1.7 KiB
1.7 KiB
Youtube
Introduction
Est-ce nécessaire ?
Obtenir l'id d'un channel afin de s'abonner à son flux RSS
# pip install scrapy
from scrapy import Spider, Request
from scrapy.crawler import CrawlerProcess
from scrapy.utils.log import configure_logging
class YoutubeChannelIdSpider(Spider):
name = "youtube_channel"
allowed_domains = ['youtube.com']
def __init__(self, channel, *args, **kwargs):
super().__init__(*args, **kwargs)
self.channel = channel
self.url = f'https://www.youtube.com/c/{channel}'
def start_requests(self):
yield Request(url=self.url, callback=self.parse, cookies={'CONSENT': 'YES+1'})
def parse(self, response):
if channel_id := response.xpath('//meta[@itemprop="channelId"]/@content').get():
print(f'{self.channel} channel ID is : "{channel_id}"')
else:
print(f'Unable to find ID for channel {self.channel}')
channel = input("What's the Youtube channel for which the ID shall be retrieved ?")
process = CrawlerProcess()
process.crawl(YoutubeChannelIdSpider, channel=channel)
process.start() # the script will block here until the crawling is finishedAAAAAAAAAAAAAAAAAAAAAAAAA url = 'https://www.youtube.com/c/Matrixdotorg/'