Scrap author and illustrator (may not work for some books)

media/scraper.py

@@ -56,6 +56,8 @@ class BedetequeScraper:
         regex_subtitle = r'<h2>\s*(.*)</h2>'
         regex_publish_date = r'datePublished\" content=\"([\d-]*)\">'
         regex_nb_of_pages = r'numberOfPages\">(\d*)</span'
+        regex_author = r'<span itemprop=\"author\">(((?!<).)*)</span>'
+        regex_illustrator = r'<span itemprop=\"illustrator\">(((?!<).)*)</span>'
 
         data = {
             'external_url': bd_url,
@@ -87,4 +89,16 @@ class BedetequeScraper:
         if search_nb_pages and search_nb_pages.group(1).isnumeric():
             data['number_of_pages'] = search_nb_pages.group(1)
 
+        # Get author and illustrator
+        author = re.search(regex_author, content)
+        if not 'author' in data:
+            data['author'] = list()
+        if author:
+            data['author'].append(author.group(1))
+        illustrator = re.search(regex_illustrator, content)
+        if illustrator:
+            data['author'].append(illustrator.group(1))
+
+        print(data)
+
         return data