re-common 2.0.0__py3-none-any.whl → 2.0.1__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 (200) hide show
  1. re_common/v2/baselibrary/tools/search_hash_tools.py +33 -0
  2. re_common/v2/baselibrary/tools/text_matcher.py +223 -0
  3. re_common/v2/baselibrary/utils/BusinessStringUtil.py +2 -2
  4. re_common/v2/baselibrary/utils/author_smi.py +308 -0
  5. re_common/v2/baselibrary/utils/string_clear.py +15 -1
  6. re_common/v2/baselibrary/utils/stringutils.py +36 -1
  7. {re_common-2.0.0.dist-info → re_common-2.0.1.dist-info}/METADATA +1 -1
  8. re_common-2.0.1.dist-info/RECORD +25 -0
  9. re_common/baselibrary/__init__.py +0 -4
  10. re_common/baselibrary/baseabs/__init__.py +0 -7
  11. re_common/baselibrary/baseabs/baseabs.py +0 -26
  12. re_common/baselibrary/database/mbuilder.py +0 -132
  13. re_common/baselibrary/database/moudle.py +0 -93
  14. re_common/baselibrary/database/msqlite3.py +0 -194
  15. re_common/baselibrary/database/mysql.py +0 -169
  16. re_common/baselibrary/database/sql_factory.py +0 -26
  17. re_common/baselibrary/mthread/MThreadingRun.py +0 -486
  18. re_common/baselibrary/mthread/MThreadingRunEvent.py +0 -349
  19. re_common/baselibrary/mthread/__init__.py +0 -3
  20. re_common/baselibrary/mthread/mythreading.py +0 -695
  21. re_common/baselibrary/pakge_other/__init__.py +0 -0
  22. re_common/baselibrary/pakge_other/socks.py +0 -404
  23. re_common/baselibrary/readconfig/__init__.py +0 -0
  24. re_common/baselibrary/readconfig/config_factory.py +0 -18
  25. re_common/baselibrary/readconfig/ini_config.py +0 -317
  26. re_common/baselibrary/readconfig/toml_config.py +0 -49
  27. re_common/baselibrary/temporary/__init__.py +0 -0
  28. re_common/baselibrary/temporary/envdata.py +0 -36
  29. re_common/baselibrary/tools/__init__.py +0 -0
  30. re_common/baselibrary/tools/all_requests/__init__.py +0 -0
  31. re_common/baselibrary/tools/all_requests/aiohttp_request.py +0 -118
  32. re_common/baselibrary/tools/all_requests/httpx_requet.py +0 -102
  33. re_common/baselibrary/tools/all_requests/mrequest.py +0 -412
  34. re_common/baselibrary/tools/all_requests/requests_request.py +0 -81
  35. re_common/baselibrary/tools/batch_compre/__init__.py +0 -0
  36. re_common/baselibrary/tools/batch_compre/bijiao_batch.py +0 -31
  37. re_common/baselibrary/tools/contrast_db3.py +0 -123
  38. re_common/baselibrary/tools/copy_file.py +0 -39
  39. re_common/baselibrary/tools/db3_2_sizedb3.py +0 -102
  40. re_common/baselibrary/tools/foreachgz.py +0 -40
  41. re_common/baselibrary/tools/get_attr.py +0 -11
  42. re_common/baselibrary/tools/image_to_pdf.py +0 -62
  43. re_common/baselibrary/tools/java_code_deal.py +0 -139
  44. re_common/baselibrary/tools/javacode.py +0 -79
  45. re_common/baselibrary/tools/mdb_db3.py +0 -48
  46. re_common/baselibrary/tools/merge_file.py +0 -171
  47. re_common/baselibrary/tools/merge_gz_file.py +0 -165
  48. re_common/baselibrary/tools/mhdfstools/__init__.py +0 -0
  49. re_common/baselibrary/tools/mhdfstools/down_hdfs_files.py +0 -42
  50. re_common/baselibrary/tools/mhdfstools/hdfst.py +0 -42
  51. re_common/baselibrary/tools/mhdfstools/up_hdfs_files.py +0 -38
  52. re_common/baselibrary/tools/mongo_tools.py +0 -50
  53. re_common/baselibrary/tools/move_file.py +0 -170
  54. re_common/baselibrary/tools/move_mongo/__init__.py +0 -0
  55. re_common/baselibrary/tools/move_mongo/mongo_table_to_file.py +0 -63
  56. re_common/baselibrary/tools/move_mongo/move_mongo_table.py +0 -354
  57. re_common/baselibrary/tools/move_mongo/use_mttf.py +0 -18
  58. re_common/baselibrary/tools/move_mongo/use_mv.py +0 -93
  59. re_common/baselibrary/tools/mpandas/__init__.py +0 -0
  60. re_common/baselibrary/tools/mpandas/mpandasreadexcel.py +0 -125
  61. re_common/baselibrary/tools/mpandas/pandas_visualization.py +0 -8
  62. re_common/baselibrary/tools/myparsel.py +0 -104
  63. re_common/baselibrary/tools/rename_dir_file.py +0 -37
  64. re_common/baselibrary/tools/sequoiadb_utils.py +0 -398
  65. re_common/baselibrary/tools/split_line_to_many.py +0 -25
  66. re_common/baselibrary/tools/stringtodicts.py +0 -33
  67. re_common/baselibrary/tools/workwechant_bot.py +0 -84
  68. re_common/baselibrary/utils/__init__.py +0 -0
  69. re_common/baselibrary/utils/baseaiohttp.py +0 -296
  70. re_common/baselibrary/utils/baseaiomysql.py +0 -87
  71. re_common/baselibrary/utils/baseallstep.py +0 -191
  72. re_common/baselibrary/utils/baseavro.py +0 -19
  73. re_common/baselibrary/utils/baseboto3.py +0 -291
  74. re_common/baselibrary/utils/basecsv.py +0 -32
  75. re_common/baselibrary/utils/basedict.py +0 -133
  76. re_common/baselibrary/utils/basedir.py +0 -241
  77. re_common/baselibrary/utils/baseencode.py +0 -351
  78. re_common/baselibrary/utils/baseencoding.py +0 -29
  79. re_common/baselibrary/utils/baseesdsl.py +0 -86
  80. re_common/baselibrary/utils/baseexcel.py +0 -264
  81. re_common/baselibrary/utils/baseexcept.py +0 -109
  82. re_common/baselibrary/utils/basefile.py +0 -654
  83. re_common/baselibrary/utils/baseftp.py +0 -214
  84. re_common/baselibrary/utils/basegzip.py +0 -60
  85. re_common/baselibrary/utils/basehdfs.py +0 -135
  86. re_common/baselibrary/utils/basehttpx.py +0 -268
  87. re_common/baselibrary/utils/baseip.py +0 -87
  88. re_common/baselibrary/utils/basejson.py +0 -2
  89. re_common/baselibrary/utils/baselist.py +0 -32
  90. re_common/baselibrary/utils/basemotor.py +0 -190
  91. re_common/baselibrary/utils/basemssql.py +0 -98
  92. re_common/baselibrary/utils/baseodbc.py +0 -113
  93. re_common/baselibrary/utils/basepandas.py +0 -302
  94. re_common/baselibrary/utils/basepeewee.py +0 -11
  95. re_common/baselibrary/utils/basepika.py +0 -180
  96. re_common/baselibrary/utils/basepydash.py +0 -143
  97. re_common/baselibrary/utils/basepymongo.py +0 -230
  98. re_common/baselibrary/utils/basequeue.py +0 -22
  99. re_common/baselibrary/utils/baserar.py +0 -57
  100. re_common/baselibrary/utils/baserequest.py +0 -279
  101. re_common/baselibrary/utils/baseset.py +0 -8
  102. re_common/baselibrary/utils/basesmb.py +0 -403
  103. re_common/baselibrary/utils/basestring.py +0 -382
  104. re_common/baselibrary/utils/basetime.py +0 -320
  105. re_common/baselibrary/utils/basetuple.py +0 -0
  106. re_common/baselibrary/utils/baseurl.py +0 -121
  107. re_common/baselibrary/utils/basezip.py +0 -57
  108. re_common/baselibrary/utils/core/__init__.py +0 -8
  109. re_common/baselibrary/utils/core/bottomutils.py +0 -18
  110. re_common/baselibrary/utils/core/mdeprecated.py +0 -327
  111. re_common/baselibrary/utils/core/mlamada.py +0 -16
  112. re_common/baselibrary/utils/core/msginfo.py +0 -25
  113. re_common/baselibrary/utils/core/requests_core.py +0 -103
  114. re_common/baselibrary/utils/fateadm.py +0 -429
  115. re_common/baselibrary/utils/importfun.py +0 -123
  116. re_common/baselibrary/utils/mfaker.py +0 -57
  117. re_common/baselibrary/utils/my_abc/__init__.py +0 -3
  118. re_common/baselibrary/utils/my_abc/better_abc.py +0 -32
  119. re_common/baselibrary/utils/mylogger.py +0 -414
  120. re_common/baselibrary/utils/myredisclient.py +0 -861
  121. re_common/baselibrary/utils/pipupgrade.py +0 -21
  122. re_common/baselibrary/utils/ringlist.py +0 -85
  123. re_common/baselibrary/utils/version_compare.py +0 -36
  124. re_common/baselibrary/utils/ydmhttp.py +0 -126
  125. re_common/facade/__init__.py +0 -1
  126. re_common/facade/lazy_import.py +0 -11
  127. re_common/facade/loggerfacade.py +0 -25
  128. re_common/facade/mysqlfacade.py +0 -467
  129. re_common/facade/now.py +0 -31
  130. re_common/facade/sqlite3facade.py +0 -257
  131. re_common/facade/use/__init__.py +0 -0
  132. re_common/facade/use/mq_use_facade.py +0 -83
  133. re_common/facade/use/proxy_use_facade.py +0 -20
  134. re_common/libtest/__init__.py +0 -0
  135. re_common/libtest/base_dict_test.py +0 -19
  136. re_common/libtest/baseavro_test.py +0 -13
  137. re_common/libtest/basefile_test.py +0 -14
  138. re_common/libtest/basemssql_test.py +0 -77
  139. re_common/libtest/baseodbc_test.py +0 -8
  140. re_common/libtest/basepandas_test.py +0 -38
  141. re_common/libtest/get_attr_test/__init__.py +0 -0
  142. re_common/libtest/get_attr_test/get_attr_test_settings.py +0 -14
  143. re_common/libtest/get_attr_test/settings.py +0 -55
  144. re_common/libtest/idencode_test.py +0 -54
  145. re_common/libtest/iniconfig_test.py +0 -35
  146. re_common/libtest/ip_test.py +0 -35
  147. re_common/libtest/merge_file_test.py +0 -20
  148. re_common/libtest/mfaker_test.py +0 -9
  149. re_common/libtest/mm3_test.py +0 -32
  150. re_common/libtest/mylogger_test.py +0 -89
  151. re_common/libtest/myparsel_test.py +0 -28
  152. re_common/libtest/mysql_test.py +0 -151
  153. re_common/libtest/pymongo_test.py +0 -21
  154. re_common/libtest/split_test.py +0 -12
  155. re_common/libtest/sqlite3_merge_test.py +0 -6
  156. re_common/libtest/sqlite3_test.py +0 -34
  157. re_common/libtest/tomlconfig_test.py +0 -30
  158. re_common/libtest/use_tools_test/__init__.py +0 -3
  159. re_common/libtest/user/__init__.py +0 -5
  160. re_common/studio/__init__.py +0 -5
  161. re_common/studio/assignment_expressions.py +0 -37
  162. re_common/studio/mydash/__init__.py +0 -0
  163. re_common/studio/mydash/test1.py +0 -19
  164. re_common/studio/pydashstudio/__init__.py +0 -0
  165. re_common/studio/pydashstudio/first.py +0 -9
  166. re_common/studio/streamlitstudio/__init__.py +0 -0
  167. re_common/studio/streamlitstudio/first_app.py +0 -66
  168. re_common/studio/streamlitstudio/uber_pickups.py +0 -24
  169. re_common/studio/test.py +0 -19
  170. re_common/vip/__init__.py +0 -0
  171. re_common/vip/base_step_process.py +0 -11
  172. re_common/vip/baseencodeid.py +0 -91
  173. re_common/vip/changetaskname.py +0 -28
  174. re_common/vip/core_var.py +0 -24
  175. re_common/vip/mmh3Hash.py +0 -90
  176. re_common/vip/proxy/__init__.py +0 -0
  177. re_common/vip/proxy/allproxys.py +0 -127
  178. re_common/vip/proxy/allproxys_thread.py +0 -159
  179. re_common/vip/proxy/cnki_proxy.py +0 -153
  180. re_common/vip/proxy/kuaidaili.py +0 -87
  181. re_common/vip/proxy/proxy_all.py +0 -113
  182. re_common/vip/proxy/update_kuaidaili_0.py +0 -42
  183. re_common/vip/proxy/wanfang_proxy.py +0 -152
  184. re_common/vip/proxy/wp_proxy_all.py +0 -182
  185. re_common/vip/read_rawid_to_txt.py +0 -92
  186. re_common/vip/title/__init__.py +0 -5
  187. re_common/vip/title/transform/TransformBookTitleToZt.py +0 -125
  188. re_common/vip/title/transform/TransformConferenceTitleToZt.py +0 -139
  189. re_common/vip/title/transform/TransformCstadTitleToZt.py +0 -196
  190. re_common/vip/title/transform/TransformJournalTitleToZt.py +0 -203
  191. re_common/vip/title/transform/TransformPatentTitleToZt.py +0 -132
  192. re_common/vip/title/transform/TransformRegulationTitleToZt.py +0 -114
  193. re_common/vip/title/transform/TransformStandardTitleToZt.py +0 -135
  194. re_common/vip/title/transform/TransformThesisTitleToZt.py +0 -135
  195. re_common/vip/title/transform/__init__.py +0 -11
  196. re_common-2.0.0.dist-info/RECORD +0 -209
  197. /re_common/{baselibrary/database/__init__.py → v2/baselibrary/tools/list_tools.py} +0 -0
  198. {re_common-2.0.0.dist-info → re_common-2.0.1.dist-info}/LICENSE +0 -0
  199. {re_common-2.0.0.dist-info → re_common-2.0.1.dist-info}/WHEEL +0 -0
  200. {re_common-2.0.0.dist-info → re_common-2.0.1.dist-info}/top_level.txt +0 -0
@@ -1,153 +0,0 @@
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()
@@ -1,87 +0,0 @@
1
- import json
2
-
3
- ###########################################
4
- # 同项目调用基础包
5
- import os
6
- import sys
7
- import time
8
- import traceback
9
-
10
- filepath = os.path.abspath(__file__)
11
- pathlist = filepath.split(os.sep)
12
- pathlist = pathlist[:-4]
13
- TopPath = os.sep.join(pathlist)
14
- sys.path.insert(0, TopPath)
15
- print(TopPath)
16
- ############################################
17
-
18
- from re_common.baselibrary.utils.baserequest import BaseRequest
19
- from re_common.facade.mysqlfacade import MysqlUtiles
20
- from re_common.baselibrary.utils.basedir import BaseDir
21
- from re_common.baselibrary.utils.basefile import BaseFile
22
- from re_common.facade.lazy_import import get_streamlogger
23
-
24
-
25
- class Kproxy(object):
26
- def __init__(self):
27
- self.cur_path = BaseDir.get_file_dir_absolute(__file__)
28
- self.configfile = BaseFile.get_new_path(self.cur_path, "db.ini")
29
- self.logger = get_streamlogger()
30
- self.mysqlutils = MysqlUtiles(self.configfile, "dbkuaidaili", self.logger)
31
- self.url = "https://dps.kdlapi.com/api/getdps/?orderid=990171566857288&num=15&pt=1&format=json&sep=1"
32
- self.bsrequest = BaseRequest()
33
- self.starttime = time.time()
34
- self.starttime_val = time.time()
35
-
36
- def get_proxy(self):
37
- self.starttime = time.time()
38
- BoolResult, errString, r = self.bsrequest.base_request(self.url,
39
- timeout=30
40
- )
41
- if BoolResult:
42
- dicts = json.loads(r.text)
43
- for proxy in dicts["data"]["proxy_list"]:
44
- sql = "insert into kuaidailiproxy (proxy) values ('%s') on DUPLICATE key update stat=1" % proxy
45
- self.mysqlutils.ExeSqlToDB(sql)
46
- else:
47
- self.logger.error("获取失败")
48
-
49
- def val(self, proxy):
50
- self.starttime_val = time.time()
51
- url = f"https://dps.kdlapi.com/api/getdpsvalidtime?orderid=990171566857288&signature=wm4vq53pwrat1vye458elwyxyh9awzqj&proxy={proxy}"
52
- BoolResult, errString, r = self.bsrequest.base_request(url,
53
- timeout=30
54
- )
55
- if BoolResult:
56
- dicts = json.loads(r.text)
57
- if dicts["data"][proxy] > 0:
58
- sql = "update kuaidailiproxy set val_stat=0 where proxy='%s'" % proxy
59
- self.mysqlutils.ExeSqlToDB(sql)
60
- else:
61
- sql = "update kuaidailiproxy set val_stat=0,stat=0 where proxy='%s'" % proxy
62
- self.mysqlutils.ExeSqlToDB(sql)
63
- else:
64
- self.logger.error("获取失败")
65
-
66
- def val_all(self):
67
- self.starttime_val = time.time()
68
- sql = "select proxy from kuaidailiproxy where stat=1"
69
- bools, rows = self.mysqlutils.SelectFromDB(sql)
70
- for row in rows:
71
- try:
72
- self.val(row[0])
73
- except:
74
- traceback.print_exc()
75
-
76
- def run(self):
77
- self.get_proxy()
78
- while True:
79
- if int(time.time() - self.starttime) > 20:
80
- self.get_proxy()
81
- if int(time.time() - self.starttime_val) > 30:
82
- self.val_all()
83
- time.sleep(5)
84
-
85
-
86
- if __name__ == "__main__":
87
- Kproxy().run()
@@ -1,113 +0,0 @@
1
- import re
2
-
3
- from bs4 import BeautifulSoup
4
-
5
- from re_common.baselibrary.utils.baserequest import BaseRequest
6
- from re_common.baselibrary.utils.baseurl import BaseUrl
7
- from re_common.baselibrary.utils.myredisclient import MyRedis
8
-
9
-
10
- class ProxyAll(object):
11
-
12
- def __init__(self, config="./db.ini"):
13
- self.config = config
14
- self.myredis = MyRedis(self.config)
15
- self.myredis.set_redis_from_config()
16
- self.myredis.conn_redis()
17
- self.Headers = {
18
- 'Accept': '*/*',
19
- 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko',
20
- }
21
- self.UserAgent = 'Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko'
22
- self.baserequest = BaseRequest()
23
-
24
- def get_redis_all(self):
25
- return self.myredis.getDataFromRedis()
26
-
27
- def getProxyFromMimvp(self, num=600):
28
- r""" 从 http://proxy.mimvp.com/ 获取代理地址 """
29
- # http://proxy.mimvp.com/api/fetch.php?orderid=860160414114016557&num=100&http_type=1&anonymous=3&ping_time=1&transfer_time=5
30
- url = 'http://proxy.mimvp.com/api/fetch.php'
31
- dicts = {
32
- "orderid": "860161011165812474",
33
- "num": num,
34
- "http_type": "1", # 协议类型(http)
35
- "anonymous": "2,3,5", # 提取透明,匿名+欺骗,高匿
36
- "ping_time": "1", # 响应时间
37
- "transfer_time": "5", # 传输速度
38
- }
39
- url = BaseUrl.dicts_to_url(dicts, url=url)
40
-
41
- proxyPool = set()
42
-
43
- BoolResult, errString, r = self.baserequest.base_request(url, headers=self.Headers, timeout=10)
44
- if not BoolResult:
45
- return proxyPool
46
-
47
- lst = r.text.split('\n')
48
- for line in lst:
49
- line = line.strip()
50
- if line.count('.') == 3:
51
- proxyPool.add(line)
52
- return proxyPool
53
-
54
- # 从 http://tpv.daxiangdaili.com 获取代理地址,<- 大象代理
55
- # http://tpv.daxiangdaili.com/ip/?tid=556923006054759&num=1000
56
- def getProxyFromDaxiang(self, num):
57
- url = 'http://tpv.daxiangdaili.com/ip/'
58
- dicts = {
59
- "tid": "556923006054759",
60
- "num": num,
61
- # "filter":"on",
62
- "foreign": "all",
63
- "delay": "5" # 延迟时间
64
- }
65
- url = BaseUrl.dicts_to_url(dicts, url=url)
66
-
67
- proxyPool = set()
68
-
69
- BoolResult, errString, r = self.baserequest.base_request(url, headers=self.Headers, timeout=10)
70
- if not BoolResult:
71
- return proxyPool
72
-
73
- # print('daili666:' + repr(r.text))
74
- lst = r.text.split('\n')
75
- for line in lst:
76
- line = line.strip()
77
- if line.count('.') == 3:
78
- proxyPool.add(line)
79
-
80
- return proxyPool
81
-
82
- # 从http://www.xici.net.co/nn/获取代理地址
83
- # pageNum表示采集第几页
84
- def getProxyFromXICIOnePage(self, pageNum):
85
- ProxyPool = set()
86
-
87
- url = 'http://www.xicidaili.com/nn/'
88
- if pageNum > 1:
89
- url += str(pageNum)
90
-
91
- proxyPool = set()
92
- BoolResult, errString, r = self.baserequest.base_request(url, headers=self.Headers, timeout=10)
93
- if not BoolResult:
94
- return proxyPool
95
-
96
- html = r.content.decode('utf-8')
97
-
98
- soup = BeautifulSoup(html, 'html.parser')
99
- ipTable = soup.find('table', id='ip_list')
100
- if not ipTable:
101
- print('Error: not ipTable')
102
- return set()
103
-
104
- for trTag in ipTable.find_all('tr'):
105
- lst = list(trTag.find_all('td'))
106
- if len(lst) != 10:
107
- continue
108
- ip = ''.join(lst[1].stripped_strings)
109
- port = ''.join(lst[2].stripped_strings)
110
- item = ip + ':' + port
111
- if re.match(r'^[\d\.:]+$', item):
112
- ProxyPool.add(item)
113
- return ProxyPool
@@ -1,42 +0,0 @@
1
- import json
2
-
3
- ###########################################
4
- # 同项目调用基础包
5
- import os
6
- import sys
7
- import time
8
-
9
- filepath = os.path.abspath(__file__)
10
- pathlist = filepath.split(os.sep)
11
- pathlist = pathlist[:-4]
12
- TopPath = os.sep.join(pathlist)
13
- sys.path.insert(0, TopPath)
14
- print(TopPath)
15
- ############################################
16
-
17
- from re_common.baselibrary.utils.baserequest import BaseRequest
18
- from re_common.facade.mysqlfacade import MysqlUtiles
19
- from re_common.baselibrary.utils.basedir import BaseDir
20
- from re_common.baselibrary.utils.basefile import BaseFile
21
- from re_common.facade.lazy_import import get_streamlogger
22
-
23
-
24
- class Kproxy(object):
25
- def __init__(self):
26
- self.cur_path = BaseDir.get_file_dir_absolute(__file__)
27
- self.configfile = BaseFile.get_new_path(self.cur_path, "db.ini")
28
- self.logger = get_streamlogger()
29
- self.mysqlutils = MysqlUtiles(self.configfile, "dbkuaidaili", self.logger)
30
- self.starttime = time.time()
31
- self.starttime_val = time.time()
32
-
33
- def run(self):
34
- sql = "update `kuaidailiproxy` set val_stat=1 WHERE stat=1"
35
- self.mysqlutils.ExeSqlToDB(sql)
36
-
37
-
38
- if __name__ == "__main__":
39
- k = Kproxy()
40
- while True:
41
- k.run()
42
- time.sleep(60*2)
@@ -1,152 +0,0 @@
1
- ###########################################
2
- # 同项目调用基础包
3
- import os
4
- import sys
5
- import time
6
-
7
- filepath = os.path.abspath(__file__)
8
- pathlist = filepath.split(os.sep)
9
- pathlist = pathlist[:-4]
10
- TopPath = os.sep.join(pathlist)
11
- sys.path.insert(0, TopPath)
12
- print(TopPath)
13
- ############################################
14
-
15
- from re_common.facade.loggerfacade import get_streamlogger
16
- from re_common.baselibrary.mthread.MThreadingRun import MThreadingRun
17
- from re_common.baselibrary.mthread.mythreading import ThreadPoolManger, ThreadInfo
18
- from re_common.baselibrary.utils.baserequest import BaseRequest
19
- from re_common.baselibrary.utils.core.requests_core import set_proxy
20
- from re_common.baselibrary.utils.myredisclient import MyRedis
21
- from re_common.facade.mysqlfacade import MysqlUtiles
22
-
23
- from proxy_all import ProxyAll
24
-
25
-
26
- class WanfangProxy(object):
27
-
28
- def __init__(self, config="./db.ini"):
29
- self.config = config
30
- self.logger = get_streamlogger()
31
- self.mysqlutils = MysqlUtiles(self.config, "dbwanfang", self.logger)
32
- self.Headers = {
33
- 'Accept': '*/*',
34
- 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko'
35
- }
36
- self.UserAgent = 'Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko'
37
- self.baserequest = BaseRequest()
38
-
39
- def checking_proxy(self, proxy):
40
- url = "http://www.wanfangdata.com.cn/index.html"
41
- proxies = set_proxy(proxy)
42
- BoolResult, errString, r = self.baserequest.base_request(url,
43
- headers=self.Headers,
44
- proxies=proxies,
45
- marks=["container"],
46
- timeout=5)
47
- if BoolResult:
48
- return proxy
49
- return ""
50
-
51
- def get_mysql_proxy(self):
52
- sql = "SELECT proxy FROM `proxy_pool`"
53
- bools, rows = self.mysqlutils.SelectFromDB(sql)
54
- if not bools:
55
- return set()
56
- results = set()
57
- for row in rows:
58
- results.add(row[0])
59
- sql = "delete from proxy_pool"
60
- self.mysqlutils.ExeSqlToDB(sql)
61
- return results
62
-
63
- def get_all_proxy(self):
64
- proxy_set = set()
65
- proxyall = ProxyAll()
66
- redisproxy = proxyall.get_redis_all()
67
- mimvpproxy = proxyall.getProxyFromMimvp(1000)
68
- daxiangproxy = proxyall.getProxyFromDaxiang(1000)
69
- xiciproxy1 = proxyall.getProxyFromXICIOnePage(1)
70
- xiciproxy2 = proxyall.getProxyFromXICIOnePage(2)
71
- mysqlproxy = self.get_mysql_proxy()
72
- proxy_set = proxy_set.union(mysqlproxy, redisproxy, mimvpproxy, daxiangproxy, xiciproxy1, xiciproxy2)
73
- self.logger.info("all proxy size is:{}".format(len(proxy_set)))
74
- self.proxy_set = proxy_set
75
- return proxy_set
76
-
77
- def get_can_use_proxy(self):
78
- count = 0
79
- use_proxy = set()
80
- for proxy in self.proxy_set:
81
- proxy_ = self.checking_proxy(proxy)
82
- use_proxy.add(proxy_)
83
- if len(use_proxy) > 20:
84
- count = count + 1
85
- if count == 1:
86
- sql = "delete from proxy_pool"
87
- self.mysqlutils.ExeSqlToDB(sql)
88
- sql = "insert into proxy_pool(proxy) values ('%s')"
89
- self.mysqlutils.ExeSqlMany(sql, use_proxy)
90
- use_proxy.clear()
91
- if len(use_proxy) > 0:
92
- sql = "insert into proxy_pool(proxy) values ('%s')"
93
- self.mysqlutils.ExeSqlMany(sql, use_proxy)
94
- use_proxy.clear()
95
-
96
-
97
- class DetailThreadRun(MThreadingRun):
98
- def __init__(self, num):
99
- self.cnki = WanfangProxy()
100
- super(DetailThreadRun, self).__init__(num)
101
- self.config = "./db.ini"
102
- self.myredisset = MyRedis(self.config)
103
- self.myredisset.set_redis_from_config(sesc="proxysetwanfangjournal")
104
- self.myredisset.conn_redis()
105
- self.myredisset.get_pipeline()
106
-
107
- @ThreadPoolManger.thread_lock
108
- def getTask(self, *args, **kwargs):
109
- self.myredisset.delete(self.myredisset.RedisKey)
110
- proxy_set = self.cnki.get_all_proxy()
111
- return proxy_set
112
-
113
- def setTask(self, results=None, *args, **kwargs):
114
- for url_tasks in results:
115
- # 将每一页加入任务队列
116
- self.add_job(self.func, url_tasks)
117
- time.sleep(10 * 60)
118
-
119
- @ThreadPoolManger.thread_lock
120
- def dealresult(self, *args, **kwargs):
121
- sql = "replace into proxy_pool(`proxy`) values (%s)"
122
- self.cnki.mysqlutils.ExeSqlMany(sql, self.results)
123
- self.myredisset.sadd(self.myredisset.RedisKey, set(self.results))
124
-
125
- def setProxy(self, proxysList=None):
126
- pass
127
-
128
- def is_break(self):
129
- return False
130
-
131
- def thread_pool_hook(self, threadinfo: ThreadInfo):
132
- # 设置代理线程不重启,默认会重启
133
- if threadinfo.get_thread_name() == self.etn.proxythreadname:
134
- threadinfo.set_is_restart(False)
135
- if threadinfo.get_thread_name() == self.etn.taskthreadname:
136
- threadinfo.set_is_restart(False)
137
- return {}
138
-
139
- def fun(self, threadval, *args, **kwargs):
140
- standardid = args[0]
141
- proxys = self.cnki.checking_proxy(standardid)
142
- if proxys != "":
143
- threadval.result_queue.put(proxys)
144
-
145
-
146
- def main():
147
- down = DetailThreadRun(40)
148
- down.run()
149
-
150
-
151
- if __name__ == "__main__":
152
- main()