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

# 取消警告
warnings.filterwarnings("ignore")


def get_html(url):
    """發(fā)送請(qǐng)求獲取網(wǎng)頁源代碼"""
    html_data = requests.get(url=url, verify=False).text
    return html_data


def parse_data_1(html_data):
    """第一次解析, 拿到所有的詳情頁鏈接"""
    selector = parsel.Selector(html_data)
    url_list = selector.xpath('//a[@class="meta-title"]/@href').getall()
    return url_list


def parse_data_2(html_data):
    """第二次解析, 獲取視頻鏈接"""
    video_url = re.findall('url: "(.*?)",', html_data)[0]
    return video_url


def save(video_url):
    """保存視頻"""
    title = video_url.split('/')[-1]    # 取鏈接當(dāng)中的字段作為標(biāo)題
    video_data = requests.get(video_url, verify=False).content    # 發(fā)送網(wǎng)絡(luò)請(qǐng)求
    with open(f'video/{title}', mode='wb') as f:
        f.write(video_data)
    print(title, "爬取成功!!!")

start_time = time.time()
url = 'https://www.520mmtv.com/hd/rewu.html'
# 1. 向目標(biāo)網(wǎng)站發(fā)送請(qǐng)求
html_data = get_html(url=url)
# 2. 第一次解析數(shù)據(jù) 提取詳情頁鏈接
url_list = parse_data_1(html_data=html_data)
for info_url in url_list[:10]:
    # 3. 向詳情頁發(fā)送請(qǐng)求
    html_data_2 = get_html(url=info_url)
    # 4. 第二次解析數(shù)據(jù) 提取視頻播放地址
    video_url = parse_data_2(html_data=html_data_2)
    # 5. 保存視頻
    save(video_url=video_url)
print('花費(fèi)時(shí)間：', time.time() - start_time)