youtube-tools/youtube-search.py

#!/usr/bin/python

from urllib import request, error, parse
from json import loads, dumps

base_url = 'https://m.youtube.com'
log = 'utsearch.log'

#Colors
RED = '\033[31m'
BLUE = '\033[34m'
CYAN = '\033[36m'
GREEN = '\33[32m'
BLACK  = '\33[30m'
WHITE  = '\33[37m'
YELLOW = '\033[33m'
END = '\033[0;0m'
BOLD = '\033[1m'
ITALIC   = '\33[3m'
UNDERLINE = '\033[4m'
            
agent = ('Mozilla/5.0 (compatible; Googlebot/2.1;'
            '+ http://www.google.com/bot.mtml')
            
user_agent = {'User-Agent': agent}
            
class YoutubeSearch:
    def __init__(self, search_terms: str, max_results=None):
        self.search_terms = search_terms
        self.max_results = max_results
        self.videos = self.search()
   
    def search(self):
        encoded_search = parse.quote(self.search_terms)

        #Search Utube by results
        urla = f'{base_url}/results?search_query={encoded_search}'
        #Search utube by date
        urlb = (f'{base_url}/results?search_query={encoded_search}'
                '&search_sort=video_date_uploaded')
        #Search utube by views
        urlc = (f'{base_url}/results?search_query={encoded_search}'
                '&search_sort=video_view_count')
        #Select search type
        url = urlb
        
        page = request.urlopen(request.Request(
                                    url, data=None, headers=user_agent))
        response = page.read().decode() 
        while "ytInitialData" not in response: 
            response = page.read().decode() 
        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):
        results = []
        start = (response.index("ytInitialData")
            + len("ytInitialData")
            + 3
        )
        end = response.index("};", start) + 1
        json_str = response[start:end]
        data = loads(json_str)

        videos = data["contents"]["twoColumnSearchResultsRenderer"][
        "primaryContents"]["sectionListRenderer"]["contents"][0][
        "itemSectionRenderer"]["contents"]
        
        #Get items from page, make a dictionary.
        for video in videos:
            res = {}
            if "videoRenderer" in video.keys():
                video_data = video.get("videoRenderer", {})
                res["Video Id:"] = video_data.get("videoId", None)
                res["Image:"] = [thumb.get(
                    "url", None) for thumb in video_data.get(
                    "thumbnail", {}).get("thumbnails", [{}]) ]
                res["Title:"] = video_data.get(
                    "title", {}).get("runs", [[{}]])[0].get(
                    "text", None)
                res["Description:"] = video_data.get(
                    "descriptionSnippet", {}).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", 0) 
                res["Url:"] = video_data.get(
                    "navigationEndpoint", {}).get(
                    "commandMetadata", {}).get(
                    "webCommandMetadata", {}).get("url", None)
                results.append(res)
        return results

    def to_dict(self):
        return self.videos

    def to_json(self):
        return json.dumps({"videos": self.videos})
        
if __name__ == '__main__':
    
    uts = input('Enter search terms for youtube :')
    #Set number of video results here.
    max_results = 100
    results = YoutubeSearch(uts, max_results).to_dict()
    
    #Print results to terminal and write to log
    with open(log, 'a') as f:
        print('%s\n'*5 % (CYAN, BOLD, 'Start Search', '='*70, END))
        f.write('%s\n'*3 % ('', 'Start Search', '='*70))
        
        for result in results:
            result['Image:'] = result['Image:'][0]
            #Make complete url 
            result['Url:'] = (base_url + result['Url:'])

            print(YELLOW, '-'*70, END)
            f.write('%s\n' % ('-'*70))
            
            for key, val in result.items():
                #Colorize output
                print(GREEN, BOLD, key, END, val)
                f.write("%s  %s\n" % (key,val))