working scraper

config.cfg

@@ -8,4 +8,4 @@
 #ENDPOINT = hladaj_zmeny.asp
 
 [APP]
-THREADS = 1
+THREADS = 32

config_base.cfg

@@ -1,5 +1,5 @@
 [DB]
-MONGODB_URI = mongodb://localhost:27017/softone
+MONGODB_URI = mongodb://localhost:27017
 MONGODB_DB = softone
 MONGODB_COLLECTION = orsr
 
@@ -8,4 +8,4 @@ BASE_URL = https://www.orsr.sk/
 ENDPOINT = hladaj_zmeny.asp
 
 [APP]
-THREADS = 4
+THREADS = 32

scraper.py

@@ -1,6 +1,7 @@
 import requests
 import re
 import json
+import unicodedata
 from bs4 import BeautifulSoup
 from tqdm.auto import tqdm
 from concurrent.futures import ThreadPoolExecutor
@@ -11,6 +12,13 @@ from app.db import connect_db, disconnect_db
 from time import sleep
 
 
+single_value = ["Obchodné meno:", "Sídlo:", "IČO:", "Deň zápisu:", "Právna forma:"]
+value_type_dict = {
+    "IČO:": "number",
+    "Spoločníci:": "spolocnici",
+    "Výška vkladu každého spoločníka:": "vklad"
+}
+
 def scrape_orsr():
     """
     This is the main function that scrapes data from endpoint defined in config and stores it in mongodb.
@@ -24,10 +32,11 @@ def scrape_orsr():
     # distribute the work in #of threads defined in config
     parts = [records[i::settings["threads"]] for i in range(settings["threads"])]
 
+    print(f"Processing {len(records)} records using {settings['threads']} threads:")
     with ThreadPoolExecutor() as t:
         for thread_id, part in enumerate(parts):
             t.submit(process_records, part, thread_id+1)
-    print("records_processed")
+    print("All records_processed")
 
 
 def process_records(records, thread):
@@ -37,7 +46,8 @@ def process_records(records, thread):
     :param thread: thread id of processing thread
     """
     data = []
-    for i in tqdm(range(len(records)), desc=f"thread {thread}"):
+    #for i in tqdm(range(len(records)), desc=f"thread {thread}"):
+    for i in tqdm(range(1), desc=f"thread {thread}"):
         record = process_record(records[i])
         data.append(InsertOne(record))
     collection = connect_db()
@@ -51,26 +61,12 @@ def process_record(url):
     :param url: url of the record
     :return dictionary of parameters
     """
+    url = "https://www.orsr.sk/vypis.asp?ID=471674&SID=4&P=1"
     html = requests.get(url)
     soup = BeautifulSoup(html.content, "html.parser")
 
-    record = {
-        "oddiel":               get_oddiel(soup),
-        "vlozka":               get_vlozka(soup),
-        "obchodneMeno":         get_data(soup, "Obchodné meno", allow_multiple_active=False),
-        "sidlo":                get_data(soup,"Sídlo", allow_multiple_active=False),
-        "ico":                  get_data(soup, "IČO", value_type="number" , allow_multiple_active=False),
-        "denZapisu":            get_data(soup, "Deň zápisu", allow_multiple_active=False),
-        "pravnaForma":          get_data(soup, "Právna forma", allow_multiple_active=False),
-        "predmetyCinnosti":     get_data(soup, "Predmet činnosti"),
-        "spolocnici":           get_data(soup, "Spoločníci", value_type="spolocnici"),
-        "vyskaVkladov":         get_data(soup, "Výška vkladu", value_type="vklad"),
-        "statutarnyOrgan":      get_data(soup, "Štatutárny orgán"),
-        "konanie":              get_data(soup, "Konanie menom"),
-        "zakladneImanie":       get_data(soup, "Základné imanie"),
-        "aktualizaciaUdajov":   get_aktualizaciaUdajov(soup),
-        "vypisUdajov":          get_vypisUdajov(soup)
-    }
+    record = get_record_data(soup)
+
     return record
 
 
@@ -94,31 +90,47 @@ def get_vypisUdajov(soup):
     return {"value": vypis}
 
 
-def get_obchodneMeno(soup):
-    data = {}
+def get_record_data(soup):
+    record = {
+        "oddiel": get_oddiel(soup),
+        "vlozka": get_vlozka(soup)
+    }
 
-    # find the table <tr> element of "Obchodné meno:"
-    meno_tr = soup.find("span", class_="tl", string=re.compile("Obchodné")).parent.parent
+    # find the last table before variable data
+    entry = soup.find("span", class_="tl", string=re.compile("Oddiel:")).parent.parent.parent
+    while True:
+        entry = entry.find_next_sibling("table")
+        entry_tr = entry.find_all("tr")
+        entry_tr = [i for i in entry_tr if i.parent == entry_tr[0].parent]
 
-    # parse the name and date
-    active = meno_tr.find_all("span", class_="ra")
-    active = [x.text.strip() for x in active]
-    if len(active) == 0:
-        value, valid_from, valid_until = "", ""
-    else:
-        value, valid = active[0], active[1]
-        valid_from, valid_until = parse_oddo(valid)
-    data.update({"value": value, "valid_from": valid_from, "valid_until": valid_until})
+        if len(entry_tr) > 1:  # last table with "Dátum aktualizácie údajov
+            break
 
-    # check for older entries
-    old = meno_tr.find_all("span", class_="ro")
-    old = [x.text.strip() for x in old]
-    if len(old) == 0:
-        old_values = []
-    else:
-        old_values = [{"value": y[0], "valid_from": y[1][0], "valid_until": y[1][1]} for y in zip(old[::2], list(map(parse_oddo,old[1::2])))]
-    data.update({"old_values": old_values})
-    return data
+        # get enry name and entry data
+        entry_container = entry_tr[0].find_all("td")
+        entry_name = entry_container[0].text.strip()
+
+        allow_multiple_active = True
+        value_type = "text"
+        if entry_name in single_value:
+            allow_multiple_active = False
+        if (v_type := value_type_dict.get(entry_name)) is not None:
+            value_type = v_type
+        entry_name = transform_entry_name(entry_name)
+        entry_data = get_data(entry_container[1], value_type=value_type, allow_multiple_active=allow_multiple_active)
+        record.update({entry_name: entry_data})
+
+    record.update({
+        "aktualizaciaUdajov": get_aktualizaciaUdajov(soup),
+        "vypisUdajov": get_vypisUdajov(soup)
+    })
+
+    return record
+
+
+def transform_entry_name(name):
+    s = unicodedata.normalize("NFKD",name).encode('ascii', 'ignore').decode().replace(":", "").lower().split()
+    return s[0].lower() + "".join(w.capitalize() for w in s[1:])
 
 
 def process_entry(entry, value_type):
@@ -137,7 +149,7 @@ def process_entry(entry, value_type):
     if value_td.span.attrs["class"][0] == "ra":
         active = True
 
-    lines = [f.strip() for f in " ".join(["\n" if x.name == "br" else x.text.strip() for x in value_td.find_all()]).split("\n") if f]
+    lines = [f.strip() for f in " ".join(["\n" if x.name == "br" else x.text.strip() for x in value_td.find_all(["br","span"])]).split("\n") if f]
 
     if value_type == "text":
         value = ", ".join(lines)
@@ -163,8 +175,8 @@ def process_entry(entry, value_type):
     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")
+def get_data(data_td, value_type="text", allow_multiple_active=True):
+    data_td = data_td
 
     data = {}
 
@@ -181,6 +193,7 @@ def get_data(soup, name, value_type="text", allow_multiple_active=True):
             old_values.append({"value": value, "valid_from": valid_from, "valid_until": valid_until})
 
     if not allow_multiple_active:
+        if len(values) > 0:
             data.update(values[0])
     else:
         data.update({"values": values})
@@ -205,35 +218,5 @@ def parse_oddo(text):
     return valid_from, valid_until
 
 
-def test():
-    url = "https://www.orsr.sk/vypis.asp?ID=12388&SID=8&P=1"
-    html = requests.get(url)
-    soup = BeautifulSoup(html.content, "html.parser")
-
-    record = {
-        "oddiel":               get_oddiel(soup),
-        "vlozka":               get_vlozka(soup),
-        "obchodneMeno":         get_data(soup, "Obchodné meno", allow_multiple_active=False),
-        "sidlo":                get_data(soup,"Sídlo", allow_multiple_active=False),
-        "ico":                  get_data(soup, "IČO", value_type="number" , allow_multiple_active=False),
-        "denZapisu":            get_data(soup, "Deň zápisu", allow_multiple_active=False),
-        "pravnaForma":          get_data(soup, "Právna forma", allow_multiple_active=False),
-        "predmetyCinnosti":     get_data(soup, "Predmet činnosti"),
-        "spolocnici":           get_data(soup, "Spoločníci", value_type="spolocnici"),
-        "vyskaVkladov":         get_data(soup, "Výška vkladu", value_type="vklad"),
-        "statutarnyOrgan":      get_data(soup, "Štatutárny orgán"),
-        "konanie":              get_data(soup, "Konanie menom"),
-        "zakladneImanie":       get_data(soup, "Základné imanie"),
-        "aktualizaciaUdajov":   get_aktualizaciaUdajov(soup),
-        "vypisUdajov":          get_vypisUdajov(soup)
-    }
-    print(json.dumps(record,indent=4,ensure_ascii=False))
-    collection = connect_db()
-    records = [InsertOne(record)]
-    collection.bulk_write(records)
-    disconnect_db(collection)
-
-
 if __name__ == "__main__":
     scrape_orsr()
-    #test()