-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
031098f
commit 6ce1097
Showing
15 changed files
with
369,355 additions
and
380,392 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,105 @@ | ||
| def oscrapuj_cd(slozka, soubor): | ||
| # Pre-compile regular expressions for better performance | ||
| date_pattern = re.compile(r'\d{4}-\d{2}-\d{2}_\d{2}-\d{2}-\d{2}') | ||
| time_pattern = re.compile(r'\d{1,2}:\d\d') | ||
|
|
||
| with open(os.path.join(slozka, soubor), "r", encoding="utf-8") as file: | ||
| raw_html = file.read() | ||
|
|
||
| # Extract date once instead of per iteration | ||
| oscrapovano = date_pattern.search(soubor).group(0) | ||
| oscrapovano_dt = datetime.strptime(oscrapovano, "%Y-%m-%d_%H-%M-%S") | ||
|
|
||
| # Split only once and store results | ||
| spojeni = raw_html.split("<article")[1:] | ||
|
|
||
| # Define common strings as constants to avoid string creation in loop | ||
| COMMON_STRINGS = { | ||
| 'to_train': 'text: to(lastTrain($index()))', | ||
| 'from_train': 'text: from(firstTrain($index()))', | ||
| 'journey_date': 'text: journeyDateTextFrom()', | ||
| 'dep_time': 'text: depTime(firstTrain($index()))', | ||
| 'buy_button': 'text: buyButtonText()', | ||
| 'train_type': 'text: model.trainTypeAndNum', | ||
| 'occupancy': '<span aria-hidden="true" data-bind="visible: occupancyLevelFull(), text: occupancyLevelText()"', | ||
| 'time_length': '<span data-bind="text: timeLength, visible: timeLength != null && timeLength != \'\'"', | ||
| 'distance': '<span data-bind="text: distance, visible: distance != null && distance != \'"', | ||
| 'delay': '<span aria-hidden="true" data-bind="text: delayText()">' | ||
| } | ||
|
|
||
| slovniky = [] | ||
|
|
||
| for s in spojeni: | ||
| # Initialize dictionary with default values | ||
| slovnik = { | ||
| 'prodejce': "ČD", | ||
| 'vlaky': [], | ||
| 'obsazenost': [], | ||
| 'zpozdeni': [], | ||
| 'oscrapovano': oscrapovano_dt, | ||
| 'prostredek': 'vlak' | ||
| } | ||
|
|
||
| lines = s.splitlines() | ||
| den = None | ||
| cas_odjezdu = None | ||
|
|
||
| for radek in lines: | ||
| # Use dictionary lookup instead of multiple if statements | ||
| if COMMON_STRINGS['to_train'] in radek: | ||
| slovnik['kam'] = radek.split('>')[-2].split('<')[0] | ||
| elif COMMON_STRINGS['from_train'] in radek: | ||
| slovnik['odkud'] = radek.split('>')[-2].split('<')[0] | ||
| elif COMMON_STRINGS['journey_date'] in radek and not den: | ||
| den = radek.split('>')[-2].split('<')[0] | ||
| elif COMMON_STRINGS['dep_time'] in radek: | ||
| cas_odjezdu = time_pattern.search(radek).group(0) | ||
| elif COMMON_STRINGS['buy_button'] in radek: | ||
| cena = radek.split('-->')[1].split('<!--')[0].replace(" Kč","") | ||
| try: | ||
| slovnik['cena'] = int(cena) | ||
| except ValueError: | ||
| pass | ||
| elif COMMON_STRINGS['train_type'] in radek: | ||
| vlak = radek.split('-->')[1].split('<!--')[0] | ||
| if vlak not in slovnik['vlaky']: | ||
| slovnik['vlaky'].append(vlak) | ||
| elif COMMON_STRINGS['occupancy'] in radek: | ||
| slovnik['obsazenost'].append(radek.split('>')[-2].split('<')[0]) | ||
| elif COMMON_STRINGS['time_length'] in radek: | ||
| jizdni_doba = radek.split('>')[-2].split('<')[0].split(":") | ||
| slovnik['jizdni_doba'] = (int(jizdni_doba[0]) * 60) + int(jizdni_doba[1][:2]) | ||
| elif COMMON_STRINGS['distance'] in radek: | ||
| try: | ||
| slovnik['vzdalenost'] = int(radek.split('>')[-2].split('<')[0].replace(" km","")) | ||
| except ValueError: | ||
| pass | ||
| elif "Náhradní autobusová doprava" in radek: | ||
| slovnik['nahradni_bus'] = True | ||
| elif COMMON_STRINGS['delay'] in radek: | ||
| if "+" in radek: | ||
| try: | ||
| slovnik['zpozdeni'].append(int(radek.split('+')[1].strip().split(' ')[0])) | ||
| except ValueError: | ||
| slovnik['zpozdeni'].append('chyba') | ||
| elif "><" in radek: | ||
| slovnik['zpozdeni'].append(0) | ||
| elif "Místenka zdarma" in radek: | ||
| slovnik['mistenka_zdarma'] = True | ||
|
|
||
| if den and cas_odjezdu: | ||
| slovnik['den'] = den.split(' ')[0].lower().strip() | ||
| date_str = '-'.join(den.split(' ')[1].split('.')[::-1]) | ||
| slovnik['odjezd'] = datetime.strptime(f"{date_str} {cas_odjezdu}", "%Y-%m-%d %H:%M") | ||
| slovnik['predstih'] = slovnik['odjezd'] - slovnik['oscrapovano'] | ||
|
|
||
| # Post-processing | ||
| if len(slovnik['vlaky']) == 1 and slovnik['obsazenost']: | ||
| slovnik['obsazenost'] = [slovnik['obsazenost'][0]] | ||
|
|
||
| slovnik['zpozdeni'] = slovnik['zpozdeni'][1::2] | ||
| slovnik['prestupy'] = len(slovnik['vlaky']) - 1 | ||
|
|
||
| slovniky.append(slovnik) | ||
|
|
||
| return [x for x in slovniky if x] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.