Skip to content

Reference for youtube_dl_scraper/site_scrapers/caption_scrapers/downsub.py

youtube_dl_scraper.site_scrapers.caption_scrapers.downsub.DownSub 

DownSub(download_path: str)

Bases: BaseScraper

A scraper wrapper for downsub.com

Source code in youtube_dl_scraper/core/base_scraper.py 
7
8
def __init__(self, download_path: str):
    self.download_path = download_path
generate_payload 
generate_payload(url: str) -> str

generate payload to fetch caption endpoint

Source code in youtube_dl_scraper/site_scrapers/caption_scrapers/downsub.py 
76
77
78
def generate_payload(self, url: str) -> str:
    """generate payload to fetch caption endpoint"""
    return f"url = '{url}'\n" + payload
parse_caption_data 
parse_caption_data(data: dict) -> dict

parse data from the caption endpoint to a general format

Source code in youtube_dl_scraper/site_scrapers/caption_scrapers/downsub.py 
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
def parse_caption_data(self, data: dict) -> dict:
    """parse data from the caption endpoint to a general format"""
    if data.get("sourceName") != "Youtube":
        raise CaptionsNotFoundError("Capition found but invalid caption type")
    captions_data = {}  # the formatted dictionary for caption data
    dl_api = data.get("urlSubtitle")
    captions_data["title"] = data.get("title", "")
    captions_data["thumbnail"] = data.get("thumbnail", "")
    captions_data["duration"] = data.get("duration")
    captions_data["subtitles"] = []
    for sub in data.get("subtitles", []):
        sub["code"] = (
            "a." + str(find_language(sub["name"]))
            if "auto" in sub["code"]
            else sub["code"]
        )
        captions_data["subtitles"].append(sub)
    captions_data["translations"] = []
    for sub in data.get("subtitlesAutoTrans", []):
        sub["code"] = str(find_language(sub["name"]))  # fetch lang code
        captions_data["translations"].append(sub)
    # add more formating to include dowload url for each formart i.e. srt, txt, raw
    translation_types = ("subtitles", "translations")
    for t_type in translation_types:
        subs = captions_data[t_type]  # subtitle dict
        for sub in subs:  # for subtitle in subtitles
            sub["urls"] = {
                "raw": f"{dl_api}?url={sub['url']}&type=raw&title={captions_data['title']}",
                "txt": f"{dl_api}?url={sub['url']}&type=txt&title={captions_data['title']}",
                "srt": f"{dl_api}?url={sub['url']}&title={captions_data['title']}",
            }
            sub.pop("url")

    # print(captions_data)
    return captions_data
process_response 
process_response(caption_endpoint: str) -> dict

fetch and processes data from the caption endpoint

Source code in youtube_dl_scraper/site_scrapers/caption_scrapers/downsub.py 
100
101
102
103
104
105
106
107
108
109
110
111
def process_response(self, caption_endpoint: str) -> dict:
    """fetch and processes data from the caption endpoint"""
    if not caption_endpoint:
        raise CaptionsNotFoundError("Caption endpoint is empty.")
    response = requests.get(caption_endpoint)
    if response.status_code == 200:
        data = response.json()
        return self.parse_caption_data(data) if data else None
    else:
        raise YouTubeDLScraperError(
            "Invalid response code: {}".format(response.status_code)
        )