Add requests and html parsing example

Signed-off-by: Christopher Arndt <chris@chrisarndt.de>

beispiele/data-errors.txt

@@ -0,0 +1,5 @@
+record 1: 100, 300, 50, 200
+record 2 300, 450, 50, 100
+record 3: 150, 200, 0, 150
+record 4: 350, 200, 5O, 250
+record 5: 50, 100, 200, 300

beispiele/data.txt

@@ -0,0 +1,5 @@
+record 1: 100, 300, 50, 200
+record 2: 300, 450, 50, 100
+record 3: 150, 200, 0, 150
+record 4: 350, 200, 50, 250
+record 5: 50, 100, 200, 300

beispiele/readfile3.py

@@ -8,7 +8,7 @@ with open(filename, "r") as fileobj:
     max_linelength = 0
     longest_line = -1
 
-    for i, line in enumerate(data):
+    for i, line in enumerate(fileobj):
         if len(line) > max_linelength:
             max_linelength = len(line)
             longest_line = i + 1

beispiele/readfile4.py

@@ -2,12 +2,15 @@
 
 import sys
 
+if len(sys.argv) >= 2:
     filename = sys.argv[1]
+else:
+    filename = "data.txt"
 
 data = {}
 
 with open(filename, "r") as fileobj:
-    for i, line in enumerate(data):
+    for i, line in enumerate(fileobj):
         line = line.strip()  # remove whitespace from start/end of line
 
         if line.startswith('#'):

beispiele/readfile5.py

@@ -0,0 +1,29 @@
+#!/usr/bin/env python
+
+import sys
+
+if len(sys.argv) >= 2:
+    filename = sys.argv[1]
+else:
+    filename = "data.txt"
+
+data = {}
+
+try:
+    with open(filename, "r") as fileobj:
+        for i, line in enumerate(fileobj):
+            line = line.strip()  # remove whitespace from start/end of line
+
+            if line.startswith('#'):
+                # ignore comment lines
+                continue
+
+            name, raw_data = line.split(":", 1)  # split line at first colon
+            items = raw_data.split(",")          # split raw data at commas
+
+            data[name.strip()] = items
+except OSError as exc:
+    print(f"Could not open file {filename}: {exc}")
+
+for key in data:
+    print(key, data[key])

beispiele/readfile6.py

@@ -0,0 +1,36 @@
+#!/usr/bin/env python
+
+import sys
+
+if len(sys.argv) >= 2:
+    filename = sys.argv[1]
+else:
+    filename = "data.txt"
+
+data = {}
+
+try:
+    with open(filename, "r") as fileobj:
+        for i, line in enumerate(fileobj):
+            line = line.strip()  # remove whitespace from start/end of line
+
+            if line.startswith('#'):
+                # ignore comment lines
+                continue
+
+            try:
+                name, raw_data = line.split(":", 1)  # split line at first colon
+            except ValueError as exc:
+                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
+                except (ValueError, TypeError) as exc:
+                    print(f"Warning: could not parse data on line {i+1}: {exc}")
+
+            data[name.strip()] = items
+except OSError as exc:
+    print(f"Could not open file {filename}: {exc}")
+
+for key in data:
+    print(key, data[key])

beispiele/wp_crawler1.py

@@ -0,0 +1,52 @@
+#!/usr/bin/env python
+
+import sys
+import urllib.parse as urlparse
+
+import requests
+import lxml.html
+
+
+def find_see_also_links(tree):
+
+    # get heading element of "See also" section using XPath
+    see_also_heading = tree.xpath("//span[@id='See_also']")[0].getparent()
+
+    # find following UL element, which contains the LI elements with the actual links
+    for sibling in see_also_heading.itersiblings():
+        hrefs = sibling.xpath("li/a")
+
+        if hrefs:
+            return [(href.text, href.get("href")) for href in hrefs]
+
+        if sibling.tag.startswith("h"):
+            break
+
+
+def main():
+    if len(sys.argv) < 2:
+        sys.exit("Usage: wp_crawler.py <url>")
+
+    url = sys.argv[1]
+    url_parts = urlparse.urlsplit(url)
+    base_url =  urlparse.urlunsplit(list(url_parts[:3]) + ['', ''])
+
+    resp = requests.get(url)
+
+    if not resp.status_code == 200:
+        sys.exit(f"Could not retrive URL '{url}'. Aborting.")
+    tree = lxml.html.fromstring(resp.text)
+
+    links = find_see_also_links(tree)
+
+    if links:
+        for title, url in links:
+            if not url.startswith("https://"):
+                if url.startswith("/"):
+                    url = urlparse.urljoin(base_url, url)
+
+            print(title, url)
+
+
+if __name__ == '__main__':
+    main()