Hugging Face's logo

Spaces:
xyz69
/
ryuzaki-api
Running

App Files Community
ryuzaki-api
File size: 5,091 Bytes 
6d78308
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
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
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
148
149
150
151
152
 
import datetime
import json
import os
import random
import re
import time
import urllib.parse
from urllib.parse import quote_plus

import httpx
import requests
from pytz import country_names, country_timezones, timezone
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.support.expected_conditions import presence_of_element_located
from selenium.webdriver.support.wait import WebDriverWait

class YoutubeDriver:
    def __init__(self, search_terms: str, max_results: int = 5):
        self.base_url = "https://youtube.com/results?search_query={0}"
        self.search_terms = search_terms
        self.max_results = max_results
        self.videos = self._search()

    def _search(self):
        encoded_search = urllib.parse.quote_plus(self.search_terms)
        response = requests.get(self.base_url.format(encoded_search)).text

        while "ytInitialData" not in response:
            response = requests.get(self.base_url.format(encoded_search)).text

        results = self._parse_html(response)

        if self.max_results is not None and len(results) > self.max_results:
            return results[: self.max_results]

        return results

    def _parse_html(self, response: str):
        results = []
        start = response.index("ytInitialData") + len("ytInitialData") + 3
        end = response.index("};", start) + 1
        json_str = response[start:end]
        data = json.loads(json_str)

        videos = data["contents"]["twoColumnSearchResultsRenderer"]["primaryContents"][
            "sectionListRenderer"
        ]["contents"][0]["itemSectionRenderer"]["contents"]

        for video in videos:
            res = {}
            if "videoRenderer" in video.keys():
                video_data = video.get("videoRenderer", {})
                _id = video_data.get("videoId", None)

                res["id"] = _id
                res["thumbnail"] = f"https://i.ytimg.com/vi/{_id}/hqdefault.jpg"
                res["title"] = (
                    video_data.get("title", {}).get("runs", [[{}]])[0].get("text", None)
                )
                res["channel"] = (
                    video_data.get("longBylineText", {})
                    .get("runs", [[{}]])[0]
                    .get("text", None)
                )
                res["duration"] = video_data.get("lengthText", {}).get("simpleText", 0)
                res["views"] = video_data.get("viewCountText", {}).get(
                    "simpleText", "Unknown"
                )
                res["publish_time"] = video_data.get("publishedTimeText", {}).get(
                    "simpleText", "Unknown"
                )
                res["url_suffix"] = (
                    video_data.get("navigationEndpoint", {})
                    .get("commandMetadata", {})
                    .get("webCommandMetadata", {})
                    .get("url", None)
                )

                results.append(res)
        return results

    def to_dict(self, clear_cache=True) -> list[dict]:
        result = self.videos
        if clear_cache:
            self.videos = []
        return result

    @staticmethod
    def check_url(url: str) -> tuple[bool, str]:
        if "&" in url:
            url = url[: url.index("&")]

        if "?si=" in url:
            url = url[: url.index("?si=")]

        youtube_regex = (
            r"(https?://)?(www\.)?"
            r"(youtube|youtu|youtube-nocookie)\.(com|be)/"
            r'(video|embed|shorts/|watch\?v=|v/|e/|u/\\w+/|\\w+/)?([^"&?\\s]{11})'
        )
        match = re.match(youtube_regex, url)
        if match:
            return True, match.group(6)
        else:
            return False, "Invalid YouTube URL!"

    @staticmethod
    def song_options() -> dict:
        return {
            "format": "bestaudio",
            "addmetadata": True,
            "key": "FFmpegMetadata",
            "prefer_ffmpeg": True,
            "geo_bypass": True,
            "nocheckcertificate": True,
            "postprocessors": [
                {
                    "key": "FFmpegExtractAudio",
                    "preferredcodec": "mp3",
                    "preferredquality": "480",
                }
            ],
            "cookiefile": "cookies.txt",
            "outtmpl": "%(id)s",
            "quiet": True,
            "logtostderr": False,
        }

    @staticmethod
    def video_options() -> dict:
        return {
            "format": "best",
            "addmetadata": True,
            "key": "FFmpegMetadata",
            "prefer_ffmpeg": True,
            "geo_bypass": True,
            "nocheckcertificate": True,
            "postprocessors": [
                {
                    "key": "FFmpegVideoConvertor",
                    "preferedformat": "mp4",
                }
            ],
            "cookiefile": "cookies.txt",
            "outtmpl": "%(id)s.mp4",
            "quiet": True,
            "logtostderr": False,
        }