From 0583199a16cad984891563c384b43bc2a18e919c Mon Sep 17 00:00:00 2001
From: Benjamin Loison <benjamin.loison@orange.fr>
Date: Mon, 1 May 2023 23:30:57 +0200
Subject: [PATCH] Use `XPath` instead of unstable `split`s

---
 bookys.py   | 10 +++++-----
 scanlibs.py | 16 +++++++---------
 2 files changed, 12 insertions(+), 14 deletions(-)

diff --git a/bookys.py b/bookys.py
index 0496f16..44d35a5 100644
--- a/bookys.py
+++ b/bookys.py
@@ -1,24 +1,24 @@
-import requests
+import requests, xmltodict
 
 def getContentFromURL(url):
     return requests.get(url).text
 
 c = 0
 
-for i in range(36, 203):#1, 203):
+# 36 is the first `i` value containing `livres`.
+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:
-        #print(entry)
         loc = entry['loc']
         if loc.startswith('https://ww9.bookys-ebooks.com/livres/'):
-            #print(entry)
             print(i, c)
             print(loc)
             content = getContentFromURL(loc)
-            title = content.split('<title>')[1].split('\n')[0]
+            tree = html.fromstring(content)
+            title = tree.xpath('/html/body/div/div/div[2]/div[1]/div/div[2]/div[2]/h1')[0].text.strip()
             print(title)
             print()
             c += 1
diff --git a/scanlibs.py b/scanlibs.py
index 80b9836..4ba76d4 100644
--- a/scanlibs.py
+++ b/scanlibs.py
@@ -1,6 +1,6 @@
-import requests, re
+import requests, re, xmltodict
 from lxml import html
-from xml.etree.ElementTree import XML, fromstring
+#from xml.etree.ElementTree import fromstring
 
 def getContentFromURL(url):
     return requests.get(url).text
@@ -29,17 +29,15 @@ for entry in jsonData:
     while True:
         content = getContentFromURL(loc)
         tree = html.fromstring(content)
-        title = content.split('<title>')[1].split('</title>')[0]
+        title = tree.xpath('/html/head/title')[0].text
         if not title.startswith('503 Service Temporarily Unavailable'):
             break
         else:
             print('MISS')
     print(title)
-    print()
-    continue
-    metaPattern = 'border-bottom:1px solid #f0f0f0">'
-    meta = content.split(metaPattern)[1].split('</p>')[0]
+    meta = tree.xpath('/html/body/div[1]/div/article/div/div/div/div/div[1]/p[1]')[0].text
     print(meta)
-    description = content.split('"></span>')[1].split('<a class="rewlink"')[0]
+    description = tree.xpath('/html/body/div[1]/div/article/div/div/div/div/div[1]/p[2]')[0].text
     print(description)
-    print()
\ No newline at end of file
+    print()
+