Skip to content

yutorah

YutorahExtractor

Bases: Extractor

Extract audio content from YUTorah.org.

This extractor handles URLs from www.yutorah.org and extracts MP3 download links along with their associated titles from the page's JavaScript content.

Source code in src/torah_dl/core/extractors/yutorah.py 
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
class YutorahExtractor(Extractor):
    """Extract audio content from YUTorah.org.

    This extractor handles URLs from www.yutorah.org and extracts MP3 download
    links along with their associated titles from the page's JavaScript content.
    """

    name: str = "YUTorah"
    homepage: str = "https://yutorah.org"

    EXAMPLES = [  # noqa: RUF012
        ExtractionExample(
            name="main_page",
            url="https://www.yutorah.org/lectures/1116616/Praying-for-Rain-and-the-International-Traveler",
            download_url="https://download.yutorah.org/2024/986/1116616/praying-for-rain-and-the-international-traveler.mp3",
            title="Praying for Rain and the International Traveler",
            file_format="audio/mp3",
            valid=True,
        ),
        ExtractionExample(
            name="short_link",
            url="https://www.yutorah.org/lectures/1117459/",
            download_url="https://download.yutorah.org/2024/986/1117459/davening-with-strep-throat.mp3",
            title="Davening with Strep Throat",
            file_format="audio/mp3",
            valid=True,
        ),
        ExtractionExample(
            name="shiurid_link",
            url="https://www.yutorah.org/lectures/details?shiurid=1117409",
            download_url="https://download.yutorah.org/2024/21197/1117409/ketubot-42-dechitat-aveilut-1.mp3",
            title="Ketubot 42: Dechitat Aveilut (1)",
            file_format="audio/mp3",
            valid=True,
        ),
        ExtractionExample(
            name="invalid_link",
            url="https://www.yutorah.org/lectures/details?shiurid=0000000",
            download_url="",
            title="",
            file_format="",
            valid=False,
        ),
    ]

    # URL pattern for YUTorah.org pages
    URL_PATTERN = re.compile(r"https?://(?:www\.)?yutorah\.org/")

    # Pattern to find download URL in script tags
    DOWNLOAD_URL_PATTERN = re.compile(r'"downloadURL":"(https?://[^\"]+\.mp3)"')

    @property
    def url_patterns(self) -> list[Pattern]:
        """Return the URL pattern(s) that this extractor can handle.

        Returns:
            List[Pattern]: List of compiled regex patterns matching YUTorah.org URLs
        """
        return [self.URL_PATTERN]

    def extract(self, url: str) -> Extraction:
        """Extract download URL and title from a YUTorah.org page.

        Args:
            url: The YUTorah.org URL to extract from

        Returns:
            Extraction: Object containing the download URL and title

        Raises:
            ValueError: If the URL is invalid or content cannot be extracted
            requests.RequestException: If there are network-related issues
        """
        try:
            response = requests.get(url, timeout=30, headers={"User-Agent": "torah-dl/1.0"})
            response.raise_for_status()
        except requests.RequestException as e:
            raise NetworkError(str(e)) from e  # pragma: no cover

        # Parse the page content
        soup = BeautifulSoup(response.content, "html.parser")
        script_tag = soup.find("script", string=self.DOWNLOAD_URL_PATTERN)

        if not script_tag:
            raise DownloadURLError()

        # Extract download URL
        match = self.DOWNLOAD_URL_PATTERN.search(str(script_tag))
        if not match:
            raise DownloadURLError()

        download_url = match.group(1)

        file_name = download_url.split("/")[-1]

        # Extract and decode title
        try:
            title_tag = soup.find("h2", itemprop="name")
            title = title_tag.text if title_tag else None

        except (UnicodeError, IndexError) as e:
            raise TitleExtractionError(str(e)) from e

        if not download_url or not title:
            raise ContentExtractionError()

        return Extraction(download_url=download_url, title=title, file_format="audio/mp3", file_name=file_name)

url_patterns property 

url_patterns: list[Pattern]

Return the URL pattern(s) that this extractor can handle.

Returns:

Type Description
list[Pattern]

List[Pattern]: List of compiled regex patterns matching YUTorah.org URLs

extract 

extract(url: str) -> Extraction

Extract download URL and title from a YUTorah.org page.

Parameters:

Name Type Description Default
url str

The YUTorah.org URL to extract from

 required

Returns:

Name Type Description
Extraction Extraction

Object containing the download URL and title

Raises:

Type Description
ValueError

If the URL is invalid or content cannot be extracted
RequestException

If there are network-related issues
Source code in src/torah_dl/core/extractors/yutorah.py 
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
def extract(self, url: str) -> Extraction:
    """Extract download URL and title from a YUTorah.org page.

    Args:
        url: The YUTorah.org URL to extract from

    Returns:
        Extraction: Object containing the download URL and title

    Raises:
        ValueError: If the URL is invalid or content cannot be extracted
        requests.RequestException: If there are network-related issues
    """
    try:
        response = requests.get(url, timeout=30, headers={"User-Agent": "torah-dl/1.0"})
        response.raise_for_status()
    except requests.RequestException as e:
        raise NetworkError(str(e)) from e  # pragma: no cover

    # Parse the page content
    soup = BeautifulSoup(response.content, "html.parser")
    script_tag = soup.find("script", string=self.DOWNLOAD_URL_PATTERN)

    if not script_tag:
        raise DownloadURLError()

    # Extract download URL
    match = self.DOWNLOAD_URL_PATTERN.search(str(script_tag))
    if not match:
        raise DownloadURLError()

    download_url = match.group(1)

    file_name = download_url.split("/")[-1]

    # Extract and decode title
    try:
        title_tag = soup.find("h2", itemprop="name")
        title = title_tag.text if title_tag else None

    except (UnicodeError, IndexError) as e:
        raise TitleExtractionError(str(e)) from e

    if not download_url or not title:
        raise ContentExtractionError()

    return Extraction(download_url=download_url, title=title, file_format="audio/mp3", file_name=file_name)