class and implemented methods from AltText abstract class.

src/alttext/alttext.py

@@ -1,8 +1,12 @@
 from abc import ABC, abstractmethod
 import typing
+import warnings
 import bs4
+import ebooklib
+from ebooklib import epub
 
 class AltText(ABC):
+    # PARSING METHODS
     @abstractmethod
     def checkData(self):
         pass
@@ -28,17 +32,27 @@ class AltText(ABC):
     def exportToFile(self, path:str):
         pass
 
+def getSoup(content : str) -> bs4.BeautifulSoup:
+    try:
+        return bs4.BeautifulSoup(content, "html.parser")
+    except Exception as htmlErr:
+        try:
+            return bs4.BeautifulSoup(content, features="xml")
+        except Exception as xmlErr:
+            raise Exception(f"Failed to parse the document as HTML: {htmlErr}\nFailed to parse the document as XML: {xmlErr}")
+
+
 class AltTextHTML(AltText):
-    def __init__(self):
+    def __init__(self) -> None:
         return None
 
-    def checkData(self):
+    def checkData(self) -> bool:
         if not hasattr(self, "data"):
             raise Exception("no data set. please use .parse or .parseFile")
         return True
 
     def parse(self, html:str) -> bs4.BeautifulSoup:
-        soup = bs4.BeautifulSoup(html, "html.parser")
+        soup = getSoup(html, "html.parser")
         self.data = soup
         return soup
     
@@ -52,7 +66,6 @@ class AltTextHTML(AltText):
         return imgs
     
     def getNoAltImgs(self) -> typing.List[bs4.element.Tag]:
-        self.checkData()
         imgs = self.getAllImgs()
         noalt = []
         for img in imgs:
@@ -76,3 +89,61 @@ class AltTextHTML(AltText):
         with open(path, 'w', encoding='utf-8') as file:
             file.write(html)
         return path
+
+class AltTextEPUB(AltText):
+    def __init__(self) -> None:
+        return None
+    
+    def checkData(self) -> bool:
+        if not hasattr(self, "data"):
+            raise Exception("no data set. please use .parse or .parseFile")
+        return True
+
+    def parse(self, html:str):
+        raise Exception("parse: IMPLEMENT ME")
+
+    def parseFile(self, filename:str) -> epub.EpubBook:
+        book = epub.read_epub(filename, {"ignore_ncx": True})
+        self.data = book
+        return book
+
+    def getAllImgs(self) -> typing.List[bs4.element.Tag]:
+        documents = self.data.get_items_of_type(ebooklib.ITEM_DOCUMENT)
+        imgs = []
+        for docs in documents:
+            # features="xml"
+            soup = getSoup(docs.get_content())
+            imgsInDoc = soup.find_all("img")
+            for img in imgsInDoc:
+                imgs.append(img)
+        return imgs
+
+    def getNoAltImgs(self) -> typing.List[bs4.element.Tag]:
+        imgs = self.getAllImgs()
+        noalt = []
+        for img in imgs:
+            if not "alt" in img.attrs.keys() or img.attrs["alt"].strip() == "":
+                noalt.append(img)
+        return noalt
+
+    def setAlt(self, src:str, text:str):
+        self.checkData()
+        documents = self.data.get_items_of_type(ebooklib.ITEM_DOCUMENT)
+        for doc in documents:
+            soup = getSoup(doc.get_content())
+            imgsInDoc = soup.find_all("img")
+            for img in imgsInDoc:
+                if img.attrs["src"] == src:
+                    img.attrs["alt"] = text
+                    newHtml = soup.prettify()
+                    doc.set_content(newHtml.encode('utf-8'))
+                    return
+        raise Exception("unable to find image with src '{src}'".format(src=src))
+
+    def export(self):
+        self.checkData()
+        return self.data
+
+    def exportToFile(self, path:str) -> str:
+        epub.write_epub(path, self.export())
+        return path

tests/test.py

@@ -1,21 +1,44 @@
 import sys
 sys.path.append("../")
-import src.alttext_FEF.alttext as alttext
+import src.alttext.alttext as alttext
+import ebooklib
 
-if __name__ == "__main__":
+HTML1 = "../books/pg71856-h/pg71856-images.html"
+HTML2 = "../books/pg71859-h/pg71859-images.html"
+
+EPUB1 = "../books/pg71856-images-3.epub"
+EPUB2 = "../books/pg71908-images-3.epub"
+EPUB3 = "../books/seuss.epub"
+
+def testHTML():
     ## MAIN TEST
-    print("TESTING index.py")
-    alt:alttext.AltTextHTML = alttext.AltTextHTML()
+    print("TESTING HTML")
+    altHTML:alttext.AltTextHTML = alttext.AltTextHTML()
 
     ## PARSE TEST
     html = '<html><head><title>Test</title></head><body><img src="test"/><h1>Parse me!</h1><img src="test2"/></body></html>'
-    alt.parse(html)
+    altHTML.parse(html)
 
     ## PARSEFILE TEST
-    path1 = "../books/pg71856-h/pg71856-images.html"
-    path2 = "../books/pg71859-h/pg71859-images.html"
-    alt.parseFile(path1)
+    altHTML.parseFile(HTML1)
 
     ## GETALLIMGS & SETALT TEST
-    imgs = alt.getNoAltImgs()
-    print(imgs)
+    imgs = altHTML.getNoAltImgs()
+    print(imgs)
+
+def testEPUB():
+    print("TESTING EPUB")
+    altEPUB:alttext.AltTextEPUB = alttext.AltTextEPUB()
+
+    altEPUB.parseFile(EPUB2)    
+    imgs = altEPUB.getNoAltImgs()
+    print(imgs)
+    # img = imgs[0]
+    # print(img)
+    # src = img.attrs["src"]
+    # altEPUB.setAlt(src, "TEST ALT")
+    # print(altEPUB.getAllImgs())
+
+if __name__ == "__main__":
+    # testHTML()
+    testEPUB()