Python爬虫樱花动漫多线程下载附源码(超详细适合新手练习)

前言

别瞅了！认真看完你肯定行

一、打开动漫详细页面

二、查看网页源码

查看网页源码搜索关词能够找到相关内容，我们可以看见详情页地址并不完整，所以我们需要出拼接出完整url

def url_parse():
    new_url = input("请粘贴你想下载的动漫链接")
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.75 Safari/537.36'}
    response = requests.get(url=new_url, headers=headers).text
    tree = etree.HTML(response)
    li_list = tree.xpath("//div[@id='play_0']/ul/li")
    dic ={}
    for li in li_list:
        url = "http://www.imomoe.ai" + li.xpath("a/@href")[0]
        name = li.xpath("a/@title")[0]
        dic[name]=url
    return dic

三、进入详情页查看

打开开发者工具(F12)点击视频我们可以看到video标签中src属性为视频地址

查看网页源码发现并没有找到我们想要video标签中的属性，我们用selenum获取网页源码

def data(url):
    bro = webdriver.Chrome(executable_path="./chromedriver")
    r = bro.get(url)
    page_data = bro.page_source
    bro.quit()
    tree1 = etree.HTML(page_data)
    video= tree1.xpath('//div[@class="player"]/iframe/@src')[0]
    name = "第"+video.split(".")[-2].split("-")[-1]+"集.mp4"
    x = threading.Thread(target=videos, args=(name, video,))
    x.start()
    print(name + "解析成功")

四、线程创建

通过selenum提取url需要依次提取，这简直太费时间了，所以我们创建线程进行同步提取来节省时间

def data_parse(dic):
    tasks=[]
    urls=list(dic.values())
    for url in urls:
        x=threading.Thread(target=data,args=(url,))
        tasks.append(x)
    for task in tasks:
        task.start()
        sleep(1)

通过selenum提取的url跟我们刚才所看到视频url并不相同，不过跳转到我们selenum抓取的url在重复抓取一下就能找到视频url

def videos(name,url):
    bro= webdriver.Chrome(executable_path="./chromedriver.exe")
    bro.get(url)
    mp4_data = bro.page_source
    bro.quit()
    tree2 = etree.HTML(mp4_data)
    video= tree2.xpath("//*[@id='a1']/div[2]/video/@src")[0]
    x = threading.Thread(target=download, args=(name, video,))
    x.start()
    print(name+"正在下载")
    # print(video)

五、视频下载

def download(name,url):
    headers={"User-Agent":UserAgent().random}
    response=requests.get(url=url,headers=headers).content
    with open(name,"wb")as fp:
        fp.write(response)
        print(name+"下载完成")

代码

import requests
import threading
from fake_useragent import UserAgent
from selenium import webdriver
from  lxml import etree
from time import sleep
# from selenium.webdriver.chrome.options import Options
# chrome_options = Options()
# chrome_options.add_argument('--headless')
# chrome_options.add_argument('--disable-gpu')

def url_parse():
    new_url = input("请粘贴你想下载的动漫链接")
    headers = {
     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.75 Safari/537.36'}
    response = requests.get(url=new_url, headers=headers).text
    tree = etree.HTML(response)
    li_list = tree.xpath("//div[@id='play_0']/ul/li")
    dic ={
     }
    for li in li_list:
        url = "http://www.imomoe.ai" + li.xpath("a/@href")[0]
        name = li.xpath("a/@title")[0]
        dic[name]=url
    return dic

def data_parse(dic):
    tasks=[]
    urls=list(dic.values())
    for url in urls:
        x=threading.Thread(target=data,args=(url,))
        tasks.append(x)
    for task in tasks:
        task.start()
        sleep(1)



def data(url):
    bro = webdriver.Chrome(executable_path="./chromedriver")
    r = bro.get(url)
    page_data = bro.page_source
    bro.quit()
    tree1 = etree.HTML(page_data)
    video= tree1.xpath('//div[@class="player"]/iframe/@src')[0]
    name = "第"+video.split(".")[-2].split("-")[-1]+"集.mp4"
    x = threading.Thread(target=videos, args=(name, video,))
    x.start()
    print(name + "解析成功")
    # print(video)




def videos(name,url):
    bro= webdriver.Chrome(executable_path="./chromedriver.exe")
    bro.get(url)
    mp4_data = bro.page_source
    bro.quit()
    tree2 = etree.HTML(mp4_data)
    video= tree2.xpath("//*[@id='a1']/div[2]/video/@src")[0]
    x = threading.Thread(target=download, args=(name, video,))
    x.start()
    print(name+"正在下载")
    # print(video)


def download(name,url):
    headers={
     "User-Agent":UserAgent().random}
    response=requests.get(url=url,headers=headers).content
    with open(name,"wb")as fp:
        fp.write(response)
        print(name+"下载完成")

def main():
    dic = url_parse()
    data_parse(dic)


if __name__ == '__main__':
    main()