re-common 10.0.39__py3-none-any.whl → 10.0.41__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 (221) 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/business_utils/BusinessStringUtil.py +235 -220
  145. re_common/v2/baselibrary/business_utils/baseencodeid.py +100 -100
  146. re_common/v2/baselibrary/business_utils/full_doi_path.py +116 -116
  147. re_common/v2/baselibrary/business_utils/rel_tools.py +6 -6
  148. re_common/v2/baselibrary/decorators/utils.py +59 -59
  149. re_common/v2/baselibrary/helpers/search_packge/NearestNeighbors_test.py +105 -105
  150. re_common/v2/baselibrary/helpers/search_packge/fit_text_match.py +253 -253
  151. re_common/v2/baselibrary/helpers/search_packge/scikit_learn_text_matcher.py +260 -260
  152. re_common/v2/baselibrary/helpers/search_packge/test.py +1 -1
  153. re_common/v2/baselibrary/s3object/baseboto3.py +230 -230
  154. re_common/v2/baselibrary/tools/WeChatRobot.py +95 -95
  155. re_common/v2/baselibrary/tools/ac_ahocorasick.py +75 -75
  156. re_common/v2/baselibrary/tools/concurrency.py +35 -35
  157. re_common/v2/baselibrary/tools/data_processer/base.py +53 -53
  158. re_common/v2/baselibrary/tools/data_processer/data_processer.py +497 -508
  159. re_common/v2/baselibrary/tools/data_processer/data_reader.py +187 -187
  160. re_common/v2/baselibrary/tools/data_processer/data_writer.py +38 -38
  161. re_common/v2/baselibrary/tools/dict_tools.py +44 -44
  162. re_common/v2/baselibrary/tools/dolphinscheduler.py +187 -187
  163. re_common/v2/baselibrary/tools/hdfs_base_processor.py +204 -204
  164. re_common/v2/baselibrary/tools/hdfs_bulk_processor.py +67 -67
  165. re_common/v2/baselibrary/tools/hdfs_data_processer.py +338 -338
  166. re_common/v2/baselibrary/tools/hdfs_line_processor.py +74 -74
  167. re_common/v2/baselibrary/tools/list_tools.py +69 -69
  168. re_common/v2/baselibrary/tools/resume_tracker.py +94 -94
  169. re_common/v2/baselibrary/tools/search_hash_tools.py +54 -54
  170. re_common/v2/baselibrary/tools/text_matcher.py +326 -326
  171. re_common/v2/baselibrary/tools/tree_processor/__init__.py +0 -0
  172. re_common/v2/baselibrary/tools/tree_processor/builder.py +25 -0
  173. re_common/v2/baselibrary/tools/tree_processor/node.py +13 -0
  174. re_common/v2/baselibrary/tools/unionfind_tools.py +60 -60
  175. re_common/v2/baselibrary/utils/BusinessStringUtil.py +196 -196
  176. re_common/v2/baselibrary/utils/api_net_utils.py +270 -270
  177. re_common/v2/baselibrary/utils/author_smi.py +361 -361
  178. re_common/v2/baselibrary/utils/base_string_similarity.py +158 -158
  179. re_common/v2/baselibrary/utils/basedict.py +37 -37
  180. re_common/v2/baselibrary/utils/basehdfs.py +163 -163
  181. re_common/v2/baselibrary/utils/basepika.py +180 -180
  182. re_common/v2/baselibrary/utils/basetime.py +94 -77
  183. re_common/v2/baselibrary/utils/db.py +174 -156
  184. re_common/v2/baselibrary/utils/elasticsearch.py +46 -0
  185. re_common/v2/baselibrary/utils/json_cls.py +16 -16
  186. re_common/v2/baselibrary/utils/mq.py +83 -83
  187. re_common/v2/baselibrary/utils/n_ary_expression_tree.py +243 -243
  188. re_common/v2/baselibrary/utils/string_bool.py +187 -186
  189. re_common/v2/baselibrary/utils/string_clear.py +246 -246
  190. re_common/v2/baselibrary/utils/string_smi.py +18 -18
  191. re_common/v2/baselibrary/utils/stringutils.py +312 -271
  192. re_common/vip/base_step_process.py +11 -11
  193. re_common/vip/baseencodeid.py +90 -90
  194. re_common/vip/changetaskname.py +28 -28
  195. re_common/vip/core_var.py +24 -24
  196. re_common/vip/mmh3Hash.py +89 -89
  197. re_common/vip/proxy/allproxys.py +127 -127
  198. re_common/vip/proxy/allproxys_thread.py +159 -159
  199. re_common/vip/proxy/cnki_proxy.py +153 -153
  200. re_common/vip/proxy/kuaidaili.py +87 -87
  201. re_common/vip/proxy/proxy_all.py +113 -113
  202. re_common/vip/proxy/update_kuaidaili_0.py +42 -42
  203. re_common/vip/proxy/wanfang_proxy.py +152 -152
  204. re_common/vip/proxy/wp_proxy_all.py +181 -181
  205. re_common/vip/read_rawid_to_txt.py +91 -91
  206. re_common/vip/title/__init__.py +5 -5
  207. re_common/vip/title/transform/TransformBookTitleToZt.py +125 -125
  208. re_common/vip/title/transform/TransformConferenceTitleToZt.py +139 -139
  209. re_common/vip/title/transform/TransformCstadTitleToZt.py +195 -195
  210. re_common/vip/title/transform/TransformJournalTitleToZt.py +203 -203
  211. re_common/vip/title/transform/TransformPatentTitleToZt.py +132 -132
  212. re_common/vip/title/transform/TransformRegulationTitleToZt.py +114 -114
  213. re_common/vip/title/transform/TransformStandardTitleToZt.py +135 -135
  214. re_common/vip/title/transform/TransformThesisTitleToZt.py +135 -135
  215. re_common/vip/title/transform/__init__.py +10 -10
  216. {re_common-10.0.39.dist-info → re_common-10.0.41.dist-info}/LICENSE +201 -201
  217. {re_common-10.0.39.dist-info → re_common-10.0.41.dist-info}/METADATA +16 -16
  218. re_common-10.0.41.dist-info/RECORD +252 -0
  219. {re_common-10.0.39.dist-info → re_common-10.0.41.dist-info}/WHEEL +1 -1
  220. re_common-10.0.39.dist-info/RECORD +0 -248
  221. {re_common-10.0.39.dist-info → re_common-10.0.41.dist-info}/top_level.txt +0 -0
@@ -1,113 +1,113 @@
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
+ 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 +1,42 @@
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
+ 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 +1,152 @@
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()
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()