溫馨提示×

溫馨提示×

您好，登錄后才能下訂單哦！

密碼登錄×

忘記密碼？

登錄注冊×

獲取短信驗證碼

其他方式登錄

點擊登錄注冊即表示同意《億速云用戶服務條款》

用戶登錄×

賬戶密碼登錄

請使用微信掃描上方二維碼

使用幫助

請求超時！

請點擊重新獲取二維碼

python如何爬取影視網(wǎng)站下載鏈接

發(fā)布時間：2021-05-28 13:45:19 來源：億速云閱讀：179 作者：小新欄目：開發(fā)技術(shù)

這篇文章主要介紹python如何爬取影視網(wǎng)站下載鏈接，文中介紹的非常詳細，具有一定的參考價值，感興趣的小伙伴們一定要看完！

運行效果

python如何爬取影視網(wǎng)站下載鏈接

python如何爬取影視網(wǎng)站下載鏈接

導入模塊

import requests,re
from requests.cookies import RequestsCookieJar
from fake_useragent import UserAgent
import os,pickle,threading,time
import concurrent.futures
from goto import with_goto

爬蟲主代碼

def get_content_url_name(url):
    send_headers = {
     "User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
    "Connection": "keep-alive",
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
    "Accept-Language": "zh-CN,zh;q=0.8"

        }
    cookie_jar = RequestsCookieJar()
    cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
    response=requests.get(url,send_headers,cookies=cookie_jar)
    response.encoding='utf-8'
    content=response.text
    reg=re.compile(r'<a href="(.*?)" rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  class="thumbnail-img" title="(.*?)"')
    url_name_list=reg.findall(content)
    return url_name_list

def get_content(url):
    send_headers = {
     "User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
    "Connection": "keep-alive",
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
    "Accept-Language": "zh-CN,zh;q=0.8"

        }
    cookie_jar = RequestsCookieJar()
    cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
    response=requests.get(url,send_headers,cookies=cookie_jar)
    response.encoding='utf-8'
    return response.text



def search_durl(url):
    content=get_content(url)
    reg=re.compile(r"{'\\x64\\x65\\x63\\x72\\x69\\x70\\x74\\x50\\x61\\x72\\x61\\x6d':'(.*?)'}")
    index=reg.findall(content)[0]
    download_url=url[:-5]+r'/downloadList?decriptParam='+index
    content=get_content(download_url)
    reg1=re.compile(r'title=".*?" href="(.*?)" rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow" ')
    download_list=reg1.findall(content)
    return download_list
def get_page(url):
    send_headers = {
     "User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
    "Connection": "keep-alive",
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
    "Accept-Language": "zh-CN,zh;q=0.8"

        }
    cookie_jar = RequestsCookieJar()
    cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
    response=requests.get(url,send_headers,cookies=cookie_jar)
    response.encoding='utf-8'
    content=response.text
    reg=re.compile(r'<a target="_blank" class="title" href="(.*?)" rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  title="(.*?)">(.*?)<\/a>')
    url_name_list=reg.findall(content)
    return url_name_list
@with_goto
def main():

    print("=========================================================")
    name=input("請輸入劇名(輸入quit退出):")
    if name == "quit":
        exit()
    url="http://www.yikedy.co/search?query="+name
    dlist=get_page(url)
    print("\n")
    if(dlist):
        num=0
        count=0
        for i in dlist:
            if (name in i[1]) :
                print(f"{num} {i[1]}")
                num+=1
            elif num==0 and count==len(dlist)-1:
                goto .end
            count+=1
        dest=int(input("\n\n請輸入劇的編號(輸100跳過此次搜尋):"))
        if dest == 100:
            goto .end
        x=0
        print("\n以下為下載鏈接:\n")
        for i in dlist:
            if (name in i[1]):
                if(x==dest):
                    for durl in search_durl(i[0]):
                        print(f"{durl}\n")

                    print("\n")

                    break
                x+=1

    else:
        label .end
        print("沒找到或不想看\n")

完整代碼

import requests,re
from requests.cookies import RequestsCookieJar
from fake_useragent import UserAgent
import os,pickle,threading,time
import concurrent.futures
from goto import with_goto

def get_content_url_name(url):
    send_headers = {
     "User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
    "Connection": "keep-alive",
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
    "Accept-Language": "zh-CN,zh;q=0.8"

        }
    cookie_jar = RequestsCookieJar()
    cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
    response=requests.get(url,send_headers,cookies=cookie_jar)
    response.encoding='utf-8'
    content=response.text
    reg=re.compile(r'<a href="(.*?)" rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  class="thumbnail-img" title="(.*?)"')
    url_name_list=reg.findall(content)
    return url_name_list

def get_content(url):
    send_headers = {
     "User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
    "Connection": "keep-alive",
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
    "Accept-Language": "zh-CN,zh;q=0.8"

        }
    cookie_jar = RequestsCookieJar()
    cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
    response=requests.get(url,send_headers,cookies=cookie_jar)
    response.encoding='utf-8'
    return response.text



def search_durl(url):
    content=get_content(url)
    reg=re.compile(r"{'\\x64\\x65\\x63\\x72\\x69\\x70\\x74\\x50\\x61\\x72\\x61\\x6d':'(.*?)'}")
    index=reg.findall(content)[0]
    download_url=url[:-5]+r'/downloadList?decriptParam='+index
    content=get_content(download_url)
    reg1=re.compile(r'title=".*?" href="(.*?)" rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow" ')
    download_list=reg1.findall(content)
    return download_list
def get_page(url):
    send_headers = {
     "User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
    "Connection": "keep-alive",
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
    "Accept-Language": "zh-CN,zh;q=0.8"

        }
    cookie_jar = RequestsCookieJar()
    cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
    response=requests.get(url,send_headers,cookies=cookie_jar)
    response.encoding='utf-8'
    content=response.text
    reg=re.compile(r'<a target="_blank" class="title" href="(.*?)" rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  title="(.*?)">(.*?)<\/a>')
    url_name_list=reg.findall(content)
    return url_name_list
@with_goto
def main():

    print("=========================================================")
    name=input("請輸入劇名(輸入quit退出):")
    if name == "quit":
        exit()
    url="http://www.yikedy.co/search?query="+name
    dlist=get_page(url)
    print("\n")
    if(dlist):
        num=0
        count=0
        for i in dlist:
            if (name in i[1]) :
                print(f"{num} {i[1]}")
                num+=1
            elif num==0 and count==len(dlist)-1:
                goto .end
            count+=1
        dest=int(input("\n\n請輸入劇的編號(輸100跳過此次搜尋):"))
        if dest == 100:
            goto .end
        x=0
        print("\n以下為下載鏈接:\n")
        for i in dlist:
            if (name in i[1]):
                if(x==dest):
                    for durl in search_durl(i[0]):
                        print(f"{durl}\n")

                    print("\n")

                    break
                x+=1

    else:
        label .end
        print("沒找到或不想看\n")

print("本軟件由CLY.所有\(zhòng)n\n")
while(True):
    main()

以上是“python如何爬取影視網(wǎng)站下載鏈接”這篇文章的所有內(nèi)容，感謝各位的閱讀！希望分享的內(nèi)容對大家有幫助，更多相關(guān)知識，歡迎關(guān)注億速云行業(yè)資訊頻道！

向AI問一下細節(jié)

推薦閱讀：

免責聲明：本站發(fā)布的內(nèi)容（圖片、視頻和文字）以原創(chuàng)、轉(zhuǎn)載和分享為主，文章觀點不代表本網(wǎng)站立場，如果涉及侵權(quán)請聯(lián)系站長郵箱：is@yisu.com進行舉報，并提供相關(guān)證據(jù)，一經(jīng)查實，將立刻刪除涉嫌侵權(quán)內(nèi)容。

上一篇新聞：
如何修改手機上ip地址
下一篇新聞：
ASP.NET Core如何讀取Request.Body

猜你喜歡

AI
助
手

產(chǎn)品服務

地區(qū)劃分

專題活動

幫助支持

關(guān)于我們

售后咨詢

7*24小時在線電話：400-100-2938

7*24小時在線 QQ：800811969

關(guān)注億速云

億速云公眾號

手機網(wǎng)站二維碼