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
160c7a4a
Commit
160c7a4a
authored
Sep 23, 2020
by
litaolemo
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
update
parent
e23fd4f1
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
4 additions
and
3 deletions
+4
-3
cal_ni_and_put_to_backend.py
crawler_sys/scheduler/cal_ni_and_put_to_backend.py
+2
-1
crawler_kwai.py
crawler_sys/site_crawler/crawler_kwai.py
+1
-1
crawler_douban.py
crawler_sys/site_crawler_test/crawler_douban.py
+1
-1
No files found.
crawler_sys/scheduler/cal_ni_and_put_to_backend.py
View file @
160c7a4a
...
...
@@ -484,6 +484,7 @@ def task_main():
tractate_id
=
"test"
print
(
"line394"
,
tractate_id
,
res_data
)
if
res_data
[
"level"
]
>=
3
and
tractate_id
:
content
=
res_data
.
get
(
"content"
)
if
res_data
.
get
(
"content"
)
else
res_data
.
get
(
"title"
)
title_str
=
res_data
[
"platform"
]
+
"帖子内容审核"
body_str
=
"""
问好:
...
...
@@ -491,7 +492,7 @@ def task_main():
内容如下:
{content}
"""
.
format
(
tractate_id
=
tractate_id
,
content
=
res_data
[
"content"
]
,
level
=
res_data
[
"level"
],
releaser
=
res_data
[
"releaser"
])
"""
.
format
(
tractate_id
=
tractate_id
,
content
=
content
,
level
=
res_data
[
"level"
],
releaser
=
res_data
[
"releaser"
])
send_file_email
(
""
,
""
,
email_group
=
[
"<litao@igengmei.com>"
# "<liulingling@igengmei.com>", "<liujinhuan@igengmei.com>",
...
...
crawler_sys/site_crawler/crawler_kwai.py
View file @
160c7a4a
...
...
@@ -18,7 +18,7 @@ from crawler.crawler_sys.framework.video_fields_std import Std_fields_video
from
crawler.crawler_sys.utils.output_results
import
output_result
from
crawler.crawler_sys.utils.util_logging
import
logged
from
fontTools.ttLib
import
*
#
from crawler.crawler_sys.utils.func_verification_code import Login
from
crawler.crawler_sys.utils.func_verification_code
import
Login
try
:
from
crawler_sys.framework.func_get_releaser_id
import
*
...
...
crawler_sys/site_crawler_test/crawler_douban.py
View file @
160c7a4a
...
...
@@ -68,7 +68,7 @@ class Crawler_douban():
while
count_true
<=
3
:
try
:
count_true
+=
1
url
=
"https://frodo.douban.com/api/v2/group/topic/{0}?event_source=search&os_rom=android&apikey=0dad551ec0f84ed02907ff5c42e8ec70&channel=Baidu_Market&_sig={2}&udid=dc{1}e9f33c54b4bb579c49100b6f2cc0dc5cc"
.
format
(
mid
,
random
.
randint
(
10000
,
99999
),
random
.
choice
(
self
.
sig_list
))
url
=
"https://frodo.douban.com/api/v2/group/topic/{0}?event_source=search&os_rom=android&apikey=0dad551ec0f84ed02907ff5c42e8ec70&channel=Baidu_Market&_sig={2}&udid=dc{1}e9f33c54b4bb579c49100b6f2cc0dc5cc
&_ts=1598339497
"
.
format
(
mid
,
random
.
randint
(
10000
,
99999
),
random
.
choice
(
self
.
sig_list
))
page_res
=
retry_get_url
(
url
,
headers
=
self
.
headers
,
proxies
=
proxies
)
page_json
=
page_res
.
json
()
# content = dehtml(page_json["content"])
...
...
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