python爬虫----爬取阿里数据银行websocket接口
业务需求：爬取阿里品牌数据银行的自定义模块==>>>人群透视==>>>查看报告==>>数据
发现：数据通过websocket接口传递，此类型接口的详细理解大家可以参考：https://segmentfault.com/a/1190000013149749
最终获取页面：
页面获取情况如下：
绿色的就是我们需要模拟的请求，红色朝下的就是请求对应的数据，通过rid参数来找寻对应请求和数据，这个rid和时间戳很类似，没错这就是一个13位的时间戳，和随机数组合而成的：
randomID = str(int(time.time()*1000))+str(self.count).zfill(3)
观察发送的请求：
message = {
"method": "/iSheetCrowdService/report", "headers": {"rid": random_id, "type": "PULL"},
"body": {
"args": {
"id": "286",
"condition":"{\"compute\":\"INTERSECT\",\"ruleList\":[{\"filterList\":[{\"key\":\"brand\",\"type\":\"SINGLE_VALUE\",\"value\":\"372718624\"},{\"key\":\"ds\",\"type\":\"SINGLE_VALUE\",\"value\":\"20200224\"},{\"key\":\"stage\",\"type\":\"MULTI_VALUE\",\"value\":[\"1010\",\"1020\",\"1030\",\"1040\"]}],\"name\":\"stage\"},{\"type\":\"crowd\",\"value\":[66466812]}]}",
"tags": ["mobile_brand_name_prefer"],
"bizParam": {
"databankCrowdId": "50104182",
"bizType": "CUSTOM_ANALYSIS",
"tag_identifier": "all",
"captcha":\'%7B%22a%22%3A%22TSF2%22%2C%22c%22%3A%221582700342424%3A0.23973179491554664%22%2C%22d%22%3A%22nvc_register%22%2C%22h%22%3A%7B%22key1%22%3A%22code0%22%2C%22nvcCode%22%3A400%2C%22umidToken%22%3A%22T08C67EE3AD81E11A23D01F0EE4CA1134D6022447F84D66B6623678D5FE%22%7D%2C%22j%22%3A%7B%22test%22%3A1%7D%2C%22b%22%3A%22122%23i5kRCD9eEE%2BqAJpZy4pjEJponDJE7SNEEP7ZpJRBuDPpJFQLpCGwoHZDpJEL7SwBEyGZpJLlu4Ep%2BFQLpoGUEELWn4yE7SNEEP7ZpERBuDPE%2BBQPpC76EJponDJLKMQEspPA04nTtBOmKBvALOESIAOsJhoR8HJNZIbVrA4tlm9BE5R8XAJh3Ue7sqj97bm98oL6JXWpO%2F%2BDqMfEl8WxXWplul5EELXZ8CL6JNbERF3mqM3okBTlpM%2B1ul9rDLVZ8CRfJ4bEyF3mqW32E5pangLlul5EELXZ8oL6JNEEyB3DqMfbDEpxnSp1tP0EDLf%2F8om6J4EqRoBHqevfAIAKkS7gz4MzTChsGRkP%2BeqxYlg3ypGmtolPBVsN6ovcGQYuNVCPWaTtjBbU5X0QWvFMSFzE%2FaVEWBKYt4%2FavytijGp1%2FQCeg%2F2SfxjZw8fIlfio42QXEpWhdEspy4fBSEZgHrMRhwhnBIFLuxd8hTc7Y99x%2BfF2UuU5oOXLG0an0CHvFQqCYMqZXb8myhlZHuHOXI0GZ%2BPvFxGzVjTf4AmL63HeSjbSP8L6CSCuq47zX7tPDBWS%2FhdLqwO8dtOkEXes248plPRkVf5gVlcqsHSdYxDkjT%2FpfSszn8vXlIUg3GRKm9eMWi09PxekLM2tUu0nivXzonmbHdGHLsqhNe%2FbdjoKHYG6ygnnx3aZ9DU9ugUWmZgB9Ztbv1BYo%2FhPlYLykr4j14BCvVlwMUtgZbK%2BpgNu7vKERSRkRosaHoNotkt%2B%2BToClNeIRM%2Fk7vQm1x0YbZT3hzfU9k5kadIafvosIReZwiQhd4%2B0sYXOjxvChWtv2%2FSMKb9fIeSKsALCP%2FNshczJBF5y1TMo4YIPh7%2BaMuMfcUqmMC%2BWrr1Xm%2FUAjtyHnttlwQlkGDRPsSS4DMlM0OdWYLD9vL0ekEm7iz566ESLHP2aykbJ%2F3id3DwjcdgDENA6%2F8oojlvm6WP0JBDUviVTeDPK9V5RFekM3drtuDFit2UwRc%2B09xUvKcueMc%2FPrKKRhC%2FuRLXdx0WzgP4%2F2RJJeZhuKEQhYDTsFiDZnArDQMQyiMN0hRuwdfalhZFe27jXUG4Y%2BwPnHvpj1OXxEJ1VOgEtBzOO1AgwUr5SYa6UKhrbynm2X1J1HRyEn%2FVUqkvgc9Rx8ZYG2GqRr4L7eQ1N4sa7S6oqKEND6fX3eQhxFaqnimVCIg%2B6TwTp9Ant4P15WlGdVueq6HWATk8zB1CglVmsVH08lUwArNKjBpArD7v%2BIxx5VP1hJLChZOgfHqa6MVh7fP0lg6HXLeyMLSOXCz3oAK7iSOFkfu6RAx%2BGrBAj50ha%22%2C%22e%22%3A%22HELtCcggjijySBif5QK5Flm60fyrLzjVSvY2GZ7kF9k2ufvery5t6e1OxIGoUHpc7a0IbkE_0FA-F5WgiEpV7aeWlyQyxr1LL83v6PCoc3YbWdFNpRGiSow97HJFmhSolqL2iP8Yg3b6GvpNCl1IVN3_kiy7mdt7qA7PsE2Fu9J1ZID-lo1BWsvQpV6riLNbYizM9JlKkpiqJYbEB2zQGA%22%7D\'
},
"insightType": 0,
"interaction": \'false\',
"rateParam": {},
"appId": "208"}}}
其中关注几个变化的参数：databankCrowdId参数表示人群ID，condition参数含义未知可能与标签有关，可从https://databank.tmall.com/api/ecapi返回的数据得到；captcha则是先需要URL解码得到是字典格式的数据
{"a":"TSF2","c":"1582700342424:0.23973179491554664",
"d":"nvc_register",
"h":{"key1":"code0","nvcCode":400,"umidToken":"T08C67EE3AD81E11A23D01F0EE4CA1134D6022447F84D66B6623678D5FE"},
"j":{"test":1},
"b":"122#i5kRCD9eEE+qAJpZy4pjEJponDJE7SNEEP7ZpJRBuDPpJFQLpCGwoHZDpJEL7SwBEyGZpJLlu4Ep+FQLpoGUEELWn4yE7SNEEP7ZpERBuDPE+BQPpC76EJponDJLKMQEspPA04nTtBOmKBvALOESIAOsJhoR8HJNZIbVrA4tlm9BE5R8XAJh3Ue7sqj97bm98oL6JXWpO/+DqMfEl8WxXWplul5EELXZ8CL6JNbERF3mqM3okBTlpM+1ul9rDLVZ8CRfJ4bEyF3mqW32E5pangLlul5EELXZ8oL6JNEEyB3DqMfbDEpxnSp1tP0EDLf/8om6J4EqRoBHqevfAIAKkS7gz4MzTChsGRkP+eqxYlg3ypGmtolPBVsN6ovcGQYuNVCPWaTtjBbU5X0QWvFMSFzE/aVEWBKYt4/avytijGp1/QCeg/2SfxjZw8fIlfio42QXEpWhdEspy4fBSEZgHrMRhwhnBIFLuxd8hTc7Y99x+fF2UuU5oOXLG0an0CHvFQqCYMqZXb8myhlZHuHOXI0GZ+PvFxGzVjTf4AmL63HeSjbSP8L6CSCuq47zX7tPDBWS/hdLqwO8dtOkEXes248plPRkVf5gVlcqsHSdYxDkjT/pfSszn8vXlIUg3GRKm9eMWi09PxekLM2tUu0nivXzonmbHdGHLsqhNe/bdjoKHYG6ygnnx3aZ9DU9ugUWmZgB9Ztbv1BYo/hPlYLykr4j14BCvVlwMUtgZbK+pgNu7vKERSRkRosaHoNotkt++ToClNeIRM/k7vQm1x0YbZT3hzfU9k5kadIafvosIReZwiQhd4+0sYXOjxvChWtv2/SMKb9fIeSKsALCP/NshczJBF5y1TMo4YIPh7+aMuMfcUqmMC+Wrr1Xm/UAjtyHnttlwQlkGDRPsSS4DMlM0OdWYLD9vL0ekEm7iz566ESLHP2aykbJ/3id3DwjcdgDENA6/8oojlvm6WP0JBDUviVTeDPK9V5RFekM3drtuDFit2UwRc+09xUvKcueMc/PrKKRhC/uRLXdx0WzgP4/2RJJeZhuKEQhYDTsFiDZnArDQMQyiMN0hRuwdfalhZFe27jXUG4Y+wPnHvpj1OXxEJ1VOgEtBzOO1AgwUr5SYa6UKhrbynm2X1J1HRyEn/VUqkvgc9Rx8ZYG2GqRr4L7eQ1N4sa7S6oqKEND6fX3eQhxFaqnimVCIg+6TwTp9Ant4P15WlGdVueq6HWATk8zB1CglVmsVH08lUwArNKjBpArD7v+Ixx5VP1hJLChZOgfHqa6MVh7fP0lg6HXLeyMLSOXCz3oAK7iSOFkfu6RAx+GrBAj50ha",
"e":"HELtCcggjijySBif5QK5Flm60fyrLzjVSvY2GZ7kF9k2ufvery5t6e1OxIGoUHpc7a0IbkE_0FA-F5WgiEpV7aeWlyQyxr1LL83v6PCoc3YbWdFNpRGiSow97HJFmhSolqL2iP8Yg3b6GvpNCl1IVN3_kiy7mdt7qA7PsE2Fu9J1ZID-lo1BWsvQpV6riLNbYizM9JlKkpiqJYbEB2zQGA"}umidToken
c参数是时间戳+":"+随机数；h.umidToken也是和时间有关的数据，可从um.json页面获取tn参数值；b参数需要复杂计算，但是通过测试可以为空字符串
代码：
# -*- coding:utf-8 -*-import base64
import json
import os
import ssl
import zlib
import requests
import websocket
from requests.adapters import HTTPAdapter
try:
import thread
except ImportError:
import _thread as thread
import time
class Test(object):
def __init__(self, cookie_info):
self.count = 0
self.ws = None
super(Test, self).__init__()def on_message(self, message):
print("####### on_message #######")
print(message)
def on_error(self, error):
print("####### on_error #######")
print(error)
def on_close(self):
print("####### on_close #######")
print(self)
print("####### closed #######")
def on_open(self):
def run(*args):
# for i in range(5):
random_id = str(int(time.time() * 1000)) + str(self.count).zfill(2)
print(\'random_id-----------------------------\', random_id)
message = {"method": "/iSheetCrowdService/report",
"headers": {"rid": random_id, "type": "PULL"},
"body": {
"args": {
"id": "286",
"condition":"{\"compute\":\"INTERSECT\",\"ruleList\":[{\"filterList\":[{\"key\":\"brand\",\"type\":\"SINGLE_VALUE\",\"value\":\"372718624\"},{\"key\":\"ds\",\"type\":\"SINGLE_VALUE\",\"value\":\"20200224\"},{\"key\":\"stage\",\"type\":\"MULTI_VALUE\",\"value\":[\"1010\",\"1020\",\"1030\",\"1040\"]}],\"name\":\"stage\"},{\"type\":\"crowd\",\"value\":[66466812]}]}",
"tags": ["mobile_brand_name_prefer"],
"bizParam": {
"databankCrowdId": "50104182",
"bizType": "CUSTOM_ANALYSIS",
"tag_identifier": "all",
"captcha":\'%7B%22a%22%3A%22TSF2%22%2C%22c%22%3A%221582700342424%3A0.23973179491554664%22%2C%22d%22%3A%22nvc_register%22%2C%22h%22%3A%7B%22key1%22%3A%22code0%22%2C%22nvcCode%22%3A400%2C%22umidToken%22%3A%22T08C67EE3AD81E11A23D01F0EE4CA1134D6022447F84D66B6623678D5FE%22%7D%2C%22j%22%3A%7B%22test%22%3A1%7D%2C%22b%22%3A%22122%23i5kRCD9eEE%2BqAJpZy4pjEJponDJE7SNEEP7ZpJRBuDPpJFQLpCGwoHZDpJEL7SwBEyGZpJLlu4Ep%2BFQLpoGUEELWn4yE7SNEEP7ZpERBuDPE%2BBQPpC76EJponDJLKMQEspPA04nTtBOmKBvALOESIAOsJhoR8HJNZIbVrA4tlm9BE5R8XAJh3Ue7sqj97bm98oL6JXWpO%2F%2BDqMfEl8WxXWplul5EELXZ8CL6JNbERF3mqM3okBTlpM%2B1ul9rDLVZ8CRfJ4bEyF3mqW32E5pangLlul5EELXZ8oL6JNEEyB3DqMfbDEpxnSp1tP0EDLf%2F8om6J4EqRoBHqevfAIAKkS7gz4MzTChsGRkP%2BeqxYlg3ypGmtolPBVsN6ovcGQYuNVCPWaTtjBbU5X0QWvFMSFzE%2FaVEWBKYt4%2FavytijGp1%2FQCeg%2F2SfxjZw8fIlfio42QXEpWhdEspy4fBSEZgHrMRhwhnBIFLuxd8hTc7Y99x%2BfF2UuU5oOXLG0an0CHvFQqCYMqZXb8myhlZHuHOXI0GZ%2BPvFxGzVjTf4AmL63HeSjbSP8L6CSCuq47zX7tPDBWS%2FhdLqwO8dtOkEXes248plPRkVf5gVlcqsHSdYxDkjT%2FpfSszn8vXlIUg3GRKm9eMWi09PxekLM2tUu0nivXzonmbHdGHLsqhNe%2FbdjoKHYG6ygnnx3aZ9DU9ugUWmZgB9Ztbv1BYo%2FhPlYLykr4j14BCvVlwMUtgZbK%2BpgNu7vKERSRkRosaHoNotkt%2B%2BToClNeIRM%2Fk7vQm1x0YbZT3hzfU9k5kadIafvosIReZwiQhd4%2B0sYXOjxvChWtv2%2FSMKb9fIeSKsALCP%2FNshczJBF5y1TMo4YIPh7%2BaMuMfcUqmMC%2BWrr1Xm%2FUAjtyHnttlwQlkGDRPsSS4DMlM0OdWYLD9vL0ekEm7iz566ESLHP2aykbJ%2F3id3DwjcdgDENA6%2F8oojlvm6WP0JBDUviVTeDPK9V5RFekM3drtuDFit2UwRc%2B09xUvKcueMc%2FPrKKRhC%2FuRLXdx0WzgP4%2F2RJJeZhuKEQhYDTsFiDZnArDQMQyiMN0hRuwdfalhZFe27jXUG4Y%2BwPnHvpj1OXxEJ1VOgEtBzOO1AgwUr5SYa6UKhrbynm2X1J1HRyEn%2FVUqkvgc9Rx8ZYG2GqRr4L7eQ1N4sa7S6oqKEND6fX3eQhxFaqnimVCIg%2B6TwTp9Ant4P15WlGdVueq6HWATk8zB1CglVmsVH08lUwArNKjBpArD7v%2BIxx5VP1hJLChZOgfHqa6MVh7fP0lg6HXLeyMLSOXCz3oAK7iSOFkfu6RAx%2BGrBAj50ha%22%2C%22e%22%3A%22HELtCcggjijySBif5QK5Flm60fyrLzjVSvY2GZ7kF9k2ufvery5t6e1OxIGoUHpc7a0IbkE_0FA-F5WgiEpV7aeWlyQyxr1LL83v6PCoc3YbWdFNpRGiSow97HJFmhSolqL2iP8Yg3b6GvpNCl1IVN3_kiy7mdt7qA7PsE2Fu9J1ZID-lo1BWsvQpV6riLNbYizM9JlKkpiqJYbEB2zQGA%22%7D\'
},
"insightType": 0,
"interaction": \'false\',
"rateParam": {},
"appId": "208"}}}
# message = {"method":"/iSheetCrowdService/report","headers":{"rid":"158270035289505","type":"PULL"},"body":{"args":{"id":"286","condition":"{\"compute\":\"INTERSECT\",\"ruleList\":[{\"filterList\":[{\"key\":\"brand\",\"type\":\"SINGLE_VALUE\",\"value\":\"372718624\"},{\"key\":\"ds\",\"type\":\"SINGLE_VALUE\",\"value\":\"20200225\"},{\"key\":\"stage\",\"type\":\"MULTI_VALUE\",\"value\":[\"1010\",\"1020\",\"1030\",\"1040\"]}],\"name\":\"stage\"},{\"type\":\"crowd\",\"value\":[66466812]}]}","tags":["mobile_brand_name_prefer"],"bizParam":{"databankCrowdId":"50104182","bizType":"CUSTOM_ANALYSIS","tag_identifier":"all","captcha":"%7B%22a%22%3A%22TSF2%22%2C%22c%22%3A%221582700342424%3A0.23973179491554664%22%2C%22d%22%3A%22nvc_register%22%2C%22h%22%3A%7B%22key1%22%3A%22code0%22%2C%22nvcCode%22%3A400%2C%22umidToken%22%3A%22T08C67EE3AD81E11A23D01F0EE4CA1134D6022447F84D66B6623678D5FE%22%7D%2C%22j%22%3A%7B%22test%22%3A1%7D%2C%22b%22%3A%22122%23i5kRCD9eEE%2BqAJpZy4pjEJponDJE7SNEEP7ZpJRBuDPpJFQLpCGwoHZDpJEL7SwBEyGZpJLlu4Ep%2BFQLpoGUEELWn4yE7SNEEP7ZpERBuDPE%2BBQPpC76EJponDJLKMQEspPA04nTtBOmKBvALOESIAOsJhoR8HJNZIbVrA4tlm9BE5R8XAJh3Ue7sqj97bm98oL6JXWpO%2F%2BDqMfEl8WxXWplul5EELXZ8CL6JNbERF3mqM3okBTlpM%2B1ul9rDLVZ8CRfJ4bEyF3mqW32E5pangLlul5EELXZ8oL6JNEEyB3DqMfbDEpxnSp1tP0EDLf%2F8om6J4EqRoBHqevfAIAKkS7gz4MzTChsGRkP%2BeqxYlg3ypGmtolPBVsN6ovcGQYuNVCPWaTtjBbU5X0QWvFMSFzE%2FaVEWBKYt4%2FavytijGp1%2FQCeg%2F2SfxjZw8fIlfio42QXEpWhdEspy4fBSEZgHrMRhwhnBIFLuxd8hTc7Y99x%2BfF2UuU5oOXLG0an0CHvFQqCYMqZXb8myhlZHuHOXI0GZ%2BPvFxGzVjTf4AmL63HeSjbSP8L6CSCuq47zX7tPDBWS%2FhdLqwO8dtOkEXes248plPRkVf5gVlcqsHSdYxDkjT%2FpfSszn8vXlIUg3GRKm9eMWi09PxekLM2tUu0nivXzonmbHdGHLsqhNe%2FbdjoKHYG6ygnnx3aZ9DU9ugUWmZgB9Ztbv1BYo%2FhPlYLykr4j14BCvVlwMUtgZbK%2BpgNu7vKERSRkRosaHoNotkt%2B%2BToClNeIRM%2Fk7vQm1x0YbZT3hzfU9k5kadIafvosIReZwiQhd4%2B0sYXOjxvChWtv2%2FSMKb9fIeSKsALCP%2FNshczJBF5y1TMo4YIPh7%2BaMuMfcUqmMC%2BWrr1Xm%2FUAjtyHnttlwQlkGDRPsSS4DMlM0OdWYLD9vL0ekEm7iz566ESLHP2aykbJ%2F3id3DwjcdgDENA6%2F8oojlvm6WP0JBDUviVTeDPK9V5RFekM3drtuDFit2UwRc%2B09xUvKcueMc%2FPrKKRhC%2FuRLXdx0WzgP4%2F2RJJeZhuKEQhYDTsFiDZnArDQMQyiMN0hRuwdfalhZFe27jXUG4Y%2BwPnHvpj1OXxEJ1VOgEtBzOO1AgwUr5SYa6UKhrbynm2X1J1HRyEn%2FVUqkvgc9Rx8ZYG2GqRr4L7eQ1N4sa7S6oqKEND6fX3eQhxFaqnimVCIg%2B6TwTp9Ant4P15WlGdVueq6HWATk8zB1CglVmsVH08lUwArNKjBpArD7v%2BIxx5VP1hJLChZOgfHqa6MVh7fP0lg6HXLeyMLSOXCz3oAK7iSOFkfu6RAx%2BGrBAj50ha%22%2C%22e%22%3A%22HELtCcggjijySBif5QK5Flm60fyrLzjVSvY2GZ7kF9k2ufvery5t6e1OxIGoUHpc7a0IbkE_0FA-F5WgiEpV7aeWlyQyxr1LL83v6PCoc3YbWdFNpRGiSow97HJFmhSolqL2iP8Yg3b6GvpNCl1IVN3_kiy7mdt7qA7PsE2Fu9J1ZID-lo1BWsvQpV6riLNbYizM9JlKkpiqJYbEB2zQGA%22%7D"},"insightType":0,"interaction":\'false\',"rateParam":{},"appId":"208"}}}
# message = {"method":"/iSheetCrowdService/report","headers":{"rid":"158270351707803","type":"PULL"},"body":{"args":{"id":"286","condition":"{\"compute\":\"INTERSECT\",\"ruleList\":[{\"filterList\":[{\"key\":\"brand\",\"type\":\"SINGLE_VALUE\",\"value\":\"372718624\"},{\"key\":\"ds\",\"type\":\"SINGLE_VALUE\",\"value\":\"20200225\"},{\"key\":\"stage\",\"type\":\"MULTI_VALUE\",\"value\":[\"1010\",\"1020\",\"1030\",\"1040\"]}],\"name\":\"stage\"},{\"type\":\"crowd\",\"value\":[66021683]}]}","tags":["mobile_brand_name_prefer"],"bizParam":{"databankCrowdId":"50083012","bizType":"CUSTOM_ANALYSIS","tag_identifier":"all","captcha":"%7B%22a%22%3A%22TSF2%22%2C%22c%22%3A%221582703516277%3A0.4058205419923615%22%2C%22d%22%3A%22nvc_register%22%2C%22h%22%3A%7B%22key1%22%3A%22code0%22%2C%22nvcCode%22%3A400%2C%22umidToken%22%3A%22T64FCFB4BB4291AEADBCE045345EFA40062471EC081DBF0B70E8D984C29%22%7D%2C%22j%22%3A%7B%22test%22%3A1%7D%2C%22b%22%3A%22122%23zKE7CE5OEEx2EDpZy4pjEJponDJE7SNEEP7ZpJRBuDPpJFQLpCGwoHZDpJEL7SwBEyGZpJLlu4Ep%2BFQLpoGUEELWn4yE7SNEEP7ZpERBuDPE%2BBQPpC76EJponDJLKMQEspPA04nTtBOmKBvALOESIAOsJhoR8HJNZIbVrA4tlm9BE5R8XAJh3Ue7sqj9qbj48oL6JlcpyBfDq9XpD5VanSL1uO5EELXZ8opwJ4EEyFvTkzlvDDpanAG4ul5EEtpr8CpUJ4bEyF3mqW32E5VanSL1uOIEELXZ8oL6JzEEyBfDqMfbDEb3ngL48liEmLXr8yt3%2ByYEmtWNsLigEzj4EOBJ1NftM0%2BL319%2FxuhJLSWywyyApnX897f6NIAyuyM%2BFgpQ9FU32VbYt2axX3Tlt%2BAQRv%2FkGLICcUjd0kuLF22mDbTj6q7rtA8xPM516jlZ9xnr%2FUhA%2Brn4Q7IxoSFpd3G7i03eGV6%2BEGYLr6Y43nfsZi8lWUZwISbYkgdNc%2F%2Bi5j6v4vfXndqyxsa3JOL7zraUIx7w3z%2BznKvXvHVsFFm56M6LrV8OzJQ8%2BkUw4ueUfYGEqGvNW8eTS%2B4SNpX73oQzDtsSgkAWxradYxWP%2F9OzqWvQp6rAkrdjYfnp%2BQQnf0eaGLCgHngMKG8xbPtABa0tUkkm41LFZlZB1olrI1LJYJojWRQXPkJ2qzIZmP4A%2FLeIH6nnGmqG5%2Fdk%2BR85BxFkzRfNvs3F4xKCJY7BLXJ%3D%22%2C%22e%22%3A%22HELtCcggjijySBif5QK5Flm60fyrLzjVSvY2GZ7kF9k2ufvery5t6e1OxIGoUHpc7a0IbkE_0FA-F5WgiEpV7aeWlyQyxr1LL83v6PCoc3YbWdFNpRGiSow97HJFmhSolqL2iP8Yg3b6GvpNCl1IVN3_kiy7mdt7qA7PsE2Fu9J1ZID-lo1BWsvQpV6riLNbYizM9JlKkpiqJYbEB2zQGA%22%7D"},"insightType":0,"interaction":\'false\',"rateParam":{},"appId":"208"}}}
# message = {"method":"/iSheetCrowdService/report","headers":{"rid":"158279331489213","type":"PULL"},"body":{"args":{"id":"286","condition":"{\"compute\":\"INTERSECT\",\"ruleList\":[{\"filterList\":[{\"key\":\"brand\",\"type\":\"SINGLE_VALUE\",\"value\":\"372718624\"},{\"key\":\"ds\",\"type\":\"SINGLE_VALUE\",\"value\":\"20200224\"},{\"key\":\"stage\",\"type\":\"MULTI_VALUE\",\"value\":[\"1010\",\"1020\",\"1030\",\"1040\"]}],\"name\":\"stage\"},{\"type\":\"crowd\",\"value\":[66477382]}]}","tags":["mobile_brand_name_prefer"],"bizParam":{"databankCrowdId":"50104297","bizType":"CUSTOM_ANALYSIS","tag_identifier":"all","captcha":"%7B%22a%22%3A%22TSF2%22%2C%22c%22%3A%221582793313952%3A0.5572064376494401%22%2C%22d%22%3A%22nvc_register%22%2C%22h%22%3A%7B%22key1%22%3A%22code0%22%2C%22nvcCode%22%3A400%2C%22umidToken%22%3A%22T4B68EC0873FE11C30B608CA1D8453CD51D467E11E58EAC62C1D92D68D3%22%7D%2C%22j%22%3A%7B%22test%22%3A1%7D%2C%22b%22%3A%22%22%2C%22e%22%3A%22HELtCcggjijySBif5QK5Flm60fyrLzjVSvY2GZ7kF9k2ufvery5t6e1OxIGoUHpc7a0IbkE_0FA-F5WgiEpV7aeWlyQyxr1LL83v6PCoc3YbWdFNpRGiSow97HJFmhSolqL2iP8Yg3b6GvpNCl1IVN3_kiy7mdt7qA7PsE2Fu9J1ZID-lo1BWsvQpV6riLNbYizM9JlKkpiqJYbEB2zQGA%22%7D"},"insightType":0,"interaction":\'false\',"rateParam":{},"appId":"208"}}}
self.ws.send(json.dumps(message))
self.count += 2
# run()
thread.start_new_thread(run, ())
def start(self):
randomness = os.urandom(16)
sec_websocket_key = base64.b64encode(randomness).decode(\'utf-8\').strip()
print(sec_websocket_key)
header = {\'Cookie\': self.cookie,
# \'x_csrf_token\': self.x_csrf_token,
\'Host\': \'ws-insight-engine.tmall.com\',
\'Origin\': \'https://insight-engine.tmall.com\',
\'Pragma\': \'no-cache\',
\'Sec-WebSocket-Extensions\': \'permessage-deflate; client_max_window_bits\',
# 这个参数要进行实时修改
\'Sec-WebSocket-Key\': sec_websocket_key, # \'IiVEH4VXg4doluxZ+jjhwA==\',
\'Sec-WebSocket-Version\': \'13\',
\'Upgrade\': \'websocket\',
\'User-Agent\': \'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36\'
}
url = \'wss://ws-insight-engine.tmall.com/\'
# ob = Test(cookie)
websocket.enableTrace(True)
self.ws = websocket.WebSocketApp(url=url,
on_message=self.on_message,
on_error=self.on_error,
on_close=self.on_close,
# on_open=self.on_open,
header=header
)
self.ws.on_open = self.on_open
self.ws.run_forever(ping_interval=5)
self.ws.close()
if __name__ == \'__main__\':
# cookie = \'cna=WVOlFr5u0GICAbSnr+SPipyd; lid=%E6%9B%B2%E7%BB%88%E4%BA%BA%E6%95%A3%E7%9A%84%E5%AF%82%E5%AF%9E%E6%B2%A1%E4%BA%BA%E6%87%82; enc=9cXAFThmyAgHiO%2FENYqm6TMx3M2iB6cB2%2BAszb%2F%2BiaM50PadsWGSN3OKooNrUXVyWs8ipZ6twUdCdaV%2BjkuBrA%3D%3D; t=7ed2d6ca2123fa1881e6b8fe97f185bd; _tb_token_=f36be58353654; cookie2=1643f0defa3225c1ed6be959bfc91256; unb=2206632888386; sn=anessa%E5%AE%89%E7%83%AD%E6%B2%99%E5%AE%98%E6%96%B9%E6%97%97%E8%88%B0%E5%BA%97%3Ait; __YSF_SESSION__={"baseId":"16a92e2747e29249","brandId":"bb52e1138cab1ddf","departmentId":"dc2f99d94018bd16","smartId":"1b66d71c287d3867","databankProjectId":"80457668a4affd3e"}; welcomeShownTime=1582606263036; sgcookie=DFzxOMaFc%2BovDXgNBTCL1; uc1=cookie14=UoTUOLUnHn2Ybg%3D%3D&lng=zh_CN; csg=76c331bb; _mw_us_time_=1582617537341; l=dBSesswPQExBY34QBOCNhOlrE8bOSIRAguzM48-6i_5a-OY6kYQOo8CFCHv6VjWfTzTB47_ypV99-etkV3MmndUU0ThjGxDc.; isg=BGVlRhs9VzAJErOY2VVv-JPpdCGfohk0W6VGnmdKIRyrfoXwL_IpBPMeDOII_jHs\'
# cookie = \'cna=WVOlFr5u0GICAbSnr+SPipyd; lid=%E6%9B%B2%E7%BB%88%E4%BA%BA%E6%95%A3%E7%9A%84%E5%AF%82%E5%AF%9E%E6%B2%A1%E4%BA%BA%E6%87%82; enc=9cXAFThmyAgHiO%2FENYqm6TMx3M2iB6cB2%2BAszb%2F%2BiaM50PadsWGSN3OKooNrUXVyWs8ipZ6twUdCdaV%2BjkuBrA%3D%3D; t=7ed2d6ca2123fa1881e6b8fe97f185bd; _tb_token_=f36be58353654; cookie2=1643f0defa3225c1ed6be959bfc91256; unb=2206632888386; sn=anessa%E5%AE%89%E7%83%AD%E6%B2%99%E5%AE%98%E6%96%B9%E6%97%97%E8%88%B0%E5%BA%97%3Ait; __YSF_SESSION__={"baseId":"16a92e2747e29249","brandId":"bb52e1138cab1ddf","departmentId":"dc2f99d94018bd16","smartId":"1b66d71c287d3867","databankProjectId":"80457668a4affd3e"}; welcomeShownTime=1582606263036; sgcookie=DFzxOMaFc%2BovDXgNBTCL1; uc1=cookie14=UoTUOLUnHn2Ybg%3D%3D&lng=zh_CN; csg=76c331bb; _mw_us_time_=1582617537341; isg=BF9fYqxYfUJhcHkq73MVis137rPpxLNm9esMTPGs_I5VgH8C-ZfStt1CQBD-A4ve; l=dBSesswPQExBYE42BOCwlOlrE8bOSIRYYuzM48-6i_5aJ6T18q_Oo8COPF96VjS1MoLB47_ypV99-etkqpxxF_kJyFrhit77nea_IFimexf..\'
cookie = \'cna=WVOlFr5u0GICAbSnr+SPipyd; lid=%E6%9B%B2%E7%BB%88%E4%BA%BA%E6%95%A3%E7%9A%84%E5%AF%82%E5%AF%9E%E6%B2%A1%E4%BA%BA%E6%87%82; enc=9cXAFThmyAgHiO%2FENYqm6TMx3M2iB6cB2%2BAszb%2F%2BiaM50PadsWGSN3OKooNrUXVyWs8ipZ6twUdCdaV%2BjkuBrA%3D%3D; t=d1c8dd737265e71d81c287ffa0e31436; _tb_token_=346ebfbaf3b65; cookie2=1d7315e9db402b38ebd67b74e172fdce; unb=2206632888386; sn=anessa%E5%AE%89%E7%83%AD%E6%B2%99%E5%AE%98%E6%96%B9%E6%97%97%E8%88%B0%E5%BA%97%3Ait; __YSF_SESSION__={"baseId":"16a92e2747e29249","brandId":"bb52e1138cab1ddf","departmentId":"dc2f99d94018bd16","smartId":"1b66d71c287d3867","databankProjectId":"80457668a4affd3e"}; welcomeShownTime=1582781993068; sgcookie=Dp%2FVOMDrzVopvKfT1OIMP; uc1=lng=zh_CN&cookie14=UoTUOLRxVjlLtw%3D%3D; csg=4e11fe74; _mw_us_time_=1582789699772; isg=BOjoR_A8Itylow4vXKYaZ44qudb6EUwbFoabiaIZNGNW_YhnSiEcq34_8ZUNVgTz; l=dBSesswPQExBY5b2BOCanurza77OSIRYYuPzaNbMi_5LR6T_3-bOo8mLsF96VjWfG1TB47_ypV99-etkq3DmndUU0ThjGxDc\'
Test(cookie).start()
需要注意的是构造好请求头和更新cookie,否则连接失败，websocket库新老版本架构不一致，如果版本过旧会导致代码报错可参考博客https://blog.csdn.net/tz_zs/article/details/95492963
参考博客：
https://segmentfault.com/a/1190000013149749
https://blog.csdn.net/weixin_41505223/article/details/84401044
https://blog.csdn.net/tz_zs/article/details/95492963
以上是 python爬虫----爬取阿里数据银行websocket接口 的全部内容， 来源链接： utcz.com/z/389228.html
