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
56124821
Commit
56124821
authored
Aug 10, 2020
by
litaolemo
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
update
parent
b437f023
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
4 additions
and
4 deletions
+4
-4
search_page_multi_process.py
crawler_sys/framework/search_page_multi_process.py
+1
-1
crawler_weibo.py
crawler_sys/site_crawler/crawler_weibo/crawler_weibo.py
+1
-1
crawler_zhihu.py
crawler_sys/site_crawler/crawler_zhihu.py
+2
-2
No files found.
crawler_sys/framework/search_page_multi_process.py
View file @
56124821
...
...
@@ -2699,7 +2699,7 @@ def search_page_task(platform, output_to_es_raw,
search_pages_max
=
search_pages
,
output_to_es_raw
=
output_to_es_raw
,
output_to_es_register
=
output_to_es_register
,
es_index
=
es_index
,
proxies_num
=
3
)
es_index
=
es_index
,
proxies_num
=
5
)
except
Exception
as
e
:
print
(
e
)
...
...
crawler_sys/site_crawler/crawler_weibo/crawler_weibo.py
View file @
56124821
...
...
@@ -425,7 +425,7 @@ class Crawler_weibo():
video_dic
[
"title"
]
=
data
[
"title"
]
video_dic
[
"fetch_time"
]
=
int
(
datetime
.
datetime
.
now
()
.
timestamp
()
*
1e3
)
video_dic
[
"release_time"
]
=
trans_strtime_to_timestamp
(
data
[
"create_at"
])
video_dic
[
"play_count"
]
=
i
nt
(
data
[
"read_count"
])
video_dic
[
"play_count"
]
=
trans_play_cou
nt
(
data
[
"read_count"
])
video_dic
[
"content"
]
=
data
[
"content"
]
video_dic
[
"releaser"
]
=
data
[
"userinfo"
]
.
get
(
'screen_name'
)
video_dic
[
"releaser_id"
]
=
str
(
data
[
"userinfo"
]
.
get
(
'id'
))
...
...
crawler_sys/site_crawler/crawler_zhihu.py
View file @
56124821
...
...
@@ -92,8 +92,8 @@ class Crawler_zhihu():
video_dic
[
"title"
]
=
data
[
"entities"
][
"answers"
][
answer_id
][
"question"
][
"title"
]
video_dic
[
"fetch_time"
]
=
int
(
datetime
.
datetime
.
now
()
.
timestamp
()
*
1e3
)
video_dic
[
"release_time"
]
=
int
(
data
[
"entities"
][
"answers"
][
answer_id
][
"createdTime"
]
*
1e3
)
video_dic
[
"voteup_count"
]
=
data
[
"entities"
][
"answers"
][
answer_id
][
"voteupCount"
]
video_dic
[
"comment_count"
]
=
data
[
"entities"
][
"answers"
][
answer_id
][
"commentCount"
]
video_dic
[
"voteup_count"
]
=
trans_play_count
(
data
[
"entities"
][
"answers"
][
answer_id
][
"voteupCount"
])
video_dic
[
"comment_count"
]
=
trans_play_count
(
data
[
"entities"
][
"answers"
][
answer_id
][
"commentCount"
])
video_dic
[
"content"
]
=
data
[
"entities"
][
"answers"
][
answer_id
][
"content"
]
video_dic
[
"releaser"
]
=
data
[
"entities"
][
"answers"
][
answer_id
][
"author"
][
"name"
]
video_dic
[
"releaser_id"
]
=
data
[
"entities"
][
"answers"
][
answer_id
][
"author"
][
"urlToken"
]
...
...
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