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
backend
crawler
Commits
d007eae9
Commit
d007eae9
authored
4 years ago
by
litaolemo
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
update
parent
dab02ae8
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
14 additions
and
8 deletions
+14
-8
cal_ni_and_put_to_backend.py
crawler_sys/scheduler/cal_ni_and_put_to_backend.py
+14
-8
No files found.
crawler_sys/scheduler/cal_ni_and_put_to_backend.py
View file @
d007eae9
...
@@ -312,6 +312,8 @@ def write_data_into_mysql(res_data):
...
@@ -312,6 +312,8 @@ def write_data_into_mysql(res_data):
now_str
=
datetime
.
datetime
.
now
()
.
strftime
(
"
%
Y-
%
m-
%
d
%
H:
%
M:
%
S"
)
now_str
=
datetime
.
datetime
.
now
()
.
strftime
(
"
%
Y-
%
m-
%
d
%
H:
%
M:
%
S"
)
# 清洗数据为可以入库的格式
# 清洗数据为可以入库的格式
data
=
push_data_to_user
(
res_data
)
data
=
push_data_to_user
(
res_data
)
if
not
data
[
"content"
]:
return
None
tractate_id
=
0
tractate_id
=
0
try
:
try
:
sql_query
=
"""insert into api_tractate
sql_query
=
"""insert into api_tractate
...
@@ -386,19 +388,23 @@ def task_main():
...
@@ -386,19 +388,23 @@ def task_main():
# 循环处理抓取数据,返回需要添加至后端的数据
# 循环处理抓取数据,返回需要添加至后端的数据
for
res_data
in
scan_from_redis
(
rules_list
):
for
res_data
in
scan_from_redis
(
rules_list
):
tractate_id
=
write_data_into_mysql
(
res_data
)
tractate_id
=
write_data_into_mysql
(
res_data
)
if
res_data
[
"level"
]
>=
1
:
try
:
title_str
=
res_data
[
"platform"
]
+
"帖子内容审核"
print
(
res_data
)
body_str
=
"""
if
res_data
[
"level"
]
>=
1
and
tractate_id
:
title_str
=
res_data
[
"platform"
]
+
"帖子内容审核"
body_str
=
"""
问好:
问好:
有一篇新的内容需要审核,帖子号为{tractate_id}
有一篇新的内容需要审核,帖子号为{tractate_id}
内容如下:
内容如下:
{content}
{content}
"""
.
format
(
tractate_id
=
tractate_id
,
content
=
res_data
[
"content"
])
"""
.
format
(
tractate_id
=
tractate_id
,
content
=
res_data
[
"content"
])
send_file_email
(
""
,
""
,
email_group
=
[
"<duanyingrong@igengmei.com>"
],
cc_group
=
[
"litao@igengmei.com"
],
send_file_email
(
""
,
""
,
email_group
=
[
"<duanyingrong@igengmei.com>"
],
cc_group
=
[
"litao@igengmei.com"
],
email_msg_body_str
=
body_str
,
title_str
=
title_str
)
email_msg_body_str
=
body_str
,
title_str
=
title_str
)
print
(
"send to mysql"
)
print
(
"send to mysql"
)
print
(
res_data
)
except
Exception
as
e
:
print
(
"send email error
%
s"
%
e
)
# test = {'release_time': 1595952037000, 'fetch_time': 1596012816514, 'url': 'https://www.douban.com/group/topic/186707979/', 'releaser': '🍫', 'repost_count': 40, 'comment_count': 411, 'favorite_count': 144, 'title': '王俊凯终于还是举铁了', 'releaserUrl': 'https://www.douban.com/people/57762442', 'releaser_id_str': 'douban_57762442', 'video_img': 'https://img3.doubanio.com/view/group_topic/sqxs/public/p317684082.webp', 'mid': '186707979', 'platform': 'douban', 'doc_id': 'douban_186707979', 'content': '<div id=\'content\'><div class="image-container image-float-center"><div class="image-wrapper"><img src="https://img3.doubanio.com/view/group_topic/l/public/p317684082.webp" width="500"/></div></div><div class="image-container image-float-center"><div class="image-wrapper"><img src="https://img9.doubanio.com/view/group_topic/l/public/p317684064.webp" width="500"/></div></div><div class="image-container image-float-center"><div class="image-wrapper"><img src="https://img3.doubanio.com/view/group_topic/l/public/p317684093.webp" width="500"/></div></div><div class="image-container image-float-center"><div class="image-wrapper"><img src="https://img9.doubanio.com/view/group_topic/l/public/p317684095.webp" width="500"/></div></div><div class="image-container image-float-center"><div class="image-wrapper"><img src="https://img3.doubanio.com/view/group_topic/l/public/p317684052.webp" width="500"/></div></div><p></p></div>', 'collection_count': 107, 'img_list': ['https://img3.doubanio.com/view/group_topic/l/public/p317684082.webp', 'https://img9.doubanio.com/view/group_topic/l/public/p317684064.webp', 'https://img3.doubanio.com/view/group_topic/l/public/p317684093.webp', 'https://img9.doubanio.com/view/group_topic/l/public/p317684095.webp', 'https://img3.doubanio.com/view/group_topic/l/public/p317684052.webp'], 'level': 5}
# test = {'release_time': 1595952037000, 'fetch_time': 1596012816514, 'url': 'https://www.douban.com/group/topic/186707979/', 'releaser': '🍫', 'repost_count': 40, 'comment_count': 411, 'favorite_count': 144, 'title': '王俊凯终于还是举铁了', 'releaserUrl': 'https://www.douban.com/people/57762442', 'releaser_id_str': 'douban_57762442', 'video_img': 'https://img3.doubanio.com/view/group_topic/sqxs/public/p317684082.webp', 'mid': '186707979', 'platform': 'douban', 'doc_id': 'douban_186707979', 'content': '<div id=\'content\'><div class="image-container image-float-center"><div class="image-wrapper"><img src="https://img3.doubanio.com/view/group_topic/l/public/p317684082.webp" width="500"/></div></div><div class="image-container image-float-center"><div class="image-wrapper"><img src="https://img9.doubanio.com/view/group_topic/l/public/p317684064.webp" width="500"/></div></div><div class="image-container image-float-center"><div class="image-wrapper"><img src="https://img3.doubanio.com/view/group_topic/l/public/p317684093.webp" width="500"/></div></div><div class="image-container image-float-center"><div class="image-wrapper"><img src="https://img9.doubanio.com/view/group_topic/l/public/p317684095.webp" width="500"/></div></div><div class="image-container image-float-center"><div class="image-wrapper"><img src="https://img3.doubanio.com/view/group_topic/l/public/p317684052.webp" width="500"/></div></div><p></p></div>', 'collection_count': 107, 'img_list': ['https://img3.doubanio.com/view/group_topic/l/public/p317684082.webp', 'https://img9.doubanio.com/view/group_topic/l/public/p317684064.webp', 'https://img3.doubanio.com/view/group_topic/l/public/p317684093.webp', 'https://img9.doubanio.com/view/group_topic/l/public/p317684095.webp', 'https://img3.doubanio.com/view/group_topic/l/public/p317684052.webp'], 'level': 5}
# write_data_into_mysql(test)
# write_data_into_mysql(test)
cur
.
close
()
cur
.
close
()
...
...
This diff is collapsed.
Click to expand it.
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