gald/galdistream
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

Replace requests with urllib for HTTP requests in JSON file retrieval, enhancing compatibility and removing the test_regex.py file as it is no longer needed.

Browse Source
This commit is contained in:
gald
2025-07-29 19:18:09 +02:00
parent da4b380b1e
commit c92f583609
2 changed files with 17 additions and 56 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
main.py
View File

@@ -6,19 +6,25 @@
import sys import sys
import galdPl import galdPl
import requests import urllib.request
import urllib.parse
import re import re
import os import os
def get_json_files_from_folder(folder): def get_json_files_from_folder(folder):
base_url = "https://git.gald.site/gald/galdistream/src/branch/main/resources/" base_url = "https://git.gald.site/gald/galdistream/src/branch/main/resources/"
url = base_url + folder url = base_url + folder
r = requests.get(url, timeout=10)
r.raise_for_status() # Použijeme urllib místo requests
req = urllib.request.Request(url)
req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36')
with urllib.request.urlopen(req, timeout=10) as response:
html_content = response.read().decode('utf-8')
# Hledáme JSON soubory pomocí regex # Hledáme JSON soubory pomocí regex
json_pattern = r'href="(/gald/galdistream/src/branch/main/resources/[^"]*\.json)"' json_pattern = r'href="(/gald/galdistream/src/branch/main/resources/[^"]*\.json)"'
matches = re.findall(json_pattern, r.text) matches = re.findall(json_pattern, html_content)
files = [] files = []
for match in matches: for match in matches:
@@ -41,11 +47,15 @@ def update_json_db():
url = base_url_raw + file url = base_url_raw + file
local_path = "resources/" + file local_path = "resources/" + file
try: try:
r = requests.get(url, timeout=10) req = urllib.request.Request(url)
r.raise_for_status() req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36')
with urllib.request.urlopen(req, timeout=10) as response:
content = response.read()
os.makedirs(os.path.dirname(local_path), exist_ok=True) os.makedirs(os.path.dirname(local_path), exist_ok=True)
with open(local_path, "wb") as f: with open(local_path, "wb") as f:
f.write(r.content) f.write(content)
except Exception as e: except Exception as e:
print(f"Chyba při stahování {file}: {e}") print(f"Chyba při stahování {file}: {e}")

49
test_regex.py
View File

@@ -1,49 +0,0 @@
import requests
import re
import os
def get_json_files_from_folder(folder):
base_url = "https://git.gald.site/gald/galdistream/src/branch/main/resources/"
url = base_url + folder
r = requests.get(url, timeout=10)
r.raise_for_status()
# Hledáme JSON soubory pomocí regex
json_pattern = r'href="(/gald/galdistream/src/branch/main/resources/[^"]*\.json)"'
matches = re.findall(json_pattern, r.text)
files = []
for match in matches:
# Extrahujeme pouze název souboru
file_name = match.split("/")[-1]
files.append(file_name)
return files
def update_json_db():
base_url_raw = "https://git.gald.site/gald/galdistream/raw/branch/main/resources/"
folders = ["movies", "series"]
all_files = []
for folder in folders:
try:
files = get_json_files_from_folder(folder)
print(f"Nalezené soubory v {folder}: {files}")
all_files += [f"{folder}/{file}" for file in files]
except Exception as e:
print(f"Chyba při získávání souborů ze složky {folder}: {e}")
print(f"Celkem souborů ke stažení: {len(all_files)}")
for file in all_files:
url = base_url_raw + file
local_path = "resources/" + file
try:
r = requests.get(url, timeout=10)
r.raise_for_status()
os.makedirs(os.path.dirname(local_path), exist_ok=True)
with open(local_path, "wb") as f:
f.write(r.content)
print(f"Staženo: {file}")
except Exception as e:
print(f"Chyba při stahování {file}: {e}")
if __name__ == '__main__':
update_json_db()