1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
# -*- coding:utf-8 -*-
# @Time : 2019/4/17 9:15
# @Author : litao
# -*- coding: utf-8 -*-
import os
import re
import time
import copy,random
import requests
import datetime
import json
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
from crawler.crawler_sys.framework.video_fields_std import Std_fields_video
from crawler.crawler_sys.utils.output_results import output_result
from crawler.crawler_sys.utils.util_logging import logged
from fontTools.ttLib import *
try:
from crawler_sys.framework.func_get_releaser_id import *
except:
from func_get_releaser_id import *
from crawler.crawler_sys.proxy_pool.func_get_proxy_form_kuaidaili import get_proxy
# from crawler.crawler_sys.utils.func_verification_code import Login
from crawler.crawler_sys.utils.trans_str_play_count_to_int import trans_play_count
class Crawler_kwai():
def __init__(self, timeout=None, platform='kwai'):
if timeout == None:
self.timeout = 10
else:
self.timeout = timeout
self.platform = platform
self.TotalVideo_num = None
self.midstepurl = None
std_fields = Std_fields_video()
self.video_data = std_fields.video_data
self.video_data['platform'] = self.platform
unused_key_list = ['channel', 'describe', 'repost_count', 'isOriginal']
for key in unused_key_list:
self.video_data.pop(key)
self.first_page_headers = {
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3",
"Accept-Encoding": "gzip, deflate, br",
"Accept-Language": "zh-CN,zh;q=0.9",
"Cache-Control": "max-age=0",
"Connection": "keep-alive",
"Host": "live.kuaishou.com",
"Upgrade-Insecure-Requests": "1",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36",
# "Cookie": "did=web_c7c42d62cbb24{0}4d1ca5ffca052c3; didv=1582271776000; sid=e12d2ec74ec7af3a24d{1}cd6;pua5rv=1".format(
# random.randint(1000, 9000), random.randint(20, 99)),
}
self.loginObj = Login()
self.get_cookies_and_front = self.loginObj.get_cookies_and_front
def get_cookies_and_font(self,releaserUrl):
self.cookie_dic, self.uni_code_dic = self.get_cookies_and_front(releaserUrl)
# self.cookie_dic = {}
# chrome_options = webdriver.ChromeOptions()
# chrome_options.add_argument('--headless')
# chrome_options.add_argument('--disable-gpu')
# # driver = webdriver.Remote(command_executor='http://192.168.18.11:4444/wd/hub',
# # desired_capabilities=DesiredCapabilities.CHROME)
# driver = webdriver.Chrome(r'chromedriver', options=chrome_options)
# driver.get(url)
# time.sleep(2)
# driver.get(url)
# cookie = driver.get_cookies()
# for k in cookie:
# self.cookie_dic[k["name"]] = k["value"]
# # print(self.cookie_dic)
#
# font_face = driver.find_element_by_xpath("/html/head/style[1]")
# font_woff_link = re.findall("url\('(.*?)'\)\s+format\('woff'\)", font_face.get_attribute("innerHTML"))
# woff_name = font_woff_link[0].split("/")[-1]
# print(woff_name)
# woff = requests.get(font_woff_link[0]).content
# os_path = "/home/hanye/"
# this_path = os.path.isdir(os_path)
# if not this_path:
# os_path = "."
# try:
# f = open("%s/%s.xml" % (os_path, woff_name), encoding="utf-8")
# except:
# woff = requests.get(font_woff_link[0],
# headers={
# "Referer": url,
# "Sec-Fetch-Mode": "cors",
# "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36"}).content
# with open("%s/%s" % (os_path, woff_name), "wb") as f:
# f.write(woff)
# font = TTFont("%s/%s" % (os_path, woff_name))
# font.saveXML("%s/%s.xml" % (os_path, woff_name))
# f = open("%s/%s.xml" % (os_path, woff_name), encoding="utf-8")
# #f = open("./%s.xml" % woff_name, encoding="utf-8")
# self.xml_text = f.read()
# driver.quit()
# self.uni_code_dic = self.get_num_dic()
def get_releaser_id(self,releaserUrl):
return get_releaser_id(platform=self.platform, releaserUrl=releaserUrl)
@staticmethod
def re_cal_count(count_num):
if isinstance(count_num, int):
return count_num
if isinstance(count_num, str):
if count_num[-1] == "w":
return int(float(count_num[:-1]) * 10000)
try:
return int(count_num)
except:
return False
return False
# def get_num_dic(self):
# xml_re = {
# '<TTGlyph name="(.*)" xMin="32" yMin="-6" xMax="526" yMax="729">': 0,
# '<TTGlyph name="(.*)" xMin="32" yMin="7" xMax="526" yMax="742">': 0,
# '<TTGlyph name="(.*)" xMin="98" yMin="13" xMax="363" yMax="726">': 1,
# '<TTGlyph name="(.*)" xMin="98" yMin="26" xMax="363" yMax="739">': 1,
# '<TTGlyph name="(.*)" xMin="32" yMin="13" xMax="527" yMax="732">': 2,
# '<TTGlyph name="(.*)" xMin="32" yMin="26" xMax="527" yMax="745">': 2,
# '<TTGlyph name="(.*)" xMin="25" yMin="-6" xMax="525" yMax="730">': 3,
# '<TTGlyph name="(.*)" xMin="25" yMin="7" xMax="525" yMax="743">': 3,
# '<TTGlyph name="(.*)" xMin="26" yMin="13" xMax="536" yMax="731">': 4,
# '<TTGlyph name="(.*)" xMin="26" yMin="26" xMax="536" yMax="744">': 4,
# '<TTGlyph name="(.*)" xMin="33" yMin="-5" xMax="526" yMax="717">': 5,
# '<TTGlyph name="(.*)" xMin="33" yMin="8" xMax="526" yMax="730">': 5,
# '<TTGlyph name="(.*)" xMin="39" yMin="-5" xMax="530" yMax="732">': 6,
# '<TTGlyph name="(.*)" xMin="39" yMin="8" xMax="530" yMax="745">': 6,
# '<TTGlyph name="(.*)" xMin="38" yMin="13" xMax="536" yMax="717">': 7,
# '<TTGlyph name="(.*)" xMin="38" yMin="26" xMax="536" yMax="730">': 7,
# '<TTGlyph name="(.*)" xMin="33" yMin="-7" xMax="525" yMax="731">': 8,
# '<TTGlyph name="(.*)" xMin="33" yMin="6" xMax="525" yMax="744">': 8,
# '<TTGlyph name="(.*)" xMin="37" yMin="-7" xMax="521" yMax="730">': 9,
# '<TTGlyph name="(.*)" xMin="37" yMin="6" xMax="521" yMax="743">': 9
# }
# uni_code_dic = {}
# try:
# for re_code in xml_re:
# code_dic = re.findall(re_code, self.xml_text)
# if code_dic:
# uni_code_dic[code_dic[0].replace("uni", "\\\\u").lower()] = xml_re[re_code]
# print("uni_code_dic", uni_code_dic)
# return uni_code_dic
# except:
# print(self.xml_text,"error front_error")
# return False
#
def unicode_to_num(self,uni_str):
count_num = str(uni_str.encode("unicode_escape"))[2:-1]
#print(count_num)
for i in self.uni_code_dic:
if i in count_num:
count_num = count_num.replace(i, str(self.uni_code_dic[i]))
#print(count_num)
return count_num
@staticmethod
def get_video_image(data):
pass
def get_web_url_cookies(self,releaserUrl):
# firset_page = requests.get(releaserUrl, headers=self.first_page_headers)
# cookie = firset_page.cookies
firset_page = requests.get(releaserUrl, headers=self.first_page_headers)
cookie = firset_page.cookies
cookie = requests.utils.dict_from_cookiejar(cookie)
cookie["pua5rv"] = "1"
cookie["didv"] = "1582271776000"
cookie["sid"] = "e12d2ec74ec7af3a24d{0}cd6".format(random.randint(10,99))
cookie.pop("kuaishou.live.bfb1s",0)
print(cookie)
return cookie
def releaser_page(self,releaserUrl,**kwargs):
for data in self.releaser_page_web(releaserUrl,**kwargs):
yield data
# for data in self.releaser_page_pc(releaserUrl,**kwargs):
# yield data
def releaser_page_web(self, releaserUrl,
output_to_file=False,
filepath=None,
releaser_page_num_max=5000,
output_to_es_raw=False,
es_index=None,
doc_type=None,
output_to_es_register=False,
push_to_redis=False, proxies_num=None, **kwargs):
"""
get video info from api instead of web page html
the most scroll page is 1000
# """
releaser = ""
count = 1
# has_more = True
retry_time = 0
result_list = []
releaser_id = self.get_releaser_id(releaserUrl)
releaserUrl = 'https://live.kuaishou.com/profile/%s' % releaser_id
principalId = releaser_id
self.video_data['releaserUrl'] = releaserUrl
pcursor = None
headers = {
"Accept": "application/json",
"Accept-Encoding": "gzip, deflate",
"Accept-Language": "zh,zh-CN;q=0.9",
"Connection": "keep-alive",
"Content-Type": "application/json; charset=UTF-8",
"Cookie": "clientid=3; did=web_549cd4825914642449695ddccf5bfa99; client_key=65890b29; userId=%s; didv=1589785882000; sid=a94d55c86bbbccd28b8e2a8d" % random.randint(861446000,861449800),
"Host": "c.kuaishou.com",
"kpf": "H5",
"kpn": "KUAISHOU",
"Origin": "https://c.kuaishou.com",
"Referer": "https://c.kuaishou.com/fw/user/%s?fid=1535125321&cc=share_copylink&shareMethod=TOKEN&docId=0&kpn=KUAISHOU&subBiz=PROFILE&shareId=176513752168&docABKey=share_textid_profile&shareToken=X6btjdy2izGxVqQ_A&shareResourceType=PROFILE_OTHER&groupABKey=share_group_profile&groupName=&expTag=null&appType=21&shareObjectId=1478754458&shareUrlOpened=0" %releaser_id,
"Sec-Fetch-Dest": "empty",
"Sec-Fetch-Mode": "cors",
"Sec-Fetch-Site": "same-origin",
"User-Agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 13_2_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.0.3 Mobile/15E148 Safari/604.1",
}
# cookies = self.get_web_url_cookies(headers["Referer"])
proxies = get_proxy(proxies_num)
while count <= releaser_page_num_max and count <= 1000 and pcursor != "no_more":
try:
if proxies_num:
get_page = requests.post("https://c.kuaishou.com/rest/kd/feed/profile",
json={"eid": releaser_id, "count": 18, "pcursor": pcursor},
headers=headers, timeout=10, proxies=proxies)
else:
get_page = requests.post("https://c.kuaishou.com/rest/kd/feed/profile",
json={"eid": releaser_id, "count": 18, "pcursor": pcursor},
headers=headers, timeout=10)
except:
proxies = get_proxy(proxies_num)
continue
# print(get_page.content)
time.sleep(random.randint(3,4))
page_dic = get_page.json()
data_list = page_dic.get("feeds")
# print(data_list)
# if not data_list:
# get_page = requests.post("https://kpfbeijing.m.chenzhongtech.com/rest/kd/feed/profile",
# json={"eid": releaser_id, "count":50, "pcursor": pcursor},
# headers=headers, timeout=10)
# page_dic = get_page.json()
# data_list = page_dic.get("feeds")
# time.sleep(2)
if not data_list:
print("no more data at releaser: %s page: %s " % (releaser_id, count))
proxies = get_proxy(proxies_num)
retry_time += 1
if retry_time > 3:
proxies_num = 0
if retry_time > 5:
pcursor = "no_more"
continue
else:
pcursor = page_dic.get("pcursor")
print("get data at releaser: %s page: %s" % (releaser_id, count))
count += 1
for info_dic in data_list:
video_dic = copy.deepcopy(self.video_data)
try:
video_dic['title'] = info_dic.get('caption')
releaser_id_ = info_dic.get("userEid")
photoId_list = info_dic.get('share_info').split("&")
for photoid in photoId_list:
if "photoId=" in photoid:
photoid = photoid.replace("photoId=", "")
break
video_dic['video_id'] = photoid
video_dic['url'] = "https://live.kuaishou.com/u/%s/%s" % (releaser_id_, photoid)
video_dic['release_time'] = info_dic.get('timestamp')
video_dic['releaser'] = info_dic.get("userName")
video_dic['play_count'] = trans_play_count(info_dic.get("viewCount"))
video_dic['comment_count'] = trans_play_count(info_dic.get("commentCount"))
video_dic['favorite_count'] = trans_play_count(info_dic.get('likeCount'))
video_dic['repost_count'] = trans_play_count(info_dic.get('forwardCount'))
video_dic['fetch_time'] = int(time.time() * 1e3)
try:
video_dic['duration'] = int(info_dic.get("ext_params").get("video")/1000)
except:
video_dic['duration'] = 0
print("duration error")
video_dic['releaser_id_str'] = "kwai_%s" % (releaser_id_)
video_dic['releaserUrl'] = 'https://live.kuaishou.com/profile/%s' % releaser_id_
video_dic['video_img'] = info_dic.get("coverUrls")[0].get("url")
except Exception as e:
print(e)
continue
if video_dic['play_count'] is False or video_dic['comment_count'] is False or video_dic[
'favorite_count'] is False:
print(info_dic)
continue
else:
yield video_dic
# @logged
def releaser_page_pc(self, releaserUrl,
output_to_file=False,
filepath=None,
releaser_page_num_max=10000,
output_to_es_raw=False,
es_index=None,
doc_type=None,
output_to_es_register=False,
push_to_redis=False,proxies_num=None):
"""
get video info from api instead of web page html
the most scroll page is 1000
"""
releaser = ""
user_id = "153512{0}".format(random.randint(1000,9000))
proxies = get_proxy(proxies_num)
headers = {
"accept": "*/*",
"Accept-Encoding": "gzip, deflate, br",
"Accept-Language": "zh-CN,zh;q=0.9",
"Connection": "keep-alive",
"content-type": "application/json",
"Cookie": "did=web_504e72386a69c6d6172f1457b591415c ;userId=%s" % (user_id),
"Host": "live.kuaishou.com",
"Origin": "https://live.kuaishou.com",
"Referer": releaserUrl,
"Sec-Fetch-Mode": "cors",
"Sec-Fetch-Site": "same-origin",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36"
}
count = 1
# has_more = True
retry_time = 0
result_list = []
releaser_id = self.get_releaser_id(releaserUrl)
pcursor = ""
principalId = releaser_id
self.video_data['releaserUrl'] = releaserUrl
while count <= releaser_page_num_max and count <= 1000 and pcursor != "no_more":
time.sleep(random.randint(1,2))
# self.get_cookies_and_font(releaserUrl)
url_dic = {"operationName":"publicFeedsQuery","variables":
{"principalId":releaser_id,"pcursor":pcursor,"count":100},
"query":"query publicFeedsQuery($principalId: String, $pcursor: String, $count: Int) {\n publicFeeds(principalId: $principalId, pcursor: $pcursor, count: $count) {\n pcursor\n live {\n user {\n id\n avatar\n name\n __typename\n }\n watchingCount\n poster\n coverUrl\n caption\n id\n playUrls {\n quality\n url\n __typename\n }\n quality\n gameInfo {\n category\n name\n pubgSurvival\n type\n kingHero\n __typename\n }\n hasRedPack\n liveGuess\n expTag\n __typename\n }\n list {\n id\n thumbnailUrl\n poster\n workType\n type\n useVideoPlayer\n imgUrls\n imgSizes\n magicFace\n musicName\n caption\n location\n liked\n onlyFollowerCanComment\n relativeHeight\n timestamp\n width\n height\n counts {\n displayView\n displayLike\n displayComment\n __typename\n }\n user {\n id\n eid\n name\n avatar\n __typename\n }\n expTag\n __typename\n }\n __typename\n }\n}\n"}
api_url = 'https://live.kuaishou.com/m_graphql'
try:
if proxies:
get_page = requests.post(api_url, headers=headers, json=url_dic,timeout=5,proxies=proxies)
else:
get_page = requests.post(api_url, headers=headers, json=url_dic,timeout=5)
except:
proxies = get_proxy(proxies_num)
continue
#print(get_page.content)
page_dic = get_page.json()
data_list = page_dic.get("data").get("publicFeeds").get("list")
#print(data_list)
if data_list == []:
print("no more data at releaser: %s page: %s " % (releaser_id, count))
# self.loginObj.delete_cookies(self.cookie_dic)
proxies = get_proxy(proxies_num)
retry_time += 1
if retry_time > 3:
pcursor = "no_more"
continue
else:
pcursor = page_dic.get("data").get("publicFeeds").get("pcursor")
print("get data at releaser: %s page: %s" % (releaser_id, count))
count += 1
for info_dic in data_list:
video_dic = copy.deepcopy(self.video_data)
video_dic['title'] = info_dic.get('caption')
releaser_id = info_dic.get('user').get("eid")
video_dic['url'] = "https://live.kuaishou.com/u/%s/%s" % (releaser_id, info_dic.get('id'))
video_dic['releaser'] = info_dic.get('user').get("name")
video_dic['release_time'] = info_dic.get('timestamp')
video_dic['play_count'] = trans_play_count(info_dic.get('counts').get("displayView"))
video_dic['comment_count'] = trans_play_count(info_dic.get('counts').get("displayComment"))
video_dic['favorite_count'] = trans_play_count(info_dic.get('counts').get("displayLike"))
video_dic['video_id'] = info_dic.get('id')
video_dic['fetch_time'] = int(time.time() * 1e3)
video_dic['releaser_id_str'] = "kwai_%s"% (releaser_id)
video_dic['releaserUrl'] = 'https://live.kuaishou.com/profile/%s' % releaser_id
video_dic['video_img'] = self.get_video_image(info_dic)
if video_dic['play_count'] is False or video_dic['comment_count'] is False or video_dic['favorite_count'] is False:
print(info_dic)
continue
else:
yield video_dic
def releaser_page_by_time(self, start_time, end_time, url,allow,**kwargs):
count_false = 0
for res in self.releaser_page(url,proxies_num=kwargs.get("proxies_num")):
video_time = res["release_time"]
# print(res)
if video_time:
if start_time < video_time:
if video_time < end_time:
yield res
else:
count_false += 1
if count_false > allow:
break
else:
yield res
def get_releaser_follower_num(self, releaserUrl):
count_true = 0
headers = {
"Accept": "*/*",
"Accept-Encoding": "gzip, deflate, br",
"Accept-Language": "zh-CN,zh;q=0.9",
"content-type": "application/json",
"Referer": releaserUrl,
"Origin": "https://live.kuaishou.com",
"Cache-Control": "max-age=0",
"Connection": "keep-alive",
"Host": "live.kuaishou.com",
"Upgrade-Insecure-Requests": "1",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36",
"Sec-Fetch-Mode": "cors",
"Sec-Fetch-Site": "same-origin",
}
while count_true < 5:
proxies = get_proxy(proxies_num=1)
self.get_cookies_and_font(releaserUrl)
releaser_id = self.get_releaser_id(releaserUrl)
if not releaser_id:
return None, None
post_url = 'https://live.kuaishou.com/graphql'
post_dic = {"operationName": "userInfoQuery", "variables": {"principalId": releaser_id},
"query": "query userInfoQuery($principalId: String) {\n userInfo(principalId: $principalId) {\n id\n principalId\n kwaiId\n eid\n userId\n profile\n name\n description\n sex\n constellation\n cityName\n living\n watchingCount\n isNew\n privacy\n feeds {\n eid\n photoId\n thumbnailUrl\n timestamp\n __typename\n }\n verifiedStatus {\n verified\n description\n type\n new\n __typename\n }\n countsInfo {\n fan\n follow\n photo\n liked\n open\n playback\n private\n __typename\n }\n bannedStatus {\n banned\n defriend\n isolate\n socialBanned\n __typename\n }\n __typename\n }\n}\n"}
try:
releaser_page = requests.post(post_url, headers=headers, cookies=self.cookie_dic, json=post_dic,
proxies=proxies, timeout=2)
except:
releaser_page = requests.post(post_url, headers=headers, cookies=self.cookie_dic,
json=post_dic)
res_dic = releaser_page.json()
print(res_dic)
if res_dic.get("errors"):
self.loginObj.delete_cookies(self.cookie_dic)
try:
releaser_follower_num_str = res_dic["data"]["userInfo"]["countsInfo"]["fan"]
releaser_follower_num = self.re_cal_count(self.unicode_to_num(releaser_follower_num_str))
print(releaser_follower_num)
releaser_img = self.get_releaser_image(data=res_dic)
return releaser_follower_num, releaser_img
except:
if count_true == 4:
self.loginObj.delete_cookies(self.cookie_dic)
count_true += 1
return None, None
# @staticmethod
# def get_video_image(data):
# return data.get("poster")
# def get_releaser_follower_num(self, releaserUrl):
# self.get_cookies_and_font(releaserUrl)
# releaser_id = self.get_releaser_id(releaserUrl)
# releaserUrl = 'https://live.kuaishou.com/graphql'
# post_dic = {"operationName":"userInfoQuery","variables":{"principalId":releaser_id},"query":"query userInfoQuery($principalId: String) {\n userInfo(principalId: $principalId) {\n id\n principalId\n kwaiId\n eid\n userId\n profile\n name\n description\n sex\n constellation\n cityName\n living\n watchingCount\n isNew\n privacy\n feeds {\n eid\n photoId\n thumbnailUrl\n timestamp\n __typename\n }\n verifiedStatus {\n verified\n description\n type\n new\n __typename\n }\n countsInfo {\n fan\n follow\n photo\n liked\n open\n playback\n private\n __typename\n }\n bannedStatus {\n banned\n defriend\n isolate\n socialBanned\n __typename\n }\n __typename\n }\n}\n"}
# releaser_page = requests.post(releaserUrl, headers=self.first_page_headers, cookies=self.cookie_dic,json=post_dic)
# res_dic = releaser_page.json()
#
# try:
# releaser_follower_num_str =res_dic["data"]["userInfo"]["countsInfo"]["fan"]
# releaser_follower_num = self.re_cal_count(self.unicode_to_num(releaser_follower_num_str))
# print(releaser_follower_num)
# releaser_img = self.get_releaser_image(data=res_dic)
# return releaser_follower_num,releaser_img
# except:
# return None
def get_releaser_image(self, releaserUrl=None,data=None):
if releaserUrl:
self.get_cookies_and_font(releaserUrl)
releaser_id = self.get_releaser_id(releaserUrl)
releaserUrl = 'https://live.kuaishou.com/graphql'
post_dic = {"operationName": "userInfoQuery", "variables": {"principalId": releaser_id},
"query": "query userInfoQuery($principalId: String) {\n userInfo(principalId: $principalId) {\n id\n principalId\n kwaiId\n eid\n userId\n profile\n name\n description\n sex\n constellation\n cityName\n living\n watchingCount\n isNew\n privacy\n feeds {\n eid\n photoId\n thumbnailUrl\n timestamp\n __typename\n }\n verifiedStatus {\n verified\n description\n type\n new\n __typename\n }\n countsInfo {\n fan\n follow\n photo\n liked\n open\n playback\n private\n __typename\n }\n bannedStatus {\n banned\n defriend\n isolate\n socialBanned\n __typename\n }\n __typename\n }\n}\n"}
releaser_page = requests.post(releaserUrl, headers=self.first_page_headers, cookies=self.cookie_dic,
json=post_dic)
res_dic = releaser_page.json()
try:
releaser_img = res_dic["data"]["userInfo"]["profile"]
print(releaser_img)
return releaser_img
except:
return None
else:
releaser_img = data["data"]["userInfo"]["profile"]
print(releaser_img)
return releaser_img
if __name__ == '__main__':
test = Crawler_kwai()
url = 'https://live.kuaishou.com/profile/IIloveyoubaby'
user_lis = [
# "https://live.kuaishou.com/profile/3xx3vac2uctn2ak"
"https://live.kuaishou.com/profile/3xn3bwab5q5pehc",
"https://live.kuaishou.com/profile/3x25rpyd2v6qv86",
"https://live.kuaishou.com/profile/3xziqtumtj6xzkm",
"https://live.kuaishou.com/profile/3xugxze3x97r2w4",
"https://live.kuaishou.com/profile/3xnhsx3wt8if74c",
"https://live.kuaishou.com/profile/3xcdy8gzaqsy6zu",
"https://live.kuaishou.com/profile/3xid2nndq4fk3t6",
"https://live.kuaishou.com/profile/3xeqdvqjp553nvm",
"https://live.kuaishou.com/profile/3xhyd98hf8bcxsi",
"https://live.kuaishou.com/profile/3x9m4am579hrvfq",
"https://live.kuaishou.com/profile/3xkkkfxxd48dei6",
"https://live.kuaishou.com/profile/3xjqv4mspa4bw8i",
"https://live.kuaishou.com/profile/3xgxy8yiqnqtkt4",
"https://live.kuaishou.com/profile/3xxxsfnuie3ucfi",
"https://live.kuaishou.com/profile/3x3t5epr3max95y",
"https://live.kuaishou.com/profile/3xny3xcwghpi7yk",
"https://live.kuaishou.com/profile/3xcm5jbmtyhezj4",
"https://live.kuaishou.com/profile/3x7twx645iyapkm",
"https://live.kuaishou.com/profile/3xzu7cr583vt5zg",
"https://live.kuaishou.com/profile/3x83h23sbmjxiq4",
"https://live.kuaishou.com/profile/3xijrqj69f8ckjk",
"https://live.kuaishou.com/profile/3xv47uc6r7gq882",
"https://live.kuaishou.com/profile/3xqv5w2kzccqk5y",
"https://live.kuaishou.com/profile/3x5yh4d4wtfnvs6",
"https://live.kuaishou.com/profile/3xwxakqi8whe9ju",
"https://live.kuaishou.com/profile/3x58zdtbg9ecqxy",
"https://live.kuaishou.com/profile/3xd6szsxerggfu4",
"https://live.kuaishou.com/profile/3xzfhbh9q2afynk",
"https://live.kuaishou.com/profile/3xgy42jat4kp8yk",
"https://live.kuaishou.com/profile/3xq9ya2akj52f8a",
"https://live.kuaishou.com/profile/3xvbgjz6vxdr4zq",
"https://live.kuaishou.com/profile/3xaqiypqnwfwakg",
"https://live.kuaishou.com/profile/3x57bdie5v8bag6",
"https://live.kuaishou.com/profile/3x6e8hdhmtssdae",
"https://live.kuaishou.com/profile/3xeszmbm3rphnn4",
"https://live.kuaishou.com/profile/3x67fxqg6wd39tw",
]
for u in user_lis:
ttt = test.releaser_page_by_time(1577808000000,1585632335193,u, output_to_es_raw=True,
es_index='crawler-data-raw',
doc_type='doc',
releaser_page_num_max=2000,proxies_num=1,allow=10)
for t in ttt:
print(t)
# break