From 1a7d5b424aad29c8fd26c4822b27904a6ceaf5ad Mon Sep 17 00:00:00 2001
From: Benjamin Loison <benjamin.loison@orange.fr>
Date: Mon, 1 May 2023 23:15:23 +0200
Subject: [PATCH] Add `{scanlibs,bookys}.py`

---
 bookys.py   | 25 +++++++++++++++++++++++++
 scanlibs.py | 45 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 70 insertions(+)
 create mode 100644 bookys.py
 create mode 100644 scanlibs.py

diff --git a/bookys.py b/bookys.py
new file mode 100644
index 0000000..0496f16
--- /dev/null
+++ b/bookys.py
@@ -0,0 +1,25 @@
+import requests
+
+def getContentFromURL(url):
+    return requests.get(url).text
+
+c = 0
+
+for i in range(36, 203):#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]
+            print(title)
+            print()
+            c += 1
+
diff --git a/scanlibs.py b/scanlibs.py
new file mode 100644
index 0000000..80b9836
--- /dev/null
+++ b/scanlibs.py
@@ -0,0 +1,45 @@
+import requests, re
+from lxml import html
+from xml.etree.ElementTree import XML, fromstring
+
+def getContentFromURL(url):
+    return requests.get(url).text
+
+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']
+    print(loc)
+    print(entry['lastmod'])
+    print(entry['image:image']['image:loc'])
+    while True:
+        content = getContentFromURL(loc)
+        tree = html.fromstring(content)
+        title = content.split('<title>')[1].split('</title>')[0]
+        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]
+    print(meta)
+    description = content.split('"></span>')[1].split('<a class="rewlink"')[0]
+    print(description)
+    print()
\ No newline at end of file