make data extraction more general

scraper.py

@@ -68,7 +68,8 @@ 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")
@@ -91,6 +92,88 @@ def get_obchodneMeno(soup):
     return data
 
 
+def get_sidlo(soup):
+    data = {}
+
+    # find the table <tr> element of "Sídlo:"
+    sidlo_tr = get_data_td(soup, "Sídlo")
+    return data
+
+
+def get_ico(soup):
+    data = {}
+
+    return data
+
+
+def get_denZapisu(soup):
+    data = {}
+
+    return data
+
+
+def get_pravnaForma(soup):
+    data = {}
+
+    return data
+
+
+def get_predmetyCinnosti(soup):
+    data = {}
+
+    return data
+
+
+def get_spolocnici(soup):
+    data = {}
+
+    return data
+
+
+def get_vyskaVkladov(soup):
+    data = {}
+
+    return data
+
+
+def get_statutarnyOrgan(soup):
+    data = {}
+
+    return data
+
+
+def get_konanie(soup):
+    data = {}
+
+    return data
+
+
+def get_zakladneImanie(soup):
+    data = {}
+
+    return data
+
+
+def get_aktualizaciaUdajov(soup):
+    data = {}
+
+    return data
+
+
+def get_vypisUdajov(soup):
+    data = {}
+
+    return data
+
+
+def get_data(soup, name):
+    data_td = soup.find("span", class_="tl", string=re.compile(f"{name}")).parent.find_next_sibling("td")
+
+
+    return []
+
+
+
 def parse_oddo(text):
     """
     Parses the valid_from and valid_until from string
@@ -106,8 +189,9 @@ def parse_oddo(text):
 
     return valid_from, valid_until
 
+
 def test():
-    url = "https://www.orsr.sk/vypis.asp?ID=670947&SID=2&P=1"
+    url = "https://www.orsr.sk/vypis.asp?ID=12388&SID=8&P=1"
     html = requests.get(url)
     soup = BeautifulSoup(html.content, "html.parser")
 
@@ -115,20 +199,20 @@ def test():
         "oddiel":               get_oddiel(soup),
         "vlozka":               get_vlozka(soup),
         "obchodneMeno":         get_obchodneMeno(soup),
-        "sidlo":                "",
+        "sidlo":                get_sidlo(soup),
-        "ico":                  "",
+        "ico":                  get_ico(soup),
-        "denZapisu":            "",
+        "denZapisu":            get_denZapisu(soup),
-        "pravnaForma":          "",
+        "pravnaForma":          get_pravnaForma(soup),
-        "predmetyCinnosti":     "",
+        "predmetyCinnosti":     get_predmetyCinnosti(soup),
-        "spolocnici":           "",
+        "spolocnici":           get_spolocnici(soup),
-        "vyskaVkladov":         "",
+        "vyskaVkladov":         get_vyskaVkladov(soup),
-        "statutarnyOrgan":      "",
+        "statutarnyOrgan":      get_statutarnyOrgan(soup),
-        "konanie":              "",
+        "konanie":              get_konanie(soup),
-        "zakladneImanie":       "",
+        "zakladneImanie":       get_zakladneImanie(soup),
-        "aktualizaciaUdajov":   "",
+        "aktualizaciaUdajov":   get_aktualizaciaUdajov(soup),
-        "vypisUdajov":          ""
+        "vypisUdajov":          get_vypisUdajov(soup)
     }
-    print(json.dumps(record,indent=4))
+    print(json.dumps(record,indent=4,ensure_ascii=False))
     collection = connect_db()
     #collection.bulk_write(soup)
     disconnect_db(collection)