1from __future__ import annotations
  2import logging
  3import bs4
  4from src.download import *
  5from basic_colors import *
  6from src.downloader.page_search import *
  7from src.link_to_file import Link_to_file, compare_sizes
  8
  9class Sdilej_downloader(Download_page_search):
 10    """
 11    Downloader from: sdilej.cz
 12    """
 13    webpage = "https://sdilej.cz"
 14
 15    logger = logging.getLogger("Sdilej_downloader")
 16    if not logger.hasHandlers():
 17        os.makedirs("logs", exist_ok=True)
 18        handler = logging.FileHandler("logs/sdilej_downloader.log", encoding="utf-8")
 19        formatter = logging.Formatter("%(asctime)s %(levelname)s: %(message)s")
 20        handler.setFormatter(formatter)
 21        logger.addHandler(handler)
 22        logger.setLevel(logging.INFO)
 23    
 24    def __init__(self):
 25        pass
 26    
 27    def search(self, prompt, file_type="all", search_type="relevance") -> 'Generator[Link_to_file, None, None]':
 28        if prompt is None or prompt.strip() == "":
 29            raise ValueError("Prompt cannot be empty.")
 30        url = Sdilej_downloader.generate_search_url(prompt, file_type, search_type)
 31        Sdilej_downloader.logger.info(f"Searching Sdilej with URL: {url}")
 32        response = requests.get(url)
 33        Sdilej_downloader.logger.info(f"Response received: {response.status_code}")
 34        return Sdilej_downloader.parse_catalogue(response)
 35
 36    @staticmethod
 37    def generate_search_url(prompt, file_type="all", search_type="relevance"):
 38        """
 39        generate url from input
 40        """
 41        return f"{Sdilej_downloader.webpage}/{prompt}/s/{Sdilej_downloader.file_types[file_type]}-{Sdilej_downloader.search_types[search_type]}"
 42
 43    @staticmethod
 44    def get_atributes_from_catalogue(soup) -> Link_to_file:
 45        try:
 46            link = soup.find("a").get("href")
 47            title = soup.find("a").get("title")
 48            size = soup.find_all("p")[1].text
 49            link_2_file = Link_to_file(title, link, size, Sdilej_downloader)
 50        except Exception as e:
 51            raise ValueError("ERROR: unable to parse atributes." + str(e))
 52        return link_2_file
 53
 54    @staticmethod
 55    def get_atributes_from_file_page(soup) -> Link_to_file:
 56        try:
 57            title = soup.find("h1").text
 58            size = soup.find("b").next_sibling.replace("|", "").strip()
 59            link = Sdilej_downloader.webpage+str(soup.find("a", class_="btn btn-danger").get("href"))
 60            link_2_file = Link_to_file(title, link, size, Sdilej_downloader)
 61        except Exception as e:
 62            raise ValueError("Download button not found on detail page." + str(e))
 63        return link_2_file
 64    
 65    @staticmethod
 66    def get_download_link_from_detail(detail_url: str) -> str:
 67        """
 68        Získá přímý odkaz ke stažení ze stránky s detailem souboru na sdilej.cz.
 69        """
 70        page = download_page(detail_url)
 71        soup = bs4.BeautifulSoup(page.text, "html.parser")
 72        # Najdi tlačítko pro stažení
 73        download_btn = soup.find("a", class_="btn btn-danger")
 74        if not download_btn:
 75            raise ValueError("Download button not found on detail page for: {}".format(detail_url))
 76        download_link = Sdilej_downloader.webpage + str(download_btn.get("href"))
 77        return download_link
 78
 79    @staticmethod
 80    def is_valid_download_page(page) -> bool:
 81        """
 82        Stránka neplatná, pokud obsahuje: 
 83        <h1 class="red">Stahuj a nahrávej soubory neomezenou rychlostí</h1>
 84        "Tento soubor byl smazán."
 85        """
 86        soup = bs4.BeautifulSoup(page.text, "html.parser")
 87        invalid_texts = (
 88            "Stahuj a nahrávej soubory neomezenou rychlostí", 
 89            "Chyba 404 Nenalezeno",
 90            "Tento soubor byl smazán."
 91        )
 92        page_title = soup.find("h1", class_="red")
 93        if page_title is not None and page_title.text in invalid_texts:
 94            return False
 95        
 96        soup = remove_style(soup)
 97        page_txt = soup.find("div", class_="content")
 98        if page_txt is not None:
 99            text = remove_empty_lines(page_txt.text)
100            if any_text_coresponds_to(text, invalid_texts):
101                return False
102        return True
103    
104    @staticmethod
105    def test_downloaded_file(link_2_file, download_folder) -> bool:
106        file_size = os.path.getsize(f"{download_folder}/{link_2_file.title}")
107        if file_size == 0:
108            raise ValueError("ERROR: File is empty.")
109        elif link_2_file.size != None and file_size < 1024:
110            file = os.path.join(download_folder, link_2_file.title)
111            data = open(file, "r", encoding='utf-8').read()
112            return Sdilej_downloader.test_downloaded_data(data)
113        elif link_2_file.size != None and not compare_sizes(file_size, link_2_file.size, 20/100):
114            raise ValueError("ERROR: File size does not match.")
115        return True
116
117    @staticmethod
118    def test_downloaded_data(data) -> bool:
119        """
120        Tests the downloaded data.
121        The data is invalid if a sufficient timeout has occurred.
122        If the page contains:
123        "<script>top.location.href='https://sdilej.cz/free-stahovani';</script>"
124        "<h1 class=\"red\">Stahování více souborů najednou</h1>"
125        """
126        if data is None:
127            raise ValueError("ERROR: No data downloaded.")
128        if "<script>top.location.href='https://sdilej.cz/free-stahovani';</script>" in data:
129            raise InsufficientTimeoutError()
130        if "<h1 class=\"red\">Stahování více souborů najednou</h1>" in data:
131            raise InsufficientTimeoutError()
132        return True
133
134    @staticmethod
135    def parse_file_page(page):
136        if not Sdilej_downloader.is_valid_download_page(page):
137            raise ValueError("Status code: " + str(page.status_code) + ". Invalid download page: no file to download.")
138        soup = bs4.BeautifulSoup(page.text, "html.parser")
139        content = soup.find("div", class_="content")
140        content = soup.find("div", class_="col-md-12 col-sm-12 detail-leftcol")
141        return content
142
143    @staticmethod
144    def parse_catalogue(page) -> 'Generator[Link_to_file, None, None]':
145        """
146        Iterates through the search results page and returns information about the files.
147
148        Yields: Link_to_file
149        """
150        soup = bs4.BeautifulSoup(page.text, "html.parser")
151        content = soup.find("div", class_="row post")
152        if content is None:
153            return None
154        content = remove_style(content)
155        for videobox in content.find_all(class_="videobox-desc"):
156            catalogue_file = None
157            try:
158                catalogue_file = Sdilej_downloader.get_atributes_from_catalogue(videobox)
159                download_page_content = Sdilej_downloader.parse_file_page(download_page(catalogue_file.detail_url))
160                link_2_file = Sdilej_downloader.get_atributes_from_file_page(download_page_content)
161                link_2_file.detail_url = catalogue_file.detail_url  # zachovej původní detail_url!
162                yield link_2_file
163            except ValueError as e:
164                print_error(str(e) + " for file: " + (catalogue_file.title if catalogue_file else "Unknown"), False)