Pythonショートビデオクローラーチュートリアル

python 3.8
pycharm 2021.2

requests
parsel
re
concurrent.futures
time
warnings

import requests
import parsel
import re
import concurrent.futures
import time
import warnings

# Cancel warnings
warnings.filterwarnings("ignore")


def get_html(url):
    """Send a request to get the source code of a web page"""
    html_data = requests.get(url=url, verify=False).text
    return html_data


def parse_data_1(html_data):
    """Parse for the first time, get all the detail page links """
    selector = parsel.Selector(html_data)
    url_list = selector.xpath('//a[@class="meta-title"]/@href').getall()
    return url_list


def parse_data_2(html_data):
    """Parse a second time, get the video link """
    video_url = re.findall('url: "(. *?) ",', html_data)[0]
    return video_url


def save(video_url):
    """Save video"""
    title = video_url.split('/')[-1] # take the field in the link as the title
    video_data = requests.get(video_url, verify=False).content # send network request
    with open(f'video/{title}', mode='wb') as f:
        f.write(video_data)
    print(title, "Crawl successful!!! ")

start_time = time.time()
url = 'https://www.520mmtv.com/hd/rewu.html'
# 1. send a request to the target site
html_data = get_html(url=url)
# 2. parse the data for the first time Extract the details page link
url_list = parse_data_1(html_data=html_data)
for info_url in url_list[:10]:
    # 3. send a request to the detail page
    html_data_2 = get_html(url=info_url)
    # 4. parse the data a second time to extract the video play address
    video_url = parse_data_2(html_data=html_data_2)
    # 5. save the video
    save(video_url=video_url)
print('Time spent:', time.time() - start_time)