使用python爬取网站视频

思路分析：

        1.确定爬取的视频地址 ，这个可以通过F12来对其进行分析

       2.确定爬取视频所需要的的参数 以及分析用哪类请求和header信息的获取

3.最好是提前拿到postman上进行初次访问然后再写代码

4.通过上述的调试发现接口存在且可以访问那么就开始愉快的写代码来解析出视频的所需信息进行

转化为本地视频了

import requests
import json
import urllib
import time
class getVideo(object):

        def getVideo(self):

            url = "http://haokan.baidu.com/videoui/api/videorec"
            header = {
                'cookie': 'BIDUPSID=33B8EE183D9B9E323939352A0E85B7A5; PSTM=1631859469; BAIDUID=33B8EE183D9B9E326F4F62C42A2E56F1:FG=1; __yjs_duid=1_9ee50ae1e2369325576fd487374d2be61632449615247; BDUSS_BFESS=xITzAwWXNCMFVOZFVVV3diRXV-MVhyfnFsdVVvdVVYQ0g2YktXNG0zemt5WFJoSUFBQUFBJCQAAAAAAAAAAAEAAACy~~joAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAOQ8TWHkPE1hMW; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; BDSFRCVID_BFESS=VdtOJeC627T5vvjHHeiNhbGZJkEmotOTH6aoyitjU2C5TJGLPT8XEG0P8f8g0K4-Nb29ogKK3gOTH4DF_2uxOjjg8UtVJeC6EG0Ptf8g0M5; H_BDCLCKID_SF_BFESS=tJCDoC8XtKL3fP36qRQEh-LDhUO-2I62aKDs_JoYBhcqEnTkLJob36J0y-7vtho3KevzaJ3cyIn8VxbSj4oTbTkXya7KLl_DaJvuBf5P-h5nhMJHb67JDMP0-45nQJby523iob3vQpPMshQ3DRoWXPIqbN7P-p5Z5mAqKl0MLPbtbb0xb6_0Djb-DaDJqTna--oa3RTeb6rjDnCrMxRTXUI82h5y05OqaJcqapn_ttJsHl3Ly4JvyT8sXnORXx7JB5vvbPOMthRnOlRKbpo6qfL1Db3JWhQGMgcTsR7yLbnoepvoDPJc3Mv3Q-jdJJQOBKQB0KnGbUQkeq8CQft20b0EeMtjW6LEtR4t_K0-fC03fP36q45H24k0-qrtetJyaR3p0PbvWJ5TMC_635o-54InyMo0Wtva3aQZBh5Ea-bcShPC-tnBMJ0q3H5mtl3Z32JT-In93l02VKnIe-t2yT3DXxKHq4RMW20e0h7mWIbUsxA45J7cM4IseboJLfT-0bc4KKJxbnLWeIJEjj6jK4JKDGttJ5bP; IMG_WH=2000_413; H_WISE_SIDS=110085_127969_131862_164869_177370_178384_178641_179346_179451_179620_181133_181489_181588_182243_182273_182531_183327_183626_184011_184267_184319_184360_184560_184794_184891_184891_185519_185880_186319_186587_186596_186636_186682_186743_186833_186841_187023_187042_187067_187086_187192_187292_187356_187433_187447_187542_187567_187669_187726_187816_187819_187929_187957_187992_188031_188182_188226_188353_188426_188467_188665_188669_188722_188733_188734_188748_188832_188842_189058_189071_189346_189391_189398_189414_189504_189680_189755; BDRCVFR[X_XKQks0S63]=mk3SLVN4HKm; BDRCVFR[dG2JNJb_ajR]=mk3SLVN4HKm; BDRCVFR[-pGxjrCMryR]=mk3SLVN4HKm; BAIDUID_BFESS=46B2ADF6599C4AC9A65B4AA239316277:FG=1; delPer=0; PSINO=6; BA_HECTOR=05agalal040k0080bd1gmsdcj0q; H_PS_PSSID=34068_31254_34712_34599_34584_34504_34832_34813_26350_34691_34675; Hm_lvt_4aadd610dfd2f5972f1efee2653a2bc5=1633663971,1634612649; HK_CH_EXPIRED_TIME=1634659199000; HK_CH_IS_CLICKED=0; HK_CH_REFRESH_TIMES=1; HK_SID=11796_2; COMMON_LID=496b0aa3b92a4dcfe85dee59d76b441f; Hm_lvt_77ca61e523cd51ec7ac7a23bc4d24edf=1634612656; Hm_lpvt_77ca61e523cd51ec7ac7a23bc4d24edf=1634612796; HK_CH_MAT_INDEX=0; PC_TAB_LOG=video_details_page; ab_sr=1.0.1_MDc5MmI3NzliM2ZjODcwNWY4ZjA3ZWRhNzc5NTQxMDBmMzhjYTM2YzM3ZTRmNWY4N2RmZjI0ODg3YzcxOTE4YmZhZWNlYzE1MGFhYzNlZmI4OGM3NWViMjRjNjRiMjFiMzYxYjc0YmUyY2I5ZmQyYjY0ODllNDc1ZDhiYjg4MmYxMjZjZmViNzViMWQ0NmYwNWJlNzgyMTkwY2QzZTNiOQ==; reptileData={"data":"03bd57de5d85cc095ec2dc325bf0bffa94ba3d7eb3b777760790a66a355a3a003b9c482e43ddf318dfbcd20d71f06f85bfe5301c24b6789788024518bfb4bf0174f252dd7b6b93e3d0fe276942b7c9d164246c4456e74438df7e078cb4216f84f4b592a5b8b4019767d59376f7e2052ebf5bf7776defa8fb84ff8ad015684a51","key_id":"30","sign":"7cec8433"}; Hm_lpvt_4aadd610dfd2f5972f1efee2653a2bc5=1634612832',

                'user-agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.81 Mobile Safari/537.36'
            }
            param = {
                'vid': 6809766516780878997,
                'title': '一首《纤夫的爱》送给你们',
                'pd': 'h5',
                'act': 'h5Rec',
                'referPd': ''
            }
            resInfo = requests.get(url=url, headers=header, params=param)
            resInfo.encoding = 'utf-8'
            data = resInfo.text
            print(data)
            resInfoText = json.loads(data)
            video = []  # 把 title 和 url都装进去  ["《纤夫的爱》好听吗",'https://haokan.baidu.com/v?pd=h5&vid=13772777109240759654']
            for index in range(len(resInfoText['data']['response']['videos'])):
                # print(type(resInfoText['data']['response']['videos'][index]))
                # print(resInfoText['data']['response']['videos'][index])
                for item in resInfoText['data']['response']['videos'][index].keys():
                    # print(resInfoText['data']['response']['videos'][index][item])
                    if item == 'title' or item == 'play_url':
                        video.append(resInfoText['data']['response']['videos'][index][item])
            movieName = ''
            for index in range(len(video)):
                if index % 2 == 0:
                    movieName = video[index]
                else:
                    time.sleep(3)
                    print("------------------" + "downloading" + "------------------")
                    urllib.request.urlretrieve(video[index], filename="D:/b/视频爬取/" + movieName + '.mp4')
                    movieName = ''
if __name__ == "__main__":
        allVideo = getVideo()
        allVideo.getVideo()

5.结果如下：