update

crawler_sys/framework/es_target_releasers.py

@@ -10,16 +10,17 @@ from elasticsearch import Elasticsearch
 from elasticsearch.helpers import scan
 
 #  rds=redis.StrictRedis(host='192.168.17.26',port=6379,db=0)
+hosts = '172.18.52.14'
+port = 9200
 
-es_framework = Elasticsearch(hosts='172.16.32.37', port=9200)
+HTTP_AUTH = ("elastic", "gm_test")
+es_framework = Elasticsearch(hosts=hosts, port=port, http_auth=HTTP_AUTH)
 
 index_target_releaser = 'target_releasers'
-doc_type_target_releaser = 'doc'
 
 
 def bulk_write_target_releasers(dict_Lst,
-                                index=index_target_releaser,
-                                doc_type=doc_type_target_releaser):
+                                index=index_target_releaser,):
     bulk_write_body=''
     write_counter=0
     for line in dict_Lst:
@@ -28,8 +29,8 @@ def bulk_write_target_releasers(dict_Lst,
             releaser=line['releaser']
             platform=line['platform']
             doc_id_releaser='%s_%s' % (platform, releaser)
-            action_str=('{ "index" : { "_index" : "%s", "_type" : "%s","_id" : "%s" } }'
-                        % (index_target_releaser, doc_type_target_releaser, doc_id_releaser) )
+            action_str=('{ "index" : { "_index" : "%s","_id" : "%s" } }'
+                        % (index_target_releaser, doc_id_releaser))
             data_str=json.dumps(line, ensure_ascii=False)
             line_body = action_str + '\n' + data_str + '\n'
             bulk_write_body += line_body
@@ -58,7 +59,7 @@ def get_releaserUrls_from_es(platform,
     #     search_body['query']['bool']['filter'].append(frequency_dict)
     # print(target_index,doc_type_target_releaser,search_body)
     print(search_body)
-    search_resp=es_framework.search(index=target_index,
+    search_resp= es_framework.search(index=target_index,
                                      body=search_body,
                                      size=0,
                                      request_timeout=100)

crawler_sys/framework/write_releasers_to_redis.py

@@ -34,8 +34,8 @@ from redis.sentinel import Sentinel
 # 连接数据库
 # rds = sentinel.master_for('ida_redis_master', socket_timeout=0.5, db=1, decode_responses=True)
 
-rds = redis.StrictRedis(host='172.16.40.164', port=6379, db=19, decode_responses=True, password='ReDis!GmTx*0aN12')
-
+# rds = redis.StrictRedis(host='172.18.51.10', port=6379, db=19, decode_responses=True, password='ReDis!GmTx*0aN12')
+rds = redis.StrictRedis(host='172.18.51.10', port=6379, db=19, decode_responses=True)
 parser = argparse.ArgumentParser(description='Specify a platform name.')
 parser.add_argument('-p', '--platform', default=[], action='append',
                     help=('Pass platform names, they will be assembled in python list.'))

crawler_sys/site_crawler/crawler_xiaohongshu.py

@@ -21,7 +21,7 @@ from crawler.gm_upload.gm_upload import upload, upload_file
 from selenium.webdriver import ActionChains
 from selenium import webdriver
 try:
-    from crawler_sys.framework.func_get_releaser_id import *
+    from write_data_into_es.func_get_releaser_id import *
 except:
     from func_get_releaser_id import *
 from crawler.crawler_sys.proxy_pool.func_get_proxy_form_kuaidaili import get_proxy

run.sh

 #!/bin/bash
 #sudo su - gmuser
-#source /root/anaconda3/bin/activate
+crawler-ops
 #conda activate crawler_env
-#/home/gmuser/.virtualenvs/litao/bin/python3  /srv/apps/crawler/crawler_sys/framework/write_releasers_to_redis.py -p weibo -d 1 -proxies 5 > /data/log/crawler/write_task.log &
-/home/gmuser/.virtualenvs/litao/bin/python3  /srv/apps/crawler/crawler_sys/framework/write_releasers_to_redis.py -p douban -d 1 -proxies 5 > /data/log/crawler/write_task.log &
+python  /srv/apps/crawler/crawler_sys/framework/write_releasers_to_redis.py -p weibo -d 1 -proxies 5 > /data/log/crawler/write_task.log &
+#/home/gmuser/.virtualenvs/litao/bin/python3  /srv/apps/crawler/crawler_sys/framework/write_releasers_to_redis.py -p douban -d 1 -proxies 5 > /data/log/crawler/write_task.log &

write_data_into_es/func_get_releaser_id.py

@@ -281,6 +281,20 @@ def douban(releaserUrl,**kwargs):
         releaser_id = re.findall(r"people/(.*)", releaserUrl)[0]
     return releaser_id
 
+def xiaohongshu(releaserUrl,**kwargs):
+    releaserUrl = releaserUrl.split("?")[0]
+    res = re.findall(r"user/profile/(.*)", releaserUrl)
+    if res:
+        return res[0]
+    else:
+        return None
+
+def zhihu(releaserUrl,**kwargs):
+    releaserUrl = releaserUrl.split("?")[0]
+    releaser_id = re.findall(r"people/(.+)", releaserUrl)[0]
+    if "/" in releaser_id:
+        releaser_id = releaser_id.split("/")[0]
+    return releaser_id
 
 plantform_func = {
     "toutiao": toutiao,
@@ -297,7 +311,9 @@ plantform_func = {
     "weixin":weixin,
     "weibo":weibo,
     "pearvideo":pearvideo,
-    "douban":douban
+    "douban":douban,
+    "zhihu":zhihu,
+    "xiaohongshu":xiaohongshu
 }
 
 
@@ -335,4 +351,4 @@ if __name__ == "__main__":
     #         print(get_releaser_id(platform=platform,releaserUrl=releaserUrl))
     # print(releaser_id)
 
-    # print(weibo("https://weibo.com/1656058115"))
+    print(zhihu("https://www.zhihu.com/people/kokokou/jkh?!23"))
\ No newline at end of file