Skip to content

Reference for youtube_dl_scraper/core/youtube.py

youtube_dl_scraper.core.youtube.YouTube 

YouTube(video_scraper_name: Optional[str] = 'savetube', caption_scraper_name: Optional[str] = 'downsub', download_path: Optional[str] = 'downloads')

A class for scraping YouTube videos and captions using specified scrapers.

Parameters:

Name Type Description Default
video_scraper_name Optional[str]

The name of the video scraper (default is "savetube").

 'savetube'
caption_scraper_name Optional[str]

The name of the caption scraper (default is "downsub").

 'downsub'
download_path Optional[str]

The directory path where videos and captions will be saved (default is "downloads").

 'downloads'
Source code in youtube_dl_scraper/core/youtube.py 
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
def __init__(
    self,
    video_scraper_name: Optional[str] = "savetube",
    caption_scraper_name: Optional[str] = "downsub",
    download_path: Optional[str] = "downloads",
):
    """
    Initialize the YouTube scraper with the specified video and caption scrapers.

    Args:
        video_scraper_name (Optional[str]): The name of the video scraper (default is "savetube").
        caption_scraper_name (Optional[str]): The name of the caption scraper (default is "downsub").
        download_path (Optional[str]): The directory path where videos and captions will be saved (default is "downloads").
    """
    from . import Manager

    self.manager = Manager
    self.download_path = download_path or "/downloads"

    # Initialize video scraper
    video_scraper_class = self.manager.get_scraper_class(
        "video", video_scraper_name
    )
    self.video_scraper = video_scraper_class(self.download_path)
    self.video_scraper_name = video_scraper_name

    # Initialize caption scraper
    caption_scraper_class = self.manager.get_scraper_class(
        "caption", caption_scraper_name
    )
    self.caption_scraper = caption_scraper_class(self.download_path)
    self.caption_scraper_name = caption_scraper_name
async_scrape_captions async 
async_scrape_captions(url: str) -> CaptionArray

Asynchronously scrape captions from the given URL.

Parameters:

Name Type Description Default
url str

The URL of the video for which to scrape captions.

 required

Returns:

Name Type Description
CaptionArray CaptionArray

A CaptionArray object containing the scraped captions.

Raises:

Type Description
ScraperExecutionError

If an error occurs while scraping captions.
Source code in youtube_dl_scraper/core/youtube.py 
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
async def async_scrape_captions(self, url: str) -> CaptionArray:
    """
    Asynchronously scrape captions from the given URL.

    Args:
        url (str): The URL of the video for which to scrape captions.

    Returns:
        CaptionArray: A CaptionArray object containing the scraped captions.

    Raises:
        ScraperExecutionError: If an error occurs while scraping captions.
    """
    try:
        caption_data = await self.caption_scraper.async_scrape(url)
        captions = CaptionArray(caption_data, self.download_path)
        captions = self.caption_scraper.custom_prop(
            captions, caption_data
        )  # add custom properties
        return captions
    except Exception as e:
        raise ScraperExecutionError(self.caption_scraper_name, str(e))
async_scrape_video async 
async_scrape_video(url: str) -> Video

Asynchronously scrape video data from the given URL.

Parameters:

Name Type Description Default
url str

The URL of the video to scrape.

 required

Returns:

Name Type Description
Video Video

A Video object containing the scraped video data.

Raises:

Type Description
ScraperExecutionError

If an error occurs while scraping the video.
Source code in youtube_dl_scraper/core/youtube.py 
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
async def async_scrape_video(self, url: str) -> Video:
    """
    Asynchronously scrape video data from the given URL.

    Args:
        url (str): The URL of the video to scrape.

    Returns:
        Video: A Video object containing the scraped video data.

    Raises:
        ScraperExecutionError: If an error occurs while scraping the video.
    """
    try:
        video_data = await self.video_scraper.async_scrape(url)
        vid = Video(video_data, self.download_path)
        vid = self.video_scraper.custom_prop(
            vid, video_data
        )  # add custom properties
        return vid
    except Exception as e:
        raise ScraperExecutionError(self.video_scraper_name, str(e))
scrape_captions 
scrape_captions(url: str) -> CaptionArray

Synchronously scrape captions from the given URL.

Parameters:

Name Type Description Default
url str

The URL of the video for which to scrape captions.

 required

Returns:

Name Type Description
CaptionArray CaptionArray

A CaptionArray object containing the scraped captions.

Raises:

Type Description
ScraperExecutionError

If an error occurs while scraping captions.
Source code in youtube_dl_scraper/core/youtube.py 
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
def scrape_captions(self, url: str) -> CaptionArray:
    """
    Synchronously scrape captions from the given URL.

    Args:
        url (str): The URL of the video for which to scrape captions.

    Returns:
        CaptionArray: A CaptionArray object containing the scraped captions.

    Raises:
        ScraperExecutionError: If an error occurs while scraping captions.
    """
    try:
        caption_data = self.caption_scraper.scrape_captions(url)
        captions = CaptionArray(caption_data, self.download_path)
        captions = self.caption_scraper.custom_prop(
            captions, caption_data
        )  # add custom properties
        return captions
    except Exception as e:
        raise ScraperExecutionError(self.caption_scraper_name, str(e))
scrape_video 
scrape_video(url: str) -> Video

Synchronously scrape video data from the given URL.

Parameters:

Name Type Description Default
url str

The URL of the video to scrape.

 required

Returns:

Name Type Description
Video Video

A Video object containing the scraped video data.

Raises:

Type Description
ScraperExecutionError

If an error occurs while scraping the video.
Source code in youtube_dl_scraper/core/youtube.py 
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
def scrape_video(self, url: str) -> Video:
    """
    Synchronously scrape video data from the given URL.

    Args:
        url (str): The URL of the video to scrape.

    Returns:
        Video: A Video object containing the scraped video data.

    Raises:
        ScraperExecutionError: If an error occurs while scraping the video.
    """
    try:
        video_data = self.video_scraper.scrape(url)
        vid = Video(video_data, self.download_path)
        vid._get_captions = lambda: self.scrape_captions(url)
        vid = self.video_scraper.custom_prop(
            vid, video_data
        )  # add custom properties
        return vid
    except Exception as e:
        raise ScraperExecutionError(self.video_scraper_name, str(e))