Python實現抓取騰訊視訊所有電影的範例程式碼

import re
import os,shutil
import requests,threading
from urllib.request import urlretrieve
from pyquery import PyQuery as pq
from multiprocessing import Pool
'''
'''
class video_down():
    def __init__(self,url):
        # 拼接全民解析url
        self.api='https://jx.618g.com'
        self.get_url = 'https://jx.618g.com/?url=' + url
        #設定UA模擬瀏覽器存取
        self.head = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'}
        #設定多執行緒數量
        self.thread_num=32
        #當前已經下載的檔案數目
        self.i = 0
        # 呼叫網頁獲取
        html = self.get_page(self.get_url)
        if html:
            # 解析網頁
            self.parse_page(html)
    def get_page(self,get_url):
        try:
            print('正在請求目標網頁....',get_url)
            response=requests.get(get_url,headers=self.head)
            if response.status_code==200:
                #print(response.text)
                print('請求目標網頁完成....n 準備解析....')
                self.head['referer'] = get_url
                return response.text
        except Exception:
            print('請求目標網頁失敗，請檢查錯誤重試')
            return None


    def parse_page(self,html):
        print('目標資訊正在解析........')
        doc=pq(html)
        self.title=doc('head title').text()
        print(self.title)
        url = doc('#player').attr('src')[14:]
        html=self.get_m3u8_1(url).strip()
        #self.url = url + '800k/hls/index.m3u8'
        self.url = url[:-10] +html
        print(self.url)
        print('解析完成，獲取快取ts檔案.........')
        self.get_m3u8_2(self.url)
    def get_m3u8_1(self,url):
        try:
            response=requests.get(url,headers=self.head)
            html=response.text
            print('獲取ts檔案成功，準備提取資訊')
            return html[-20:]
        except Exception:
            print('快取檔案請求錯誤1，請檢查錯誤')


    def get_m3u8_2(self,url):
        try:
            response=requests.get(url,headers=self.head)
            html=response.text
            print('獲取ts檔案成功，準備提取資訊')
            self.parse_ts_2(html)
        except Exception:
            print('快取檔案請求錯誤2，請檢查錯誤')
    def parse_ts_2(self,html):
        pattern=re.compile('.*?(.*?).ts')
        self.ts_lists=re.findall(pattern,html)
        print('資訊提取完成......n準備下載...')
        self.pool()
    def pool(self):
        print('經計算需要下載%d個檔案' % len(self.ts_lists))
        self.ts_url = self.url[:-10]
        if self.title not in os.listdir():
            os.makedirs(self.title)
        print('正在下載...所需時間較長，請耐心等待..')
        #開啟多程序下載
        pool=Pool(16)
        pool.map(self.save_ts,[ts_list for ts_list in self.ts_lists])
        pool.close()
        pool.join()
        print('下載完成')
        self.ts_to_mp4()
    def ts_to_mp4(self):
        print('ts檔案正在進行轉錄mp4......')
        str='copy /b '+self.title+'*.ts '+self.title+'.mp4'
        os.system(str)
        filename=self.title+'.mp4'
        if os.path.isfile(filename):
            print('轉換完成，祝你觀影愉快')
            shutil.rmtree(self.title)


    def save_ts(self,ts_list):
        try:
            ts_urls = self.ts_url + '{}.ts'.format(ts_list)
            self.i += 1
            print('當前進度%d/%d'%(self.i,len(self.ts_lists)))
            urlretrieve(url=ts_urls, filename=self.title + '/{}.ts'.format(ts_list))
        except Exception:
            print('儲存檔案出現錯誤')




if __name__ == '__main__':
    #電影目標url：狄仁傑之四大天王
    url='https://v.qq.com/x/cover/r6ri9qkcu66dna8.html'
    #電影碟中諜5：神祕國度
    url1='https://v.qq.com/x/cover/5c58griiqftvq00.html'
    #電視劇鬥破蒼穹
    url2='https://v.qq.com/x/cover/lcpwn26degwm7t3/z0027injhcq.html'
    url3='https://v.qq.com/x/cover/33bfp8mmgakf0gi.html'
    video_down(url2)