Skip to content
Projects
Groups
Snippets
Help
Loading...
Sign in
Toggle navigation
C
crawler
Project
Project
Details
Activity
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
Chengyang Zhong
crawler
Commits
77e3344a
Commit
77e3344a
authored
Jul 27, 2020
by
litaolemo
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
update
parent
1b54de34
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
5 additions
and
4 deletions
+5
-4
update_data_in_target_releasers_multi_process_by_date_from_redis.py
...a_in_target_releasers_multi_process_by_date_from_redis.py
+2
-1
crawler_douban.py
crawler_sys/site_crawler_by_redis/crawler_douban.py
+3
-3
No files found.
crawler_sys/framework/update_data_in_target_releasers_multi_process_by_date_from_redis.py
View file @
77e3344a
...
...
@@ -14,10 +14,11 @@ Data in es will be update when run this program once.
@author: hanye
"""
from
crawler.crawler_sys.site_crawler_by_redis
import
crawler_douban
from
crawler.crawler_sys.site_crawler_by_redis
import
crawler_toutiao
from
crawler.crawler_sys.site_crawler_by_redis
import
toutiao_article
from
crawler.crawler_sys.site_crawler_by_redis
import
crawler_weibo
from
crawler.crawler_sys.site_crawler_by_redis
import
crawler_douban
# crawler_v_qq, crawler_tudou, crawler_haokan,
# crawler_tencent_news,
# crawler_wangyi_news, crawler_kwai, crawler_douyin,
...
...
crawler_sys/site_crawler_by_redis/crawler_douban.py
View file @
77e3344a
...
...
@@ -26,14 +26,14 @@ from crawler.crawler_sys.utils.trans_strtime_to_timestamp import weibo_parse_tim
# from crawler.crawler_sys.utils.trans_duration_str_to_second import trans_duration
# from crawler.crawler_sys.utils.util_logging import logged
# from crawler.crawler_sys.proxy_pool.func_get_proxy_form_kuaidaili import get_proxy
from
crawler.crawler_sys.utils.html_to_str
import
dehtml
from
bs4
import
BeautifulSoup
#
from crawler.crawler_sys.utils.html_to_str import dehtml
#
from bs4 import BeautifulSoup
from
write_data_into_es.func_get_releaser_id
import
*
from
write_data_into_es.func_cal_doc_id
import
cal_doc_id
class
Crawler_douban
():
def
__init__
(
self
,
timeout
=
None
,
platform
=
'
weibo
'
):
def
__init__
(
self
,
timeout
=
None
,
platform
=
'
douban
'
):
if
timeout
==
None
:
self
.
timeout
=
10
else
:
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment