Update BookShelfScrape v1.1

AkertProjects · web-flow · commit a3f086cbd3ca · 2017-01-28T18:50:18.000-07:00
diff --git a/BookShelfScrape v1.1 b/BookShelfScrape v1.1
@@ -61,6 +61,7 @@ with requests.Session() as s:
             for span_tag in soupReading.findAll('span'):
                 span_tag.replace_with('')
             title = subReading['title']
+            title = " ".join(re.findall("[a-zA-Z0-9.]+", title))
             print('Now Scraping Reading: %s' % title)
             # Grabbing all of the blue boxes which are denoted by "figure" in the HTML
             # Trying to also save them off as word documents, with both text and tables
@@ -69,11 +70,11 @@ with requests.Session() as s:
                 readingFile = open('%s.html' % title, 'wb')
                 for figure in figures:
                     for image_tag in figure.findAll('img'):
-                        image_tag['src'] = 'https://jigsaw.vitalsource.com/books/' + str(book['isbn']) + '/epub' + image_tag['src']
+                        image_tag['src'] = 'https://jigsaw.vitalsource.com/books/' + str(book['isbn']) + '/epub/OEBPS/' + image_tag['src']
                     readingFile.write(figure.encode('UTF-8'))
                 readingFile.close()
             else:
                 continue
-        print('Done! Enjoy!')
+    print('Done! Enjoy!')
 
 
