From 205c83790c8ddc5b6e0d463cded0810b429bb0e5 Mon Sep 17 00:00:00 2001
From: Christopher Arndt <chris@chrisarndt.de>
Date: Wed, 8 May 2024 16:20:55 +0200
Subject: [PATCH] Update beispiele

Signed-off-by: Christopher Arndt <chris@chrisarndt.de>
---
 beispiele/http1.py     | 34 ++++++++++++++++++++++++++++++++++
 beispiele/readfile6.py |  6 ++++--
 2 files changed, 38 insertions(+), 2 deletions(-)
 create mode 100644 beispiele/http1.py

diff --git a/beispiele/http1.py b/beispiele/http1.py
new file mode 100644
index 0000000..4f4fd67
--- /dev/null
+++ b/beispiele/http1.py
@@ -0,0 +1,34 @@
+import sys
+import requests
+import lxml.html
+
+base_url = "https://en.wikipedia.org/"
+if len(sys.argv) >= 2:
+    url = base_url + sys.argv[1]
+else:
+    url = "https://en.wikipedia.org/wiki/Python_(programming_language)"
+
+resp = requests.get(url)
+
+see_also = []
+
+if resp.status_code == 200:
+    html = resp.text
+    #print(html[:100])
+    tree = lxml.html.fromstring(html)
+
+    see_also_heading = tree.xpath("//span[@id='See_also']")[0].getparent()
+
+    for sibling in see_also_heading.itersiblings():
+        hrefs = sibling.xpath("li/a")
+
+        for href in hrefs:
+            title = href.get("title")
+            see_also_url = href.get("href")
+            #print(title, see_also_url)
+            ## TODO
+            ## Parse URL from command line with urlllib.parse.urlsplit()
+            ## and concatenate base URL and relative URL from link
+            see_also.append((title, base_url + see_also_url))
+
+print(see_also)
\ No newline at end of file
diff --git a/beispiele/readfile6.py b/beispiele/readfile6.py
index efabef5..afa3a93 100644
--- a/beispiele/readfile6.py
+++ b/beispiele/readfile6.py
@@ -24,11 +24,13 @@ try:
                 print(f"Warning: could not parse line {i+1}: {exc}")
             else:
                 try:
-                    items = [int(item) for item in raw_data.split(",")]          # split raw data at commas
+                    # split raw data at commas
+                    items = [int(item.strip()) for item in raw_data.split(",")]
                 except (ValueError, TypeError) as exc:
                     print(f"Warning: could not parse data on line {i+1}: {exc}")
+                else:
+                    data[name.strip()] = items
 
-            data[name.strip()] = items
 except OSError as exc:
     print(f"Could not open file {filename}: {exc}")