Python抓取騰視頻所有電影，不用錢就可以看會(huì)員電影

import reimport os,shutilimport requests,threadingfrom urllib.request import urlretrievefrom pyquery import PyQuery as pqfrom 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(shè)置UA模擬瀏覽器訪問(wèn)        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(shè)置多線程數(shù)量        self.thread_num=32        #當(dāng)前已經(jīng)下載的文件數(shù)目        self.i = 0        # 調(diào)用網(wǎng)頁(yè)獲取        html = self.get_page(self.get_url)        if html:            # 解析網(wǎng)頁(yè)            self.parse_page(html)    def get_page(self,get_url):        try:            print('正在請(qǐng)求目標(biāo)網(wǎng)頁(yè)....',get_url)            response=requests.get(get_url,headers=self.head)            if response.status_code==200:                #print(response.text)                print('請(qǐng)求目標(biāo)網(wǎng)頁(yè)完成....\n 準(zhǔn)備解析....')                self.head['referer'] = get_url                return response.text        except Exception:            print('請(qǐng)求目標(biāo)網(wǎng)頁(yè)失敗，請(qǐng)檢查錯(cuò)誤重試')            return None

    def parse_page(self,html):        print('目標(biāo)信息正在解析........')        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，獲取緩存ts文件.........')        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文件成功，準(zhǔn)備提取信息')            return html[-20:]        except Exception:            print('緩存文件請(qǐng)求錯(cuò)誤1，請(qǐng)檢查錯(cuò)誤')

    def get_m3u8_2(self,url):        try:            response=requests.get(url,headers=self.head)            html=response.text            print('獲取ts文件成功，準(zhǔn)備提取信息')            self.parse_ts_2(html)        except Exception:            print('緩存文件請(qǐng)求錯(cuò)誤2，請(qǐng)檢查錯(cuò)誤')    def parse_ts_2(self,html):        pattern=re.compile('.*?(.*?).ts')        self.ts_lists=re.findall(pattern,html)        print('信息提取完成......\n準(zhǔn)備下載...')        self.pool()    def pool(self):        print('經(jīng)計(jì)算需要下載%d個(gè)文件' % 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(shí)間較長(zhǎng)，請(qǐng)耐心等待..')        #開啟多進(jìn)程下載        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文件正在進(jìn)行轉(zhuǎn)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(zhuǎn)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(dāng)前進(jìn)度%d/%d'%(self.i,len(self.ts_lists)))            urlretrieve(url=ts_urls, filename=self.title + '/{}.ts'.format(ts_list))        except Exception:            print('保存文件出現(xiàn)錯(cuò)誤')



if __name__ == '__main__':    #電影目標(biāo)url：狄仁杰之四大天王    url='https://v.qq.com/x/cover/r6ri9qkcu66dna8.html'    #電影碟中諜5：神秘國(guó)度    url1='https://v.qq.com/x/cover/5c58griiqftvq00.html'    #電視劇斗破蒼穹    url2='https://v.qq.com/x/cover/lcpwn26degwm7t3/z0027injhcq.html'    url3='https://v.qq.com/x/cover/33bfp8mmgakf0gi.html'    video_down(url2)