parsing one entry

scraper.py

@@ -68,8 +68,7 @@ def get_obchodneMeno(soup):
     data = {}
 
     # find the table <tr> element of "Obchodné meno:"
-    #meno_tr = soup.find("span", class_="tl", string=re.compile("Obchodné")).parent.parent
+    meno_tr = soup.find("span", class_="tl", string=re.compile("Obchodné")).parent.parent
-    meno_tr = get_data_td(soup, "Obchodné")
 
     # parse the name and date
     active = meno_tr.find_all("span", class_="ra")
@@ -96,7 +95,6 @@ def get_sidlo(soup):
     data = {}
 
     # find the table <tr> element of "Sídlo:"
-    sidlo_tr = get_data_td(soup, "Sídlo")
     return data
 
 
@@ -166,12 +164,51 @@ def get_vypisUdajov(soup):
     return data
 
 
-def get_data(soup, name):
+def process_entry(entry, value_type):
+    """
+    extracts one entry from the table of entries for a given data
+    :param entry: one table element of data
+    :param value_type: type of the value data
+    :return: tuple: (value, valid_from, valid_until, active)
+
+    """
+    value, valid_from, valid_until, active = None, None, None, False
+
+    value_td, valid_td = entry.find_all("td")
+
+    # Check if active entry
+    if value_td.span.attrs["class"][0] == "ra":
+        active = True
+
+
+
+    return value, valid_from, valid_until, active
+
+
+def get_data(soup, name, value_type="text", allow_multiple_active=True):
     data_td = soup.find("span", class_="tl", string=re.compile(f"{name}")).parent.find_next_sibling("td")
 
+    data = {}
 
-    return []
+    values = []
+    old_values = []
 
+    for entry in data_td.find_all("table"):
+        value, valid_from, valid_until, active = process_entry(entry, value_type)
+        if value is None:
+            continue
+        if active:
+            values.append({"value": value, "valid_from": valid_from, "valid_until": valid_until})
+        else:
+            old_values.append({"value": value, "valid_from": valid_from, "valid_until": valid_until})
+
+    if not allow_multiple_active:
+        data.update(values[0])
+    else:
+        data.update({"values": values})
+    data.update({"old_values": old_values})
+
+    return data
 
 
 def parse_oddo(text):