Python爬虫 - 用BeautifulSoup爬取CoreyMS博客的内容和视频地址到csv文件

资源：https://www.youtube.com/watch?v=ng2o98k983k

from bs4 import BeautifulSoup
import requests
import csv


source = requests.get("https://coreyms.com/").text
soup = BeautifulSoup(source, 'lxml')

csv_file = open('scraping_coreyms.csv', 'w')
csv_writer = csv.writer(csv_file)
csv_writer.writerow(['headline', 'summary', 'video_link'])

for article in soup.find_all('article'):
    headline = article.h2.a.text
    summary = article.find('div', class_="entry-content").p.text
    try:
        vid_src = article.find('iframe', class_="youtube-player")['src']
        # To get a list of sections of the youtube video address
        vid_id = vid_src.split('/')[4]
        # Get the part of address that comes before the question mark - that's