Fix #1: Add XML native use without requiring xmltodict

bookys.py

@@ -1,4 +1,6 @@
-import requests, xmltodict
+import requests
+from lxml import html
+from xml.etree.ElementTree import fromstring
 
 def getContentFromURL(url):
     return requests.get(url).text
@@ -10,9 +12,9 @@ for i in range(1, 203):
     print(i)
     url = f'https://ww9.bookys-ebooks.com/sitemaps/items{i}.xml'
     sitemapContent = getContentFromURL(url)
-    jsonData = xmltodict.parse(sitemapContent)['urlset']['url'][1:]
-    for entry in jsonData:
-        loc = entry['loc']
+    sitemapXML = fromstring(sitemapContent)
+    for entry in sitemapXML:
+        loc = entry.findtext('{*}loc')
         if loc.startswith('https://ww9.bookys-ebooks.com/livres/'):
             print(i, c)
             print(loc)

scanlibs.py

@@ -1,6 +1,6 @@
-import requests, re, xmltodict
+import requests
 from lxml import html
-#from xml.etree.ElementTree import fromstring
+from xml.etree.ElementTree import fromstring
 
 def getContentFromURL(url):
     return requests.get(url).text
@@ -8,24 +8,13 @@ def getContentFromURL(url):
 sitemapUrl = 'https://scanlibs.com/sitemap.xml'
 
 sitemapContent = getContentFromURL(sitemapUrl)
-"""
 sitemapXML = fromstring(sitemapContent)
 
-for elem in sitemapXML.iter():
-    for el in elem.iter():
-        print(el.tag, ':', el.text)
-    #print('!', elem.text, '!')
-
-import xmltodict, json
-"""
-
-jsonData = xmltodict.parse(sitemapContent)['urlset']['url'][1:]
-
-for entry in jsonData:
-    loc = entry['loc']
+for entry in sitemapXML.findall('{*}url')[1:]:
+    loc = entry.findtext('{*}loc')
     print(loc)
-    print(entry['lastmod'])
-    print(entry['image:image']['image:loc'])
+    print(entry.findtext('{*}lastmod'))
+    print(entry.find('{*}image').findtext('{*}loc'))
     while True:
         content = getContentFromURL(loc)
         tree = html.fromstring(content)