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
7edb7b21
Commit
7edb7b21
authored
Jul 27, 2020
by
litaolemo
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
update
parent
ab30ed35
Show whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
4 additions
and
4 deletions
+4
-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
-2
crawler_douban.py
crawler_sys/site_crawler_by_redis/crawler_douban.py
+2
-2
No files found.
crawler_sys/framework/update_data_in_target_releasers_multi_process_by_date_from_redis.py
View file @
7edb7b21
...
...
@@ -14,7 +14,7 @@ Data in es will be update when run this program once.
@author: hanye
"""
from
crawler.crawler_sys.site_crawler_by_redis
import
crawler_d
ouban
from
crawler.crawler_sys.site_crawler_by_redis
.crawler_douban
import
CrawlerD
ouban
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
...
...
@@ -89,7 +89,7 @@ platform_crawler_reg = {
# "网易新闻": crawler_wangyi_news.Crawler_wangyi_news,
# "kwai": crawler_kwai.Crawler_kwai,
"weibo"
:
crawler_weibo
.
Crawler_weibo
,
"douban"
:
crawler_douban
.
Crawler_
Douban
"douban"
:
Crawler
Douban
}
...
...
crawler_sys/site_crawler_by_redis/crawler_douban.py
View file @
7edb7b21
...
...
@@ -32,7 +32,7 @@ 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
():
class
CrawlerDouban
():
def
__init__
(
self
,
timeout
=
None
,
platform
=
'douban'
):
if
timeout
==
None
:
self
.
timeout
=
10
...
...
@@ -258,7 +258,7 @@ class Crawler_Douban():
if
__name__
==
'__main__'
:
test
=
Crawler_
d
ouban
()
test
=
Crawler_
D
ouban
()
url
=
'https://weibo.com/p/1644114654/home?from=page_100306&mod=TAB#place'
# releaserUrl = 'http://v.qq.com/vplus/cfa34d96d1b6609f1dccdea65b26b83d'
url_list
=
[
...
...
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