前言
別瞅了控硼！看完你肯定行
一、打開動漫詳細(xì)頁面
image.png
二艾少、查看網(wǎng)頁源碼
查看網(wǎng)頁源碼搜索關(guān)詞能夠找到相關(guān)內(nèi)容卡乾，我們可以看見詳情頁地址并不完整，所以我們需要出拼接出完整url
def url_parse():
new_url = input("請粘貼你想下載的動漫鏈接")
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("http://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
三缚够、進(jìn)入詳情頁查看
打開開發(fā)者工具(F12)點擊視頻我們可以看到video標(biāo)簽中src屬性為視頻地址
查看網(wǎng)頁源碼發(fā)現(xiàn)并沒有找到我們想要video標(biāo)簽中的屬性幔妨，我們用selenum獲取網(wǎng)頁源碼
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、線程創(chuàng)建
通過selenum提取url需要依次提取谍椅，這簡直太費時間了误堡，所以我們創(chuàng)建線程進(jìn)行同步提取來節(jié)省時間
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)
通過selenum提取的url跟我們剛才所看到視頻url并不相同，不過跳轉(zhuǎn)到我們selenum抓取的url在重復(fù)抓取一下就能找到視頻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("http://*[@id='a1']/div[2]/video/@src")[0]
x = threading.Thread(target=download, args=(name, video,))
x.start()
print(name+"正在下載")
# print(video)
五雏吭、視頻下載
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+"下載完成")
代碼
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("請粘貼你想下載的動漫鏈接")
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("http://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("http://*[@id='a1']/div[2]/video/@src")[0]
x = threading.Thread(target=download, args=(name, video,))
x.start()
print(name+"正在下載")
# 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+"下載完成")
def main():
dic = url_parse()
data_parse(dic)
if __name__ == '__main__':
main()
