re-common 10.0.21__py3-none-any.whl → 10.0.22__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (199) hide show
  1. re_common/baselibrary/__init__.py +4 -4
  2. re_common/baselibrary/baseabs/__init__.py +6 -6
  3. re_common/baselibrary/baseabs/baseabs.py +26 -26
  4. re_common/baselibrary/database/mbuilder.py +132 -132
  5. re_common/baselibrary/database/moudle.py +93 -93
  6. re_common/baselibrary/database/msqlite3.py +194 -194
  7. re_common/baselibrary/database/mysql.py +169 -169
  8. re_common/baselibrary/database/sql_factory.py +26 -26
  9. re_common/baselibrary/mthread/MThreadingRun.py +486 -486
  10. re_common/baselibrary/mthread/MThreadingRunEvent.py +349 -349
  11. re_common/baselibrary/mthread/__init__.py +2 -2
  12. re_common/baselibrary/mthread/mythreading.py +695 -695
  13. re_common/baselibrary/pakge_other/socks.py +404 -404
  14. re_common/baselibrary/readconfig/config_factory.py +18 -18
  15. re_common/baselibrary/readconfig/ini_config.py +317 -317
  16. re_common/baselibrary/readconfig/toml_config.py +49 -49
  17. re_common/baselibrary/temporary/envdata.py +36 -36
  18. re_common/baselibrary/tools/all_requests/aiohttp_request.py +118 -118
  19. re_common/baselibrary/tools/all_requests/httpx_requet.py +102 -102
  20. re_common/baselibrary/tools/all_requests/mrequest.py +412 -412
  21. re_common/baselibrary/tools/all_requests/requests_request.py +81 -81
  22. re_common/baselibrary/tools/batch_compre/bijiao_batch.py +31 -31
  23. re_common/baselibrary/tools/contrast_db3.py +123 -123
  24. re_common/baselibrary/tools/copy_file.py +39 -39
  25. re_common/baselibrary/tools/db3_2_sizedb3.py +102 -102
  26. re_common/baselibrary/tools/foreachgz.py +39 -39
  27. re_common/baselibrary/tools/get_attr.py +10 -10
  28. re_common/baselibrary/tools/image_to_pdf.py +61 -61
  29. re_common/baselibrary/tools/java_code_deal.py +139 -139
  30. re_common/baselibrary/tools/javacode.py +79 -79
  31. re_common/baselibrary/tools/mdb_db3.py +48 -48
  32. re_common/baselibrary/tools/merge_file.py +171 -171
  33. re_common/baselibrary/tools/merge_gz_file.py +165 -165
  34. re_common/baselibrary/tools/mhdfstools/down_hdfs_files.py +42 -42
  35. re_common/baselibrary/tools/mhdfstools/hdfst.py +42 -42
  36. re_common/baselibrary/tools/mhdfstools/up_hdfs_files.py +38 -38
  37. re_common/baselibrary/tools/mongo_tools.py +50 -50
  38. re_common/baselibrary/tools/move_file.py +170 -170
  39. re_common/baselibrary/tools/move_mongo/mongo_table_to_file.py +63 -63
  40. re_common/baselibrary/tools/move_mongo/move_mongo_table.py +354 -354
  41. re_common/baselibrary/tools/move_mongo/use_mttf.py +18 -18
  42. re_common/baselibrary/tools/move_mongo/use_mv.py +93 -93
  43. re_common/baselibrary/tools/mpandas/mpandasreadexcel.py +125 -125
  44. re_common/baselibrary/tools/mpandas/pandas_visualization.py +7 -7
  45. re_common/baselibrary/tools/myparsel.py +104 -104
  46. re_common/baselibrary/tools/rename_dir_file.py +37 -37
  47. re_common/baselibrary/tools/sequoiadb_utils.py +398 -398
  48. re_common/baselibrary/tools/split_line_to_many.py +25 -25
  49. re_common/baselibrary/tools/stringtodicts.py +33 -33
  50. re_common/baselibrary/tools/workwechant_bot.py +84 -84
  51. re_common/baselibrary/utils/baseaiohttp.py +296 -296
  52. re_common/baselibrary/utils/baseaiomysql.py +87 -87
  53. re_common/baselibrary/utils/baseallstep.py +191 -191
  54. re_common/baselibrary/utils/baseavro.py +19 -19
  55. re_common/baselibrary/utils/baseboto3.py +291 -291
  56. re_common/baselibrary/utils/basecsv.py +32 -32
  57. re_common/baselibrary/utils/basedict.py +133 -133
  58. re_common/baselibrary/utils/basedir.py +241 -241
  59. re_common/baselibrary/utils/baseencode.py +351 -351
  60. re_common/baselibrary/utils/baseencoding.py +28 -28
  61. re_common/baselibrary/utils/baseesdsl.py +86 -86
  62. re_common/baselibrary/utils/baseexcel.py +264 -264
  63. re_common/baselibrary/utils/baseexcept.py +109 -109
  64. re_common/baselibrary/utils/basefile.py +654 -654
  65. re_common/baselibrary/utils/baseftp.py +214 -214
  66. re_common/baselibrary/utils/basegzip.py +60 -60
  67. re_common/baselibrary/utils/basehdfs.py +135 -135
  68. re_common/baselibrary/utils/basehttpx.py +268 -268
  69. re_common/baselibrary/utils/baseip.py +87 -87
  70. re_common/baselibrary/utils/basejson.py +2 -2
  71. re_common/baselibrary/utils/baselist.py +32 -32
  72. re_common/baselibrary/utils/basemotor.py +190 -190
  73. re_common/baselibrary/utils/basemssql.py +98 -98
  74. re_common/baselibrary/utils/baseodbc.py +113 -113
  75. re_common/baselibrary/utils/basepandas.py +302 -302
  76. re_common/baselibrary/utils/basepeewee.py +11 -11
  77. re_common/baselibrary/utils/basepika.py +180 -180
  78. re_common/baselibrary/utils/basepydash.py +143 -143
  79. re_common/baselibrary/utils/basepymongo.py +230 -230
  80. re_common/baselibrary/utils/basequeue.py +22 -22
  81. re_common/baselibrary/utils/baserar.py +57 -57
  82. re_common/baselibrary/utils/baserequest.py +279 -279
  83. re_common/baselibrary/utils/baseset.py +8 -8
  84. re_common/baselibrary/utils/basesmb.py +403 -403
  85. re_common/baselibrary/utils/basestring.py +382 -382
  86. re_common/baselibrary/utils/basetime.py +320 -320
  87. re_common/baselibrary/utils/baseurl.py +121 -121
  88. re_common/baselibrary/utils/basezip.py +57 -57
  89. re_common/baselibrary/utils/core/__init__.py +7 -7
  90. re_common/baselibrary/utils/core/bottomutils.py +18 -18
  91. re_common/baselibrary/utils/core/mdeprecated.py +327 -327
  92. re_common/baselibrary/utils/core/mlamada.py +16 -16
  93. re_common/baselibrary/utils/core/msginfo.py +25 -25
  94. re_common/baselibrary/utils/core/requests_core.py +103 -103
  95. re_common/baselibrary/utils/fateadm.py +429 -429
  96. re_common/baselibrary/utils/importfun.py +123 -123
  97. re_common/baselibrary/utils/mfaker.py +57 -57
  98. re_common/baselibrary/utils/my_abc/__init__.py +3 -3
  99. re_common/baselibrary/utils/my_abc/better_abc.py +32 -32
  100. re_common/baselibrary/utils/mylogger.py +414 -414
  101. re_common/baselibrary/utils/myredisclient.py +861 -861
  102. re_common/baselibrary/utils/pipupgrade.py +21 -21
  103. re_common/baselibrary/utils/ringlist.py +85 -85
  104. re_common/baselibrary/utils/version_compare.py +36 -36
  105. re_common/baselibrary/utils/ydmhttp.py +126 -126
  106. re_common/facade/lazy_import.py +11 -11
  107. re_common/facade/loggerfacade.py +25 -25
  108. re_common/facade/mysqlfacade.py +467 -467
  109. re_common/facade/now.py +31 -31
  110. re_common/facade/sqlite3facade.py +257 -257
  111. re_common/facade/use/mq_use_facade.py +83 -83
  112. re_common/facade/use/proxy_use_facade.py +19 -19
  113. re_common/libtest/base_dict_test.py +19 -19
  114. re_common/libtest/baseavro_test.py +13 -13
  115. re_common/libtest/basefile_test.py +14 -14
  116. re_common/libtest/basemssql_test.py +77 -77
  117. re_common/libtest/baseodbc_test.py +7 -7
  118. re_common/libtest/basepandas_test.py +38 -38
  119. re_common/libtest/get_attr_test/get_attr_test_settings.py +14 -14
  120. re_common/libtest/get_attr_test/settings.py +54 -54
  121. re_common/libtest/idencode_test.py +53 -53
  122. re_common/libtest/iniconfig_test.py +35 -35
  123. re_common/libtest/ip_test.py +34 -34
  124. re_common/libtest/merge_file_test.py +20 -20
  125. re_common/libtest/mfaker_test.py +8 -8
  126. re_common/libtest/mm3_test.py +31 -31
  127. re_common/libtest/mylogger_test.py +88 -88
  128. re_common/libtest/myparsel_test.py +27 -27
  129. re_common/libtest/mysql_test.py +151 -151
  130. re_common/libtest/pymongo_test.py +21 -21
  131. re_common/libtest/split_test.py +11 -11
  132. re_common/libtest/sqlite3_merge_test.py +5 -5
  133. re_common/libtest/sqlite3_test.py +34 -34
  134. re_common/libtest/tomlconfig_test.py +30 -30
  135. re_common/libtest/use_tools_test/__init__.py +2 -2
  136. re_common/libtest/user/__init__.py +4 -4
  137. re_common/studio/__init__.py +4 -4
  138. re_common/studio/assignment_expressions.py +36 -36
  139. re_common/studio/mydash/test1.py +18 -18
  140. re_common/studio/pydashstudio/first.py +9 -9
  141. re_common/studio/streamlitstudio/first_app.py +65 -65
  142. re_common/studio/streamlitstudio/uber_pickups.py +23 -23
  143. re_common/studio/test.py +18 -18
  144. re_common/v2/baselibrary/decorators/utils.py +59 -59
  145. re_common/v2/baselibrary/s3object/baseboto3.py +230 -230
  146. re_common/v2/baselibrary/tools/WeChatRobot.py +79 -79
  147. re_common/v2/baselibrary/tools/ac_ahocorasick.py +75 -75
  148. re_common/v2/baselibrary/tools/dict_tools.py +37 -37
  149. re_common/v2/baselibrary/tools/dolphinscheduler.py +187 -187
  150. re_common/v2/baselibrary/tools/hdfs_data_processer.py +338 -338
  151. re_common/v2/baselibrary/tools/list_tools.py +65 -65
  152. re_common/v2/baselibrary/tools/search_hash_tools.py +54 -54
  153. re_common/v2/baselibrary/tools/text_matcher.py +326 -326
  154. re_common/v2/baselibrary/tools/unionfind_tools.py +60 -60
  155. re_common/v2/baselibrary/utils/BusinessStringUtil.py +196 -196
  156. re_common/v2/baselibrary/utils/author_smi.py +360 -360
  157. re_common/v2/baselibrary/utils/base_string_similarity.py +158 -158
  158. re_common/v2/baselibrary/utils/basedict.py +37 -37
  159. re_common/v2/baselibrary/utils/basehdfs.py +161 -161
  160. re_common/v2/baselibrary/utils/basepika.py +180 -180
  161. re_common/v2/baselibrary/utils/basetime.py +77 -77
  162. re_common/v2/baselibrary/utils/db.py +38 -38
  163. re_common/v2/baselibrary/utils/json_cls.py +16 -16
  164. re_common/v2/baselibrary/utils/mq.py +83 -83
  165. re_common/v2/baselibrary/utils/n_ary_expression_tree.py +243 -243
  166. re_common/v2/baselibrary/utils/string_bool.py +149 -149
  167. re_common/v2/baselibrary/utils/string_clear.py +204 -202
  168. re_common/v2/baselibrary/utils/string_smi.py +18 -18
  169. re_common/v2/baselibrary/utils/stringutils.py +213 -213
  170. re_common/vip/base_step_process.py +11 -11
  171. re_common/vip/baseencodeid.py +90 -90
  172. re_common/vip/changetaskname.py +28 -28
  173. re_common/vip/core_var.py +24 -24
  174. re_common/vip/mmh3Hash.py +89 -89
  175. re_common/vip/proxy/allproxys.py +127 -127
  176. re_common/vip/proxy/allproxys_thread.py +159 -159
  177. re_common/vip/proxy/cnki_proxy.py +153 -153
  178. re_common/vip/proxy/kuaidaili.py +87 -87
  179. re_common/vip/proxy/proxy_all.py +113 -113
  180. re_common/vip/proxy/update_kuaidaili_0.py +42 -42
  181. re_common/vip/proxy/wanfang_proxy.py +152 -152
  182. re_common/vip/proxy/wp_proxy_all.py +181 -181
  183. re_common/vip/read_rawid_to_txt.py +91 -91
  184. re_common/vip/title/__init__.py +5 -5
  185. re_common/vip/title/transform/TransformBookTitleToZt.py +125 -125
  186. re_common/vip/title/transform/TransformConferenceTitleToZt.py +139 -139
  187. re_common/vip/title/transform/TransformCstadTitleToZt.py +195 -195
  188. re_common/vip/title/transform/TransformJournalTitleToZt.py +203 -203
  189. re_common/vip/title/transform/TransformPatentTitleToZt.py +132 -132
  190. re_common/vip/title/transform/TransformRegulationTitleToZt.py +114 -114
  191. re_common/vip/title/transform/TransformStandardTitleToZt.py +135 -135
  192. re_common/vip/title/transform/TransformThesisTitleToZt.py +135 -135
  193. re_common/vip/title/transform/__init__.py +10 -10
  194. {re_common-10.0.21.dist-info → re_common-10.0.22.dist-info}/LICENSE +201 -201
  195. {re_common-10.0.21.dist-info → re_common-10.0.22.dist-info}/METADATA +16 -16
  196. re_common-10.0.22.dist-info/RECORD +227 -0
  197. {re_common-10.0.21.dist-info → re_common-10.0.22.dist-info}/WHEEL +1 -1
  198. re_common-10.0.21.dist-info/RECORD +0 -227
  199. {re_common-10.0.21.dist-info → re_common-10.0.22.dist-info}/top_level.txt +0 -0
@@ -1,159 +1,159 @@
1
- import json
2
- ###########################################
3
- # 同项目调用基础包
4
- import os
5
- import sys
6
- import time
7
-
8
- import requests
9
-
10
- from re_common.baselibrary.mthread.MThreadingRun import MThreadingRun
11
- from re_common.baselibrary.mthread.mythreading import ThreadInfo, ThreadVal, ThreadPoolManger
12
-
13
- filepath = os.path.abspath(__file__)
14
- pathlist = filepath.split(os.sep)
15
- pathlist = pathlist[:-4]
16
- TopPath = os.sep.join(pathlist)
17
- sys.path.insert(0, TopPath)
18
- print(TopPath)
19
- ############################################
20
-
21
- from re_common.baselibrary.utils.basedir import BaseDir
22
- from re_common.baselibrary.utils.basefile import BaseFile
23
- from re_common.baselibrary.utils.baserequest import BaseRequest
24
- from re_common.facade.lazy_import import get_streamlogger
25
- from re_common.facade.mysqlfacade import MysqlUtiles
26
-
27
-
28
- class Kproxy(object):
29
- def __init__(self):
30
- self.cur_path = BaseDir.get_file_dir_absolute(__file__)
31
- self.configfile = BaseFile.get_new_path(self.cur_path, "db.ini")
32
- self.logger = get_streamlogger()
33
- self.mysqlutils = MysqlUtiles(self.configfile, "allproxy", self.logger)
34
- self.bsrequest = BaseRequest()
35
- self.starttime = time.time()
36
- self.starttime_val = time.time()
37
-
38
- def get_taiyang_proxy(self, num=6):
39
- """
40
- 获取太阳代理 每分钟3个
41
- :param num:
42
- :return:
43
- """
44
- self.starttime = time.time()
45
- url = "http://http.tiqu.qingjuhe.cn/getip?num={}&type=2&pack=56912&port=1&ts=1&lb=1&pb=45&regions=".format(num)
46
- BoolResult, errString, r = self.bsrequest.base_request(url,
47
- timeout=30
48
- )
49
- if BoolResult:
50
- dicts = json.loads(r.text)
51
- for item in dicts["data"]:
52
- proxy = item["ip"] + ":" + item["port"]
53
- sources = "taiyang"
54
- expire_time = item["expire_time"]
55
- sql = "insert into proxyall_v1 (proxy,sources,expire_time) values ('%s','%s','%s') on DUPLICATE key update stat=1,expire_time='%s'" % (
56
- proxy, sources, expire_time, expire_time)
57
- self.mysqlutils.ExeSqlToDB(sql)
58
- else:
59
- self.logger.error("获取失败")
60
-
61
- def val(self, proxy, sources,threadval):
62
- # 请求地址
63
- targetUrl = "https://www.baidu.com"
64
- proxies = {
65
- "http": "http://%s" % proxy,
66
- "https": "http://%s" % proxy
67
- }
68
- resp = requests.get(targetUrl, proxies=proxies, timeout=5)
69
- if resp.status_code == 200:
70
- print(resp.status_code)
71
- sql = "update proxyall_v1 set stat=1 where proxy='%s' and sources='%s';" % (proxy, sources)
72
- threadval.get_result_queue().put(sql)
73
- return True
74
- else:
75
- sql = "update proxyall_v1 set stat=0 where proxy='%s' and sources='%s';" % (proxy, sources)
76
- # self.mysqlutils.ExeSqlToDB(sql)
77
- threadval.get_result_queue().put(sql)
78
- return False
79
-
80
- def val_all(self):
81
- self.starttime_val = time.time()
82
- sql = "select proxy,sources from proxyall_v1 where stat=1 ORDER BY `update_time`"
83
- bools, rows = self.mysqlutils.SelectFromDB(sql)
84
- for row in rows:
85
- try:
86
- self.val(row[0], row[1])
87
- except:
88
- sql = "update proxyall_v1 set stat=0 where proxy='%s' and sources='%s';" % (row[0], row[1])
89
- self.mysqlutils.ExeSqlToDB(sql)
90
-
91
- def run(self):
92
- while True:
93
- start_time = time.time()
94
- self.get_taiyang_proxy()
95
- self.val_all()
96
- use_time = int(time.time() - start_time)
97
- sleep_time = 100 - use_time
98
- print("time sleep {}".format(str(sleep_time)))
99
- if sleep_time >= 3:
100
- time.sleep(sleep_time)
101
-
102
-
103
- class DetailThreadRun(MThreadingRun):
104
- def __init__(self, num):
105
- self.down = Kproxy()
106
- super(DetailThreadRun, self).__init__(num)
107
-
108
- @ThreadPoolManger.thread_lock
109
- def getTask(self, *args, **kwargs):
110
- sql = "select proxy,sources from proxyall_v1 where stat=0 ORDER BY `expire_time` DESC limit 1000"
111
- bools, rows = self.down.mysqlutils.SelectFromDB(sql)
112
- return rows
113
-
114
- @ThreadPoolManger.thread_lock
115
- def getTask2(self, *args, **kwargs):
116
- sql = "select proxy,sources from proxyall_v1 where stat=1 ORDER BY `expire_time` DESC limit 1000"
117
- bools, rows = self.down.mysqlutils.SelectFromDB(sql)
118
- return rows
119
-
120
- def setTask(self, results=None, *args, **kwargs):
121
- if not results:
122
- return self.BREAK
123
- for row in results:
124
- self.add_job(self.func, row[0], row[1])
125
- rows = self.getTask2()
126
- for row in rows:
127
- self.add_job(self.func, row[0], row[1])
128
- time.sleep(60*2)
129
- return self.BREAK
130
-
131
- @ThreadPoolManger.thread_lock
132
- def dealresult(self, *args, **kwargs):
133
- # for sql in self.results:
134
- # self.down.mysqlutils.ExeSqlToDB(sql)
135
- self.down.mysqlutils.ExeSqlListToDB(self.results)
136
-
137
- def setProxy(self, proxysList=None):
138
- time.sleep(300)
139
-
140
- def is_break(self):
141
- return False
142
-
143
- def thread_pool_hook(self, threadinfo: ThreadInfo):
144
- # 设置代理线程不重启,默认会重启
145
- return {}
146
-
147
- def fun(self, threadval: ThreadVal, *args, **kwargs):
148
- proxy,sources = args[0],args[1]
149
- try:
150
- self.down.val(proxy, sources, threadval)
151
- except:
152
- sql = "update proxyall_v1 set stat=0 where proxy='%s' and sources='%s';" % (proxy, sources)
153
- # self.mysqlutils.ExeSqlToDB(sql)
154
- threadval.get_result_queue().put(sql)
155
-
156
-
157
- if __name__ == '__main__':
158
- down = DetailThreadRun(30)
159
- down.run()
1
+ import json
2
+ ###########################################
3
+ # 同项目调用基础包
4
+ import os
5
+ import sys
6
+ import time
7
+
8
+ import requests
9
+
10
+ from re_common.baselibrary.mthread.MThreadingRun import MThreadingRun
11
+ from re_common.baselibrary.mthread.mythreading import ThreadInfo, ThreadVal, ThreadPoolManger
12
+
13
+ filepath = os.path.abspath(__file__)
14
+ pathlist = filepath.split(os.sep)
15
+ pathlist = pathlist[:-4]
16
+ TopPath = os.sep.join(pathlist)
17
+ sys.path.insert(0, TopPath)
18
+ print(TopPath)
19
+ ############################################
20
+
21
+ from re_common.baselibrary.utils.basedir import BaseDir
22
+ from re_common.baselibrary.utils.basefile import BaseFile
23
+ from re_common.baselibrary.utils.baserequest import BaseRequest
24
+ from re_common.facade.lazy_import import get_streamlogger
25
+ from re_common.facade.mysqlfacade import MysqlUtiles
26
+
27
+
28
+ class Kproxy(object):
29
+ def __init__(self):
30
+ self.cur_path = BaseDir.get_file_dir_absolute(__file__)
31
+ self.configfile = BaseFile.get_new_path(self.cur_path, "db.ini")
32
+ self.logger = get_streamlogger()
33
+ self.mysqlutils = MysqlUtiles(self.configfile, "allproxy", self.logger)
34
+ self.bsrequest = BaseRequest()
35
+ self.starttime = time.time()
36
+ self.starttime_val = time.time()
37
+
38
+ def get_taiyang_proxy(self, num=6):
39
+ """
40
+ 获取太阳代理 每分钟3个
41
+ :param num:
42
+ :return:
43
+ """
44
+ self.starttime = time.time()
45
+ url = "http://http.tiqu.qingjuhe.cn/getip?num={}&type=2&pack=56912&port=1&ts=1&lb=1&pb=45&regions=".format(num)
46
+ BoolResult, errString, r = self.bsrequest.base_request(url,
47
+ timeout=30
48
+ )
49
+ if BoolResult:
50
+ dicts = json.loads(r.text)
51
+ for item in dicts["data"]:
52
+ proxy = item["ip"] + ":" + item["port"]
53
+ sources = "taiyang"
54
+ expire_time = item["expire_time"]
55
+ sql = "insert into proxyall_v1 (proxy,sources,expire_time) values ('%s','%s','%s') on DUPLICATE key update stat=1,expire_time='%s'" % (
56
+ proxy, sources, expire_time, expire_time)
57
+ self.mysqlutils.ExeSqlToDB(sql)
58
+ else:
59
+ self.logger.error("获取失败")
60
+
61
+ def val(self, proxy, sources,threadval):
62
+ # 请求地址
63
+ targetUrl = "https://www.baidu.com"
64
+ proxies = {
65
+ "http": "http://%s" % proxy,
66
+ "https": "http://%s" % proxy
67
+ }
68
+ resp = requests.get(targetUrl, proxies=proxies, timeout=5)
69
+ if resp.status_code == 200:
70
+ print(resp.status_code)
71
+ sql = "update proxyall_v1 set stat=1 where proxy='%s' and sources='%s';" % (proxy, sources)
72
+ threadval.get_result_queue().put(sql)
73
+ return True
74
+ else:
75
+ sql = "update proxyall_v1 set stat=0 where proxy='%s' and sources='%s';" % (proxy, sources)
76
+ # self.mysqlutils.ExeSqlToDB(sql)
77
+ threadval.get_result_queue().put(sql)
78
+ return False
79
+
80
+ def val_all(self):
81
+ self.starttime_val = time.time()
82
+ sql = "select proxy,sources from proxyall_v1 where stat=1 ORDER BY `update_time`"
83
+ bools, rows = self.mysqlutils.SelectFromDB(sql)
84
+ for row in rows:
85
+ try:
86
+ self.val(row[0], row[1])
87
+ except:
88
+ sql = "update proxyall_v1 set stat=0 where proxy='%s' and sources='%s';" % (row[0], row[1])
89
+ self.mysqlutils.ExeSqlToDB(sql)
90
+
91
+ def run(self):
92
+ while True:
93
+ start_time = time.time()
94
+ self.get_taiyang_proxy()
95
+ self.val_all()
96
+ use_time = int(time.time() - start_time)
97
+ sleep_time = 100 - use_time
98
+ print("time sleep {}".format(str(sleep_time)))
99
+ if sleep_time >= 3:
100
+ time.sleep(sleep_time)
101
+
102
+
103
+ class DetailThreadRun(MThreadingRun):
104
+ def __init__(self, num):
105
+ self.down = Kproxy()
106
+ super(DetailThreadRun, self).__init__(num)
107
+
108
+ @ThreadPoolManger.thread_lock
109
+ def getTask(self, *args, **kwargs):
110
+ sql = "select proxy,sources from proxyall_v1 where stat=0 ORDER BY `expire_time` DESC limit 1000"
111
+ bools, rows = self.down.mysqlutils.SelectFromDB(sql)
112
+ return rows
113
+
114
+ @ThreadPoolManger.thread_lock
115
+ def getTask2(self, *args, **kwargs):
116
+ sql = "select proxy,sources from proxyall_v1 where stat=1 ORDER BY `expire_time` DESC limit 1000"
117
+ bools, rows = self.down.mysqlutils.SelectFromDB(sql)
118
+ return rows
119
+
120
+ def setTask(self, results=None, *args, **kwargs):
121
+ if not results:
122
+ return self.BREAK
123
+ for row in results:
124
+ self.add_job(self.func, row[0], row[1])
125
+ rows = self.getTask2()
126
+ for row in rows:
127
+ self.add_job(self.func, row[0], row[1])
128
+ time.sleep(60*2)
129
+ return self.BREAK
130
+
131
+ @ThreadPoolManger.thread_lock
132
+ def dealresult(self, *args, **kwargs):
133
+ # for sql in self.results:
134
+ # self.down.mysqlutils.ExeSqlToDB(sql)
135
+ self.down.mysqlutils.ExeSqlListToDB(self.results)
136
+
137
+ def setProxy(self, proxysList=None):
138
+ time.sleep(300)
139
+
140
+ def is_break(self):
141
+ return False
142
+
143
+ def thread_pool_hook(self, threadinfo: ThreadInfo):
144
+ # 设置代理线程不重启,默认会重启
145
+ return {}
146
+
147
+ def fun(self, threadval: ThreadVal, *args, **kwargs):
148
+ proxy,sources = args[0],args[1]
149
+ try:
150
+ self.down.val(proxy, sources, threadval)
151
+ except:
152
+ sql = "update proxyall_v1 set stat=0 where proxy='%s' and sources='%s';" % (proxy, sources)
153
+ # self.mysqlutils.ExeSqlToDB(sql)
154
+ threadval.get_result_queue().put(sql)
155
+
156
+
157
+ if __name__ == '__main__':
158
+ down = DetailThreadRun(30)
159
+ down.run()
@@ -1,153 +1,153 @@
1
- import time
2
-
3
- ###########################################
4
- # 同项目调用基础包
5
- import os
6
- import sys
7
-
8
- pathlist = os.path.abspath(__file__).split(os.sep)
9
- root_path = os.sep.join(pathlist[:pathlist.index("re-common") + 1])
10
- sys.path.insert(0, root_path)
11
- print(root_path)
12
- ############################################
13
- from re_common.baselibrary.utils.myredisclient import MyRedis
14
-
15
- from re_common.baselibrary.mthread.MThreadingRun import MThreadingRun
16
- from re_common.baselibrary.mthread.mythreading import ThreadInfo, ThreadPoolManger
17
- from re_common.baselibrary.utils.baserequest import BaseRequest
18
-
19
- from re_common.baselibrary.utils.core.requests_core import set_proxy
20
-
21
- from re_common.facade.loggerfacade import get_streamlogger
22
-
23
- from re_common.facade.mysqlfacade import MysqlUtiles
24
- from proxy_all import ProxyAll
25
-
26
-
27
- class CnkiProxy(object):
28
-
29
- def __init__(self, config="./db.ini"):
30
- self.config = config
31
- self.logger = get_streamlogger()
32
- self.mysqlutils = MysqlUtiles(self.config, "dbcnki", self.logger)
33
- self.Headers = {
34
- 'Accept': '*/*',
35
- 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko',
36
- }
37
- self.UserAgent = 'Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko'
38
- self.baserequest = BaseRequest()
39
-
40
- def checking_proxy(self, proxy):
41
- url = "https://www.cnki.net/"
42
- proxies = set_proxy(proxy)
43
- BoolResult, errString, r = self.baserequest.base_request(url,
44
- headers=self.Headers,
45
- proxies=proxies,
46
- marks=["product-content"],
47
- timeout=5)
48
- if BoolResult:
49
- return proxy
50
- return ""
51
-
52
- def get_mysql_proxy(self):
53
- sql = "SELECT proxy FROM `proxy_pool`"
54
- bools, rows = self.mysqlutils.SelectFromDB(sql)
55
- if not bools:
56
- return set()
57
- results = set()
58
- for row in rows:
59
- results.add(row[0])
60
- sql = "delete from proxy_pool"
61
- self.mysqlutils.ExeSqlToDB(sql)
62
- return results
63
-
64
- def get_all_proxy(self):
65
- proxy_set = set()
66
- proxyall = ProxyAll()
67
- redisproxy = proxyall.get_redis_all()
68
- mimvpproxy = proxyall.getProxyFromMimvp(1000)
69
- daxiangproxy = proxyall.getProxyFromDaxiang(1000)
70
- xiciproxy1 = proxyall.getProxyFromXICIOnePage(1)
71
- xiciproxy2 = proxyall.getProxyFromXICIOnePage(2)
72
- mysqlproxy = self.get_mysql_proxy()
73
- proxy_set = proxy_set.union(mysqlproxy, redisproxy, mimvpproxy, daxiangproxy, xiciproxy1, xiciproxy2)
74
- self.logger.info("all proxy size is:{}".format(len(proxy_set)))
75
- self.proxy_set = proxy_set
76
- return proxy_set
77
-
78
- def get_can_use_proxy(self):
79
- count = 0
80
- use_proxy = set()
81
- for proxy in self.proxy_set:
82
- proxy_ = self.checking_proxy(proxy)
83
- use_proxy.add(proxy_)
84
- if len(use_proxy) > 20:
85
- count = count + 1
86
- if count == 1:
87
- sql = "delete from proxy_pool"
88
- self.mysqlutils.ExeSqlToDB(sql)
89
- sql = "insert into proxy_pool(proxy) values ('%s')"
90
- self.mysqlutils.ExeSqlMany(sql, use_proxy)
91
- use_proxy.clear()
92
- if len(use_proxy) > 0:
93
- sql = "insert into proxy_pool(proxy) values ('%s')"
94
- self.mysqlutils.ExeSqlMany(sql, use_proxy)
95
- use_proxy.clear()
96
-
97
-
98
- class DetailThreadRun(MThreadingRun):
99
- def __init__(self, num):
100
- self.cnki = CnkiProxy()
101
- super(DetailThreadRun, self).__init__(num)
102
- self.config = "./db.ini"
103
- self.myredisset = MyRedis(self.config)
104
- self.myredisset.set_redis_from_config(sesc="proxysetcnkijournal")
105
- self.myredisset.conn_redis()
106
- self.myredisset.get_pipeline()
107
-
108
- @ThreadPoolManger.thread_lock
109
- def getTask(self, *args, **kwargs):
110
- self.myredisset.delete(self.myredisset.RedisKey)
111
- proxy_set = self.cnki.get_all_proxy()
112
- return proxy_set
113
-
114
- def setTask(self, results=None, *args, **kwargs):
115
- for url_tasks in results:
116
- # 将每一页加入任务队列
117
- self.add_job(self.func, url_tasks)
118
- time.sleep(10 * 60)
119
-
120
- @ThreadPoolManger.thread_lock
121
- def dealresult(self, *args, **kwargs):
122
- sql = "replace into proxy_pool(`proxy`) values (%s)"
123
- self.cnki.mysqlutils.ExeSqlMany(sql, self.results)
124
- self.myredisset.sadd(self.myredisset.RedisKey, set(self.results))
125
-
126
- def setProxy(self, proxysList=None):
127
- pass
128
-
129
- def is_break(self):
130
- return False
131
-
132
- def thread_pool_hook(self, threadinfo: ThreadInfo):
133
- # 设置代理线程不重启,默认会重启
134
- if threadinfo.get_thread_name() == self.etn.proxythreadname:
135
- threadinfo.set_is_restart(False)
136
- if threadinfo.get_thread_name() == self.etn.taskthreadname:
137
- threadinfo.set_is_restart(False)
138
- return {}
139
-
140
- def fun(self, threadval, *args, **kwargs):
141
- standardid = args[0]
142
- proxys = self.cnki.checking_proxy(standardid)
143
- if proxys != "":
144
- threadval.result_queue.put(proxys)
145
-
146
-
147
- def main():
148
- down = DetailThreadRun(40)
149
- down.run()
150
-
151
-
152
- if __name__ == "__main__":
153
- main()
1
+ import time
2
+
3
+ ###########################################
4
+ # 同项目调用基础包
5
+ import os
6
+ import sys
7
+
8
+ pathlist = os.path.abspath(__file__).split(os.sep)
9
+ root_path = os.sep.join(pathlist[:pathlist.index("re-common") + 1])
10
+ sys.path.insert(0, root_path)
11
+ print(root_path)
12
+ ############################################
13
+ from re_common.baselibrary.utils.myredisclient import MyRedis
14
+
15
+ from re_common.baselibrary.mthread.MThreadingRun import MThreadingRun
16
+ from re_common.baselibrary.mthread.mythreading import ThreadInfo, ThreadPoolManger
17
+ from re_common.baselibrary.utils.baserequest import BaseRequest
18
+
19
+ from re_common.baselibrary.utils.core.requests_core import set_proxy
20
+
21
+ from re_common.facade.loggerfacade import get_streamlogger
22
+
23
+ from re_common.facade.mysqlfacade import MysqlUtiles
24
+ from proxy_all import ProxyAll
25
+
26
+
27
+ class CnkiProxy(object):
28
+
29
+ def __init__(self, config="./db.ini"):
30
+ self.config = config
31
+ self.logger = get_streamlogger()
32
+ self.mysqlutils = MysqlUtiles(self.config, "dbcnki", self.logger)
33
+ self.Headers = {
34
+ 'Accept': '*/*',
35
+ 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko',
36
+ }
37
+ self.UserAgent = 'Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko'
38
+ self.baserequest = BaseRequest()
39
+
40
+ def checking_proxy(self, proxy):
41
+ url = "https://www.cnki.net/"
42
+ proxies = set_proxy(proxy)
43
+ BoolResult, errString, r = self.baserequest.base_request(url,
44
+ headers=self.Headers,
45
+ proxies=proxies,
46
+ marks=["product-content"],
47
+ timeout=5)
48
+ if BoolResult:
49
+ return proxy
50
+ return ""
51
+
52
+ def get_mysql_proxy(self):
53
+ sql = "SELECT proxy FROM `proxy_pool`"
54
+ bools, rows = self.mysqlutils.SelectFromDB(sql)
55
+ if not bools:
56
+ return set()
57
+ results = set()
58
+ for row in rows:
59
+ results.add(row[0])
60
+ sql = "delete from proxy_pool"
61
+ self.mysqlutils.ExeSqlToDB(sql)
62
+ return results
63
+
64
+ def get_all_proxy(self):
65
+ proxy_set = set()
66
+ proxyall = ProxyAll()
67
+ redisproxy = proxyall.get_redis_all()
68
+ mimvpproxy = proxyall.getProxyFromMimvp(1000)
69
+ daxiangproxy = proxyall.getProxyFromDaxiang(1000)
70
+ xiciproxy1 = proxyall.getProxyFromXICIOnePage(1)
71
+ xiciproxy2 = proxyall.getProxyFromXICIOnePage(2)
72
+ mysqlproxy = self.get_mysql_proxy()
73
+ proxy_set = proxy_set.union(mysqlproxy, redisproxy, mimvpproxy, daxiangproxy, xiciproxy1, xiciproxy2)
74
+ self.logger.info("all proxy size is:{}".format(len(proxy_set)))
75
+ self.proxy_set = proxy_set
76
+ return proxy_set
77
+
78
+ def get_can_use_proxy(self):
79
+ count = 0
80
+ use_proxy = set()
81
+ for proxy in self.proxy_set:
82
+ proxy_ = self.checking_proxy(proxy)
83
+ use_proxy.add(proxy_)
84
+ if len(use_proxy) > 20:
85
+ count = count + 1
86
+ if count == 1:
87
+ sql = "delete from proxy_pool"
88
+ self.mysqlutils.ExeSqlToDB(sql)
89
+ sql = "insert into proxy_pool(proxy) values ('%s')"
90
+ self.mysqlutils.ExeSqlMany(sql, use_proxy)
91
+ use_proxy.clear()
92
+ if len(use_proxy) > 0:
93
+ sql = "insert into proxy_pool(proxy) values ('%s')"
94
+ self.mysqlutils.ExeSqlMany(sql, use_proxy)
95
+ use_proxy.clear()
96
+
97
+
98
+ class DetailThreadRun(MThreadingRun):
99
+ def __init__(self, num):
100
+ self.cnki = CnkiProxy()
101
+ super(DetailThreadRun, self).__init__(num)
102
+ self.config = "./db.ini"
103
+ self.myredisset = MyRedis(self.config)
104
+ self.myredisset.set_redis_from_config(sesc="proxysetcnkijournal")
105
+ self.myredisset.conn_redis()
106
+ self.myredisset.get_pipeline()
107
+
108
+ @ThreadPoolManger.thread_lock
109
+ def getTask(self, *args, **kwargs):
110
+ self.myredisset.delete(self.myredisset.RedisKey)
111
+ proxy_set = self.cnki.get_all_proxy()
112
+ return proxy_set
113
+
114
+ def setTask(self, results=None, *args, **kwargs):
115
+ for url_tasks in results:
116
+ # 将每一页加入任务队列
117
+ self.add_job(self.func, url_tasks)
118
+ time.sleep(10 * 60)
119
+
120
+ @ThreadPoolManger.thread_lock
121
+ def dealresult(self, *args, **kwargs):
122
+ sql = "replace into proxy_pool(`proxy`) values (%s)"
123
+ self.cnki.mysqlutils.ExeSqlMany(sql, self.results)
124
+ self.myredisset.sadd(self.myredisset.RedisKey, set(self.results))
125
+
126
+ def setProxy(self, proxysList=None):
127
+ pass
128
+
129
+ def is_break(self):
130
+ return False
131
+
132
+ def thread_pool_hook(self, threadinfo: ThreadInfo):
133
+ # 设置代理线程不重启,默认会重启
134
+ if threadinfo.get_thread_name() == self.etn.proxythreadname:
135
+ threadinfo.set_is_restart(False)
136
+ if threadinfo.get_thread_name() == self.etn.taskthreadname:
137
+ threadinfo.set_is_restart(False)
138
+ return {}
139
+
140
+ def fun(self, threadval, *args, **kwargs):
141
+ standardid = args[0]
142
+ proxys = self.cnki.checking_proxy(standardid)
143
+ if proxys != "":
144
+ threadval.result_queue.put(proxys)
145
+
146
+
147
+ def main():
148
+ down = DetailThreadRun(40)
149
+ down.run()
150
+
151
+
152
+ if __name__ == "__main__":
153
+ main()