|
|
@@ -360,7 +360,6 @@ class Follow:
|
|
|
|
|
|
@classmethod
|
|
|
def get_videoList(cls, log_type, crawler, strategy, our_uid, out_uid, oss_endpoint, env, machine):
|
|
|
- try:
|
|
|
download_cnt_1, download_cnt_2 = 0, 0
|
|
|
pcursor = ""
|
|
|
|
|
|
@@ -374,264 +373,246 @@ class Follow:
|
|
|
break
|
|
|
|
|
|
while True:
|
|
|
- if download_cnt_1 >= int(
|
|
|
- rule_dict_1['download_cnt'].replace("=", "")[-1].replace("<", "")[-1].replace(">", "")[
|
|
|
- -1]) and download_cnt_2 >= int(
|
|
|
- rule_dict_2['download_cnt'].replace("=", "")[-1].replace("<", "")[-1].replace(">", "")[-1]):
|
|
|
- Common.logger(log_type, crawler).info(
|
|
|
- f"规则1已下载{download_cnt_1}条视频，规则2已下载{download_cnt_2}条视频\n")
|
|
|
- return
|
|
|
-
|
|
|
- url = "https://www.kuaishou.com/graphql"
|
|
|
- payload = json.dumps({
|
|
|
- "operationName": "visionProfilePhotoList",
|
|
|
- "variables": {
|
|
|
- "userId": out_uid,
|
|
|
- "pcursor": pcursor,
|
|
|
- "page": "profile"
|
|
|
- },
|
|
|
- "query": "fragment photoContent on PhotoEntity {\n id\n duration\n caption\n originCaption\n likeCount\n viewCount\n realLikeCount\n coverUrl\n photoUrl\n photoH265Url\n manifest\n manifestH265\n videoResource\n coverUrls {\n url\n __typename\n }\n timestamp\n expTag\n animatedCoverUrl\n distance\n videoRatio\n liked\n stereoType\n profileUserTopPhoto\n musicBlocked\n __typename\n}\n\nfragment feedContent on Feed {\n type\n author {\n id\n name\n headerUrl\n following\n headerUrls {\n url\n __typename\n }\n __typename\n }\n photo {\n ...photoContent\n __typename\n }\n canAddComment\n llsid\n status\n currentPcursor\n tags {\n type\n name\n __typename\n }\n __typename\n}\n\nquery visionProfilePhotoList($pcursor: String, $userId: String, $page: String, $webPageArea: String) {\n visionProfilePhotoList(pcursor: $pcursor, userId: $userId, page: $page, webPageArea: $webPageArea) {\n result\n llsid\n webPageArea\n feeds {\n ...feedContent\n __typename\n }\n hostName\n pcursor\n __typename\n }\n}\n"
|
|
|
- })
|
|
|
- # get_cookie = cls.get_cookie(log_type, crawler, out_uid, machine)
|
|
|
- # if get_cookie is None:
|
|
|
- # cookie = 'kpf=PC_WEB; clientid=3; did=web_e2901e1c5a13c60af81ba88bc7a3ee24; kuaishou.server.web_st=ChZrdWFpc2hvdS5zZXJ2ZXIud2ViLnN0EqABszwASP0eGT2ym0NUdGf1PTi8_gDYrDms9otf5FKMUrx0V7MOTT1hhvpVJijmgku8KYtu3a6g3X1hZODMpX0ebZUip44txWPoY3VRqbsnBKEOs9Qkmx3uLaX33nq8KevOKLoO0cIE8nfwMJISe_BtCHr22cbJkofI0xfJXBt_ZgPqJIqWsUwdgwKzqRYn47ROkIqzeDfEjbxaZxiXy22ZhhoSlCobbmtjkvjpY9x730BPP_C5IiAl9EBaCTyvMw5IIcnkmcjMeWC8w6LKzeFMCNhcqrfkgCgFMAE; kuaishou.server.web_ph=19ae269a54f619c49def39ef5b54ae6d4353; kpn=KUAISHOU_VISION'
|
|
|
- # else:
|
|
|
- # cookie = get_cookie
|
|
|
- # Common.logger(log_type, crawler).info(f"cookie:{cookie}")
|
|
|
- headers = {
|
|
|
- # 'Cookie': f'kpf=PC_WEB; clientid=3; did=web_e2901e1c5a13c60af81ba88bc7a3ee24; userId={"".join(str(random.choice(range(1, 10))) for _ in range(10))}; kuaishou.server.web_st=ChZrdWFpc2hvdS5zZXJ2ZXIud2ViLnN0EqABOLgYYcIJ5ilxU46Jc-HLWThY8sppX3V0htC_KhSGOzAjP2hAOdegzfkZGAxS5rf6rCBS487FkxfYzLkV__I6b1lK16rDjvv94Kkoo4z7mgf8y8rFgWoqrp81JAWTtx00y-wrc1XXPf9RAVQoET70wWaeNG2r5bxtZEiNwpK_zPi0ZdUo0BW13dFKfVssAy2xKYh0UlJ8VSd_vBvyMKSxVBoSf061Kc3w5Nem7YdpVBmH39ceIiBpiGioLzbZqlHiSbwkH_LhUhNXz3o7LITj098KUytk2CgFMAE; kuaishou.server.web_ph=f1033957981996a7d50e849a9ded4cf4adff; kpn=KUAISHOU_VISION',
|
|
|
- # 'Cookie': cookie,
|
|
|
- # 'Cookie': 'kpf=PC_WEB; clientid=3; did=web_e2901e1c5a13c60af81ba88bc7a3ee24; kuaishou.server.web_st=ChZrdWFpc2hvdS5zZXJ2ZXIud2ViLnN0EqABszwASP0eGT2ym0NUdGf1PTi8_gDYrDms9otf5FKMUrx0V7MOTT1hhvpVJijmgku8KYtu3a6g3X1hZODMpX0ebZUip44txWPoY3VRqbsnBKEOs9Qkmx3uLaX33nq8KevOKLoO0cIE8nfwMJISe_BtCHr22cbJkofI0xfJXBt_ZgPqJIqWsUwdgwKzqRYn47ROkIqzeDfEjbxaZxiXy22ZhhoSlCobbmtjkvjpY9x730BPP_C5IiAl9EBaCTyvMw5IIcnkmcjMeWC8w6LKzeFMCNhcqrfkgCgFMAE; kuaishou.server.web_ph=19ae269a54f619c49def39ef5b54ae6d4353; kpn=KUAISHOU_VISION',
|
|
|
- 'Cookie': 'kpf=PC_WEB; clientid=3; did=web_8832834f71f4c6ed405b5a35e95abc6d; kpn=KUAISHOU_VISION',
|
|
|
- 'Referer': f'https://www.kuaishou.com/profile/{out_uid}',
|
|
|
- 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36 Edg/110.0.1587.41',
|
|
|
- 'content-type': 'application/json',
|
|
|
- # 'accept': '*/*',
|
|
|
- # 'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
|
|
|
- # 'Cache-Control': 'no-cache',
|
|
|
- # 'Connection': 'keep-alive',
|
|
|
- # 'Origin': 'https://www.kuaishou.com',
|
|
|
- # 'Pragma': 'no-cache',
|
|
|
- # 'Sec-Fetch-Dest': 'empty',
|
|
|
- # 'Sec-Fetch-Mode': 'cors',
|
|
|
- # 'Sec-Fetch-Site': 'same-origin',
|
|
|
- # 'sec-ch-ua': '"Chromium";v="110", "Not A(Brand";v="24", "Microsoft Edge";v="110"',
|
|
|
- # 'sec-ch-ua-mobile': '?0',
|
|
|
- # 'sec-ch-ua-platform': '"macOS"'
|
|
|
- }
|
|
|
- urllib3.disable_warnings()
|
|
|
- s = requests.session()
|
|
|
- # max_retries=3 重试3次
|
|
|
- s.mount('http://', HTTPAdapter(max_retries=3))
|
|
|
- s.mount('https://', HTTPAdapter(max_retries=3))
|
|
|
- response = s.post(url=url, headers=headers, data=payload, proxies=Common.tunnel_proxies(), verify=False,
|
|
|
- timeout=5)
|
|
|
- response.close()
|
|
|
- # Common.logger(log_type, crawler).info(f"get_videoList:{response.text}\n")
|
|
|
- if response.status_code != 200:
|
|
|
- Common.logger(log_type, crawler).warning(f"get_videoList_response:{response.text}\n")
|
|
|
- return
|
|
|
- elif 'data' not in response.json():
|
|
|
- Common.logger(log_type, crawler).warning(f"get_videoList_response:{response.json()}\n")
|
|
|
- return
|
|
|
- elif 'visionProfilePhotoList' not in response.json()['data']:
|
|
|
- Common.logger(log_type, crawler).warning(f"get_videoList_response:{response.json()['data']}\n")
|
|
|
- return
|
|
|
- elif 'feeds' not in response.json()['data']['visionProfilePhotoList']:
|
|
|
- Common.logger(log_type, crawler).warning(
|
|
|
- f"get_videoList_response:{response.json()['data']['visionProfilePhotoList']}\n")
|
|
|
- return
|
|
|
- elif len(response.json()['data']['visionProfilePhotoList']['feeds']) == 0:
|
|
|
- Common.logger(log_type, crawler).info("没有更多视频啦 ~\n")
|
|
|
- return
|
|
|
- else:
|
|
|
- feeds = response.json()['data']['visionProfilePhotoList']['feeds']
|
|
|
- pcursor = response.json()['data']['visionProfilePhotoList']['pcursor']
|
|
|
- # Common.logger(log_type, crawler).info(f"feeds0: {feeds}\n")
|
|
|
- for i in range(len(feeds)):
|
|
|
- if 'photo' not in feeds[i]:
|
|
|
- Common.logger(log_type, crawler).warning(f"get_videoList:{feeds[i]}\n")
|
|
|
- break
|
|
|
-
|
|
|
- # video_title
|
|
|
- if 'caption' not in feeds[i]['photo']:
|
|
|
- video_title = cls.random_title(log_type, crawler)
|
|
|
- elif feeds[i]['photo']['caption'].strip() == "":
|
|
|
- video_title = cls.random_title(log_type, crawler)
|
|
|
- else:
|
|
|
- video_title = cls.video_title(log_type, crawler, feeds[i]['photo']['caption'])
|
|
|
-
|
|
|
- if 'videoResource' not in feeds[i]['photo'] \
|
|
|
- and 'manifest' not in feeds[i]['photo'] \
|
|
|
- and 'manifestH265' not in feeds[i]['photo']:
|
|
|
- Common.logger(log_type, crawler).warning(f"get_videoList:{feeds[i]['photo']}\n")
|
|
|
- break
|
|
|
- videoResource = feeds[i]['photo']['videoResource']
|
|
|
-
|
|
|
- if 'h264' not in videoResource and 'hevc' not in videoResource:
|
|
|
- Common.logger(log_type, crawler).warning(f"get_videoList:{videoResource}\n")
|
|
|
- break
|
|
|
-
|
|
|
- # video_id
|
|
|
- if 'h264' in videoResource and 'videoId' in videoResource['h264']:
|
|
|
- video_id = videoResource['h264']['videoId']
|
|
|
- elif 'hevc' in videoResource and 'videoId' in videoResource['hevc']:
|
|
|
- video_id = videoResource['hevc']['videoId']
|
|
|
- else:
|
|
|
- video_id = ""
|
|
|
-
|
|
|
- # play_cnt
|
|
|
- if 'viewCount' not in feeds[i]['photo']:
|
|
|
- play_cnt = 0
|
|
|
- else:
|
|
|
- play_cnt = int(feeds[i]['photo']['viewCount'])
|
|
|
-
|
|
|
- # like_cnt
|
|
|
- if 'realLikeCount' not in feeds[i]['photo']:
|
|
|
- like_cnt = 0
|
|
|
- else:
|
|
|
- like_cnt = feeds[i]['photo']['realLikeCount']
|
|
|
-
|
|
|
- # publish_time
|
|
|
- if 'timestamp' not in feeds[i]['photo']:
|
|
|
- publish_time_stamp = 0
|
|
|
- publish_time_str = ''
|
|
|
- publish_time = 0
|
|
|
- else:
|
|
|
- publish_time_stamp = int(int(feeds[i]['photo']['timestamp']) / 1000)
|
|
|
- publish_time_str = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(publish_time_stamp))
|
|
|
- publish_time = int((int(time.time()) - publish_time_stamp) / (3600 * 24))
|
|
|
-
|
|
|
- # duration
|
|
|
- if 'duration' not in feeds[i]['photo']:
|
|
|
- duration = 0
|
|
|
- else:
|
|
|
- duration = int(int(feeds[i]['photo']['duration']) / 1000)
|
|
|
-
|
|
|
- # video_width / video_height / video_url
|
|
|
- mapping = {}
|
|
|
- for item in ['width', 'height', 'url']:
|
|
|
- try:
|
|
|
- val = str(videoResource['h264']['adaptationSet'][0]['representation'][0][item])
|
|
|
- except Exception:
|
|
|
- val = str(videoResource['hevc']['adaptationSet'][0]['representation'][0][item])
|
|
|
- except:
|
|
|
- val = ''
|
|
|
- mapping[item] = val
|
|
|
- video_width = int(mapping['width']) if mapping['width'] != '' else 0
|
|
|
- video_height = int(mapping['height']) if mapping['height'] != '' else 0
|
|
|
- video_url = mapping['url']
|
|
|
-
|
|
|
- # cover_url
|
|
|
- if 'coverUrl' not in feeds[i]['photo']:
|
|
|
- cover_url = ""
|
|
|
- else:
|
|
|
- cover_url = feeds[i]['photo']['coverUrl']
|
|
|
-
|
|
|
- # user_name / avatar_url
|
|
|
- try:
|
|
|
- user_name = feeds[i]['author']['name']
|
|
|
- avatar_url = feeds[i]['author']['headerUrl']
|
|
|
- except Exception:
|
|
|
- user_name = ''
|
|
|
- avatar_url = ''
|
|
|
-
|
|
|
- video_dict = {'video_title': video_title,
|
|
|
- 'video_id': video_id,
|
|
|
- 'play_cnt': play_cnt,
|
|
|
- 'comment_cnt': 0,
|
|
|
- 'like_cnt': like_cnt,
|
|
|
- 'share_cnt': 0,
|
|
|
- 'video_width': video_width,
|
|
|
- 'video_height': video_height,
|
|
|
- 'duration': duration,
|
|
|
- 'publish_time': publish_time,
|
|
|
- 'publish_time_stamp': publish_time_stamp,
|
|
|
- 'publish_time_str': publish_time_str,
|
|
|
- 'user_name': user_name,
|
|
|
- 'user_id': out_uid,
|
|
|
- 'avatar_url': avatar_url,
|
|
|
- 'cover_url': cover_url,
|
|
|
- 'video_url': video_url,
|
|
|
- 'session': f"kuaishou{int(time.time())}"}
|
|
|
-
|
|
|
- rule_1 = cls.download_rule(video_dict, rule_dict_1)
|
|
|
- Common.logger(log_type, crawler).info(f"video_title:{video_title}")
|
|
|
- Common.logger(log_type, crawler).info(f"video_id:{video_id}\n")
|
|
|
-
|
|
|
- Common.logger(log_type, crawler).info(
|
|
|
- f"play_cnt:{video_dict['play_cnt']}{rule_dict_1['play_cnt']}, {eval(str(video_dict['play_cnt']) + str(rule_dict_1['play_cnt']))}")
|
|
|
- Common.logger(log_type, crawler).info(
|
|
|
- f"like_cnt:{video_dict['like_cnt']}{rule_dict_1['like_cnt']}, {eval(str(video_dict['like_cnt']) + str(rule_dict_1['like_cnt']))}")
|
|
|
- Common.logger(log_type, crawler).info(
|
|
|
- f"video_width:{video_dict['video_width']}{rule_dict_1['video_width']}, {eval(str(video_dict['video_width']) + str(rule_dict_1['video_width']))}")
|
|
|
- Common.logger(log_type, crawler).info(
|
|
|
- f"video_height:{video_dict['video_height']}{rule_dict_1['video_height']}, {eval(str(video_dict['video_height']) + str(rule_dict_1['video_height']))}")
|
|
|
- Common.logger(log_type, crawler).info(
|
|
|
- f"duration:{video_dict['duration']}{rule_dict_1['duration']}, {eval(str(video_dict['duration']) + str(rule_dict_1['duration']))}")
|
|
|
+ try:
|
|
|
+ if download_cnt_1 >= int(
|
|
|
+ rule_dict_1['download_cnt'].replace("=", "")[-1].replace("<", "")[-1].replace(">", "")[
|
|
|
+ -1]) and download_cnt_2 >= int(
|
|
|
+ rule_dict_2['download_cnt'].replace("=", "")[-1].replace("<", "")[-1].replace(">", "")[-1]):
|
|
|
Common.logger(log_type, crawler).info(
|
|
|
- f"publish_time:{video_dict['publish_time']}{rule_dict_1['publish_time']}, {eval(str(video_dict['publish_time']) + str(rule_dict_1['publish_time']))}")
|
|
|
- Common.logger(log_type, crawler).info(f"rule_1:{rule_1}\n")
|
|
|
+ f"规则1已下载{download_cnt_1}条视频，规则2已下载{download_cnt_2}条视频\n")
|
|
|
+ return
|
|
|
|
|
|
- rule_2 = cls.download_rule(video_dict, rule_dict_2)
|
|
|
- Common.logger(log_type, crawler).info(
|
|
|
- f"play_cnt:{video_dict['play_cnt']}{rule_dict_2['play_cnt']}, {eval(str(video_dict['play_cnt']) + str(rule_dict_2['play_cnt']))}")
|
|
|
- Common.logger(log_type, crawler).info(
|
|
|
- f"like_cnt:{video_dict['like_cnt']}{rule_dict_2['like_cnt']}, {eval(str(video_dict['like_cnt']) + str(rule_dict_2['like_cnt']))}")
|
|
|
- Common.logger(log_type, crawler).info(
|
|
|
- f"video_width:{video_dict['video_width']}{rule_dict_2['video_width']}, {eval(str(video_dict['video_width']) + str(rule_dict_2['video_width']))}")
|
|
|
- Common.logger(log_type, crawler).info(
|
|
|
- f"video_height:{video_dict['video_height']}{rule_dict_2['video_height']}, {eval(str(video_dict['video_height']) + str(rule_dict_2['video_height']))}")
|
|
|
- Common.logger(log_type, crawler).info(
|
|
|
- f"duration:{video_dict['duration']}{rule_dict_2['duration']}, {eval(str(video_dict['duration']) + str(rule_dict_2['duration']))}")
|
|
|
- Common.logger(log_type, crawler).info(
|
|
|
- f"publish_time:{video_dict['publish_time']}{rule_dict_2['publish_time']}, {eval(str(video_dict['publish_time']) + str(rule_dict_2['publish_time']))}")
|
|
|
- Common.logger(log_type, crawler).info(f"rule_2:{rule_2}\n")
|
|
|
-
|
|
|
- if video_title == "" or video_url == "":
|
|
|
- Common.logger(log_type, crawler).info("无效视频\n")
|
|
|
- break
|
|
|
- elif rule_1 is True:
|
|
|
- if download_cnt_1 < int(
|
|
|
- rule_dict_1['download_cnt'].replace("=", "")[-1].replace("<", "")[-1].replace(">",
|
|
|
- "")[
|
|
|
- -1]):
|
|
|
- download_finished = cls.download_publish(log_type=log_type,
|
|
|
- crawler=crawler,
|
|
|
- strategy=strategy,
|
|
|
- video_dict=video_dict,
|
|
|
- rule_dict=rule_dict_1,
|
|
|
- our_uid=our_uid,
|
|
|
- oss_endpoint=oss_endpoint,
|
|
|
- env=env,
|
|
|
- machine=machine)
|
|
|
- if download_finished is True:
|
|
|
- download_cnt_1 += 1
|
|
|
- elif rule_2 is True:
|
|
|
- if download_cnt_2 < int(
|
|
|
- rule_dict_2['download_cnt'].replace("=", "")[-1].replace("<", "")[-1].replace(">",
|
|
|
- "")[
|
|
|
- -1]):
|
|
|
- download_finished = cls.download_publish(log_type=log_type,
|
|
|
- crawler=crawler,
|
|
|
- strategy=strategy,
|
|
|
- video_dict=video_dict,
|
|
|
- rule_dict=rule_dict_2,
|
|
|
- our_uid=our_uid,
|
|
|
- oss_endpoint=oss_endpoint,
|
|
|
- env=env,
|
|
|
- machine=machine)
|
|
|
- if download_finished is True:
|
|
|
- download_cnt_2 += 1
|
|
|
- else:
|
|
|
- Common.logger(log_type, crawler).info("不满足下载规则\n")
|
|
|
- # Common.logger(log_type, crawler).info(f"feeds: {feeds}\n")
|
|
|
+ url = "https://www.kuaishou.com/graphql"
|
|
|
+ payload = json.dumps({
|
|
|
+ "operationName": "visionProfilePhotoList",
|
|
|
+ "variables": {
|
|
|
+ "userId": out_uid,
|
|
|
+ "pcursor": pcursor,
|
|
|
+ "page": "profile"
|
|
|
+ },
|
|
|
+ "query": "fragment photoContent on PhotoEntity {\n id\n duration\n caption\n originCaption\n likeCount\n viewCount\n realLikeCount\n coverUrl\n photoUrl\n photoH265Url\n manifest\n manifestH265\n videoResource\n coverUrls {\n url\n __typename\n }\n timestamp\n expTag\n animatedCoverUrl\n distance\n videoRatio\n liked\n stereoType\n profileUserTopPhoto\n musicBlocked\n __typename\n}\n\nfragment feedContent on Feed {\n type\n author {\n id\n name\n headerUrl\n following\n headerUrls {\n url\n __typename\n }\n __typename\n }\n photo {\n ...photoContent\n __typename\n }\n canAddComment\n llsid\n status\n currentPcursor\n tags {\n type\n name\n __typename\n }\n __typename\n}\n\nquery visionProfilePhotoList($pcursor: String, $userId: String, $page: String, $webPageArea: String) {\n visionProfilePhotoList(pcursor: $pcursor, userId: $userId, page: $page, webPageArea: $webPageArea) {\n result\n llsid\n webPageArea\n feeds {\n ...feedContent\n __typename\n }\n hostName\n pcursor\n __typename\n }\n}\n"
|
|
|
+ })
|
|
|
+
|
|
|
+ headers = {
|
|
|
+ 'Cookie': 'kpf=PC_WEB; clientid=3; did=web_8832834f71f4c6ed405b5a35e95abc6d; kpn=KUAISHOU_VISION',
|
|
|
+ 'Referer': f'https://www.kuaishou.com/profile/{out_uid}',
|
|
|
+ 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36 Edg/110.0.1587.41',
|
|
|
+ 'content-type': 'application/json',
|
|
|
|
|
|
- if pcursor == "no_more":
|
|
|
- Common.logger(log_type, crawler).info("已经到底了，没有更多内容了\n")
|
|
|
+ }
|
|
|
+ urllib3.disable_warnings()
|
|
|
+ s = requests.session()
|
|
|
+ # max_retries=3 重试3次
|
|
|
+ s.mount('http://', HTTPAdapter(max_retries=3))
|
|
|
+ s.mount('https://', HTTPAdapter(max_retries=3))
|
|
|
+ response = s.post(url=url, headers=headers, data=payload, proxies=Common.tunnel_proxies(), verify=False,
|
|
|
+ timeout=10)
|
|
|
+ response.close()
|
|
|
+ # Common.logger(log_type, crawler).info(f"get_videoList:{response.text}\n")
|
|
|
+ if response.status_code != 200:
|
|
|
+ Common.logger(log_type, crawler).warning(f"get_videoList_response:{response.text}\n")
|
|
|
return
|
|
|
- except Exception as e:
|
|
|
- Common.logger(log_type, crawler).error(f"get_videoList:{e}\n")
|
|
|
+ elif 'data' not in response.json():
|
|
|
+ Common.logger(log_type, crawler).warning(f"get_videoList_response:{response.json()}\n")
|
|
|
+ return
|
|
|
+ elif 'visionProfilePhotoList' not in response.json()['data']:
|
|
|
+ Common.logger(log_type, crawler).warning(f"get_videoList_response:{response.json()['data']}\n")
|
|
|
+ return
|
|
|
+ elif 'feeds' not in response.json()['data']['visionProfilePhotoList']:
|
|
|
+ Common.logger(log_type, crawler).warning(
|
|
|
+ f"get_videoList_response:{response.json()['data']['visionProfilePhotoList']}\n")
|
|
|
+ return
|
|
|
+ elif len(response.json()['data']['visionProfilePhotoList']['feeds']) == 0:
|
|
|
+ Common.logger(log_type, crawler).info("没有更多视频啦 ~\n")
|
|
|
+ return
|
|
|
+ else:
|
|
|
+ feeds = response.json()['data']['visionProfilePhotoList']['feeds']
|
|
|
+ pcursor = response.json()['data']['visionProfilePhotoList']['pcursor']
|
|
|
+ # Common.logger(log_type, crawler).info(f"feeds0: {feeds}\n")
|
|
|
+ for i in range(len(feeds)):
|
|
|
+ if 'photo' not in feeds[i]:
|
|
|
+ Common.logger(log_type, crawler).warning(f"get_videoList:{feeds[i]}\n")
|
|
|
+ break
|
|
|
+
|
|
|
+ # video_title
|
|
|
+ if 'caption' not in feeds[i]['photo']:
|
|
|
+ video_title = cls.random_title(log_type, crawler)
|
|
|
+ elif feeds[i]['photo']['caption'].strip() == "":
|
|
|
+ video_title = cls.random_title(log_type, crawler)
|
|
|
+ else:
|
|
|
+ video_title = cls.video_title(log_type, crawler, feeds[i]['photo']['caption'])
|
|
|
+
|
|
|
+ if 'videoResource' not in feeds[i]['photo'] \
|
|
|
+ and 'manifest' not in feeds[i]['photo'] \
|
|
|
+ and 'manifestH265' not in feeds[i]['photo']:
|
|
|
+ Common.logger(log_type, crawler).warning(f"get_videoList:{feeds[i]['photo']}\n")
|
|
|
+ break
|
|
|
+ videoResource = feeds[i]['photo']['videoResource']
|
|
|
+
|
|
|
+ if 'h264' not in videoResource and 'hevc' not in videoResource:
|
|
|
+ Common.logger(log_type, crawler).warning(f"get_videoList:{videoResource}\n")
|
|
|
+ break
|
|
|
+
|
|
|
+ # video_id
|
|
|
+ if 'h264' in videoResource and 'videoId' in videoResource['h264']:
|
|
|
+ video_id = videoResource['h264']['videoId']
|
|
|
+ elif 'hevc' in videoResource and 'videoId' in videoResource['hevc']:
|
|
|
+ video_id = videoResource['hevc']['videoId']
|
|
|
+ else:
|
|
|
+ video_id = ""
|
|
|
+
|
|
|
+ # play_cnt
|
|
|
+ if 'viewCount' not in feeds[i]['photo']:
|
|
|
+ play_cnt = 0
|
|
|
+ else:
|
|
|
+ play_cnt = int(feeds[i]['photo']['viewCount'])
|
|
|
+
|
|
|
+ # like_cnt
|
|
|
+ if 'realLikeCount' not in feeds[i]['photo']:
|
|
|
+ like_cnt = 0
|
|
|
+ else:
|
|
|
+ like_cnt = feeds[i]['photo']['realLikeCount']
|
|
|
+
|
|
|
+ # publish_time
|
|
|
+ if 'timestamp' not in feeds[i]['photo']:
|
|
|
+ publish_time_stamp = 0
|
|
|
+ publish_time_str = ''
|
|
|
+ publish_time = 0
|
|
|
+ else:
|
|
|
+ publish_time_stamp = int(int(feeds[i]['photo']['timestamp']) / 1000)
|
|
|
+ publish_time_str = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(publish_time_stamp))
|
|
|
+ publish_time = int((int(time.time()) - publish_time_stamp) / (3600 * 24))
|
|
|
+
|
|
|
+ # duration
|
|
|
+ if 'duration' not in feeds[i]['photo']:
|
|
|
+ duration = 0
|
|
|
+ else:
|
|
|
+ duration = int(int(feeds[i]['photo']['duration']) / 1000)
|
|
|
+
|
|
|
+ # video_width / video_height / video_url
|
|
|
+ mapping = {}
|
|
|
+ for item in ['width', 'height', 'url']:
|
|
|
+ try:
|
|
|
+ val = str(videoResource['h264']['adaptationSet'][0]['representation'][0][item])
|
|
|
+ except Exception:
|
|
|
+ val = str(videoResource['hevc']['adaptationSet'][0]['representation'][0][item])
|
|
|
+ except:
|
|
|
+ val = ''
|
|
|
+ mapping[item] = val
|
|
|
+ video_width = int(mapping['width']) if mapping['width'] != '' else 0
|
|
|
+ video_height = int(mapping['height']) if mapping['height'] != '' else 0
|
|
|
+ video_url = mapping['url']
|
|
|
+
|
|
|
+ # cover_url
|
|
|
+ if 'coverUrl' not in feeds[i]['photo']:
|
|
|
+ cover_url = ""
|
|
|
+ else:
|
|
|
+ cover_url = feeds[i]['photo']['coverUrl']
|
|
|
+
|
|
|
+ # user_name / avatar_url
|
|
|
+ try:
|
|
|
+ user_name = feeds[i]['author']['name']
|
|
|
+ avatar_url = feeds[i]['author']['headerUrl']
|
|
|
+ except Exception:
|
|
|
+ user_name = ''
|
|
|
+ avatar_url = ''
|
|
|
+
|
|
|
+ video_dict = {'video_title': video_title,
|
|
|
+ 'video_id': video_id,
|
|
|
+ 'play_cnt': play_cnt,
|
|
|
+ 'comment_cnt': 0,
|
|
|
+ 'like_cnt': like_cnt,
|
|
|
+ 'share_cnt': 0,
|
|
|
+ 'video_width': video_width,
|
|
|
+ 'video_height': video_height,
|
|
|
+ 'duration': duration,
|
|
|
+ 'publish_time': publish_time,
|
|
|
+ 'publish_time_stamp': publish_time_stamp,
|
|
|
+ 'publish_time_str': publish_time_str,
|
|
|
+ 'user_name': user_name,
|
|
|
+ 'user_id': out_uid,
|
|
|
+ 'avatar_url': avatar_url,
|
|
|
+ 'cover_url': cover_url,
|
|
|
+ 'video_url': video_url,
|
|
|
+ 'session': f"kuaishou{int(time.time())}"}
|
|
|
+
|
|
|
+ rule_1 = cls.download_rule(video_dict, rule_dict_1)
|
|
|
+ Common.logger(log_type, crawler).info(f"video_title:{video_title}")
|
|
|
+ Common.logger(log_type, crawler).info(f"video_id:{video_id}\n")
|
|
|
+
|
|
|
+ Common.logger(log_type, crawler).info(
|
|
|
+ f"play_cnt:{video_dict['play_cnt']}{rule_dict_1['play_cnt']}, {eval(str(video_dict['play_cnt']) + str(rule_dict_1['play_cnt']))}")
|
|
|
+ Common.logger(log_type, crawler).info(
|
|
|
+ f"like_cnt:{video_dict['like_cnt']}{rule_dict_1['like_cnt']}, {eval(str(video_dict['like_cnt']) + str(rule_dict_1['like_cnt']))}")
|
|
|
+ Common.logger(log_type, crawler).info(
|
|
|
+ f"video_width:{video_dict['video_width']}{rule_dict_1['video_width']}, {eval(str(video_dict['video_width']) + str(rule_dict_1['video_width']))}")
|
|
|
+ Common.logger(log_type, crawler).info(
|
|
|
+ f"video_height:{video_dict['video_height']}{rule_dict_1['video_height']}, {eval(str(video_dict['video_height']) + str(rule_dict_1['video_height']))}")
|
|
|
+ Common.logger(log_type, crawler).info(
|
|
|
+ f"duration:{video_dict['duration']}{rule_dict_1['duration']}, {eval(str(video_dict['duration']) + str(rule_dict_1['duration']))}")
|
|
|
+ Common.logger(log_type, crawler).info(
|
|
|
+ f"publish_time:{video_dict['publish_time']}{rule_dict_1['publish_time']}, {eval(str(video_dict['publish_time']) + str(rule_dict_1['publish_time']))}")
|
|
|
+ Common.logger(log_type, crawler).info(f"rule_1:{rule_1}\n")
|
|
|
+
|
|
|
+ rule_2 = cls.download_rule(video_dict, rule_dict_2)
|
|
|
+ Common.logger(log_type, crawler).info(
|
|
|
+ f"play_cnt:{video_dict['play_cnt']}{rule_dict_2['play_cnt']}, {eval(str(video_dict['play_cnt']) + str(rule_dict_2['play_cnt']))}")
|
|
|
+ Common.logger(log_type, crawler).info(
|
|
|
+ f"like_cnt:{video_dict['like_cnt']}{rule_dict_2['like_cnt']}, {eval(str(video_dict['like_cnt']) + str(rule_dict_2['like_cnt']))}")
|
|
|
+ Common.logger(log_type, crawler).info(
|
|
|
+ f"video_width:{video_dict['video_width']}{rule_dict_2['video_width']}, {eval(str(video_dict['video_width']) + str(rule_dict_2['video_width']))}")
|
|
|
+ Common.logger(log_type, crawler).info(
|
|
|
+ f"video_height:{video_dict['video_height']}{rule_dict_2['video_height']}, {eval(str(video_dict['video_height']) + str(rule_dict_2['video_height']))}")
|
|
|
+ Common.logger(log_type, crawler).info(
|
|
|
+ f"duration:{video_dict['duration']}{rule_dict_2['duration']}, {eval(str(video_dict['duration']) + str(rule_dict_2['duration']))}")
|
|
|
+ Common.logger(log_type, crawler).info(
|
|
|
+ f"publish_time:{video_dict['publish_time']}{rule_dict_2['publish_time']}, {eval(str(video_dict['publish_time']) + str(rule_dict_2['publish_time']))}")
|
|
|
+ Common.logger(log_type, crawler).info(f"rule_2:{rule_2}\n")
|
|
|
+
|
|
|
+ if video_title == "" or video_url == "":
|
|
|
+ Common.logger(log_type, crawler).info("无效视频\n")
|
|
|
+ break
|
|
|
+ elif rule_1 is True:
|
|
|
+ if download_cnt_1 < int(
|
|
|
+ rule_dict_1['download_cnt'].replace("=", "")[-1].replace("<", "")[-1].replace(">",
|
|
|
+ "")[
|
|
|
+ -1]):
|
|
|
+ download_finished = cls.download_publish(log_type=log_type,
|
|
|
+ crawler=crawler,
|
|
|
+ strategy=strategy,
|
|
|
+ video_dict=video_dict,
|
|
|
+ rule_dict=rule_dict_1,
|
|
|
+ our_uid=our_uid,
|
|
|
+ oss_endpoint=oss_endpoint,
|
|
|
+ env=env,
|
|
|
+ machine=machine)
|
|
|
+ if download_finished is True:
|
|
|
+ download_cnt_1 += 1
|
|
|
+ elif rule_2 is True:
|
|
|
+ if download_cnt_2 < int(
|
|
|
+ rule_dict_2['download_cnt'].replace("=", "")[-1].replace("<", "")[-1].replace(">",
|
|
|
+ "")[
|
|
|
+ -1]):
|
|
|
+ download_finished = cls.download_publish(log_type=log_type,
|
|
|
+ crawler=crawler,
|
|
|
+ strategy=strategy,
|
|
|
+ video_dict=video_dict,
|
|
|
+ rule_dict=rule_dict_2,
|
|
|
+ our_uid=our_uid,
|
|
|
+ oss_endpoint=oss_endpoint,
|
|
|
+ env=env,
|
|
|
+ machine=machine)
|
|
|
+ if download_finished is True:
|
|
|
+ download_cnt_2 += 1
|
|
|
+ else:
|
|
|
+ Common.logger(log_type, crawler).info("不满足下载规则\n")
|
|
|
+ # Common.logger(log_type, crawler).info(f"feeds: {feeds}\n")
|
|
|
+
|
|
|
+ if pcursor == "no_more":
|
|
|
+ Common.logger(log_type, crawler).info("已经到底了，没有更多内容了\n")
|
|
|
+ return
|
|
|
+ except Exception as e:
|
|
|
+ Common.logger(log_type, crawler).error(f"get_videoList:{e}\n")
|
|
|
|
|
|
@classmethod
|
|
|
def repeat_video(cls, log_type, crawler, video_id, video_title, publish_time, env, machine):
|
|
|
@@ -760,17 +741,21 @@ class Follow:
|
|
|
user_name = user["user_name"]
|
|
|
our_uid = user["our_uid"]
|
|
|
Common.logger(log_type, crawler).info(f"开始抓取 {user_name} 用户主页视频\n")
|
|
|
- cls.get_videoList(log_type=log_type,
|
|
|
- crawler=crawler,
|
|
|
- strategy=strategy,
|
|
|
- our_uid=our_uid,
|
|
|
- out_uid=out_uid,
|
|
|
- oss_endpoint=oss_endpoint,
|
|
|
- env=env,
|
|
|
- machine=machine)
|
|
|
- sleep_time = 120
|
|
|
- Common.logger(log_type, crawler).info(f"休眠{sleep_time}秒\n")
|
|
|
- time.sleep(sleep_time)
|
|
|
+ try:
|
|
|
+ cls.get_videoList(log_type=log_type,
|
|
|
+ crawler=crawler,
|
|
|
+ strategy=strategy,
|
|
|
+ our_uid=our_uid,
|
|
|
+ out_uid=out_uid,
|
|
|
+ oss_endpoint=oss_endpoint,
|
|
|
+ env=env,
|
|
|
+ machine=machine)
|
|
|
+ except Exception as e:
|
|
|
+ Common.logger(log_type, crawler).info(f"用户:{user_name}, 抓取异常:{e}\n")
|
|
|
+ continue
|
|
|
+ # sleep_time = 120
|
|
|
+ # Common.logger(log_type, crawler).info(f"休眠{sleep_time}秒\n")
|
|
|
+ # time.sleep(sleep_time)
|
|
|
|
|
|
|
|
|
if __name__ == "__main__":
|
