十年网站开发经验 + 多家企业客户 + 靠谱的建站团队
量身定制 + 运营维护+专业推广+无忧售后,网站问题一站解决
这篇文章主要讲解了基于线程池提升request模块效率的方法,内容清晰明了,对此有兴趣的小伙伴可以学习一下,相信大家阅读完之后会有帮助。
创新互联于2013年开始,先为古田等服务建站,古田等地企业,进行企业商务咨询服务。为古田企业网站制作PC+手机+微官网三网同步一站式服务解决您的所有建站问题。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)