update,

bf_helloworld_1-extract.py

@@ -0,0 +1,44 @@
+#!/usr/bin/env python
+
+import os,sys
+from pprint import pprint
+from bs4 import BeautifulSoup
+import requests
+
+main_url = "https://www.mchk.org.hk/english/list_register/list.php?page=4&ipp=20&type=L"
+req = requests.get(main_url)
+soup = BeautifulSoup(req.text, "html.parser")
+
+title = soup.find("h1")
+
+trs = soup.select("table#Table_5 table tr")
+
+for tr in trs[2:]:
+    try:
+      # name
+      tds = tr.select('td[headers="reg"]')
+      if (len(tds) > 0):
+        # reg field got something
+        print(tds[0].get_text())
+
+        # # name
+        tds = tr.select('td[headers="name"]')
+        print(tds[0].get_text())
+
+        # # qualification
+        tds = tr.select('td[headers="qualification"]')
+        print(tds[0].get_text())
+        print(tds[1].get_text())
+        pass
+      else:
+        # reg field got nothing
+        tds = tr.select('td[headers="qualification"]')
+        for i in range(0, len(tds), 2):
+          pprint(f'{tds[i].get_text()}, {tds[i+1].get_text()}')
+        pass
+    except Exception as e:
+      print(tr)
+      print(e)
+      print('error')
+      pass
+