普通方法:爬取梨视频
import re import time import random import requests from lxml import etree start_time = time.time() url = "https://www.pearvideo.com/category_3" headers = { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36" } ex = 'srcUrl="(.*?)",vdoUrl=srcUrl' def request_video(url): """ 向视频链接发送请求 """ return requests.get(url=url, headers=headers).content def save_video(content): """ 将视频的二进制数据保存到本地 """ video_name = str(random.randint(100, 999)) + ".mp4" with open(video_name, 'wb') as f: f.write(content) # 获取首页源码 page_text = requests.get(url=url, headers=headers).text tree = etree.HTML(page_text) li_list = tree.xpath('//ul[@class="listvideo-list clearfix"]/li') video_url_list = list() for li in li_list: detail_url = "https://www.pearvideo.com/" + li.xpath('./div/a/@href')[0] # 获取该视频页面的源码 detail_page_text = requests.get(url=detail_url, headers=headers).text # 正则匹配视频的URL video_url = re.findall(ex, detail_page_text, re.S)[0] video_url_list.append(video_url) content = request_video(video_url) save_video(content) print("执行耗时: ", time.time() - start_time)
执行耗时: 147.22410440444946
使用线程池:爬取梨视频
# 使用线程池爬去梨视频的 import re import time import random import requests from lxml import etree from multiprocessing.dummy import Pool start_time = time.time() url = "https://www.pearvideo.com/category_3" headers = { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36" } ex = 'srcUrl="(.*?)",vdoUrl=srcUrl' def request_video(url): """ 向视频链接发送请求 """ return requests.get(url=url, headers=headers).content def save_video(content): """ 将视频的二进制数据保存到本地 """ video_name = str(random.randint(100, 999)) + ".mp4" with open(video_name, 'wb') as f: f.write(content) # 获取首页源码 page_text = requests.get(url=url, headers=headers).text tree = etree.HTML(page_text) li_list = tree.xpath('//ul[@class="listvideo-list clearfix"]/li') video_url_list = list() for li in li_list: detail_url = "https://www.pearvideo.com/" + li.xpath('./div/a/@href')[0] # 获取该视频页面的源码 detail_page_text = requests.get(url=detail_url, headers=headers).text # 正则匹配视频的URL video_url = re.findall(ex, detail_page_text, re.S)[0] video_url_list.append(video_url) pool = Pool(4) #使用线程池将视频的二进制数据下载下来 content_list = pool.map(request_video, video_url_list) # 使用线程池将视频的二进制数据保存到本地 pool.map(save_video, content_list) print("执行耗时: ", time.time() - start_time)
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持。