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
e3acccb8
Commit
e3acccb8
authored
Dec 30, 2020
by
haowang
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
fix
parent
9bde750f
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
10 additions
and
16 deletions
+10
-16
spider.py
tasks/zhihu/spider.py
+10
-16
No files found.
tasks/zhihu/spider.py
View file @
e3acccb8
...
...
@@ -22,15 +22,6 @@ PASSWD = 'Gengmei123'
DB
=
'spider'
# JS_FILE_PATH = '/srv/apps/crawler/crawler_sys/site_crawler/zhihu.js'
JS_FILE_PATH
=
'/Users/haowei/workspace/gm/crawler/crawler_sys/site_crawler/zhihu.js'
# SPIDER_URL = 'https://www.zhihu.com/people/geng-mei-suo-chang/answers?page=1'
# ANSWER_URL = 'https://www.zhihu.com/api/v4/members/geng-mei-suo-chang/answers?include=data%5B*%5D.is_normal%2Cadmin_closed_comment%2Creward_info%2Cis_collapsed%2Cannotation_action%2Cannotation_detail%2Ccollapse_reason%2Ccollapsed_by%2Csuggest_edit%2Ccomment_count%2Ccan_comment%2Ccontent%2Ceditable_content%2Cvoteup_count%2Creshipment_settings%2Ccomment_permission%2Cmark_infos%2Ccreated_time%2Cupdated_time%2Creview_info%2Cexcerpt%2Cis_labeled%2Clabel_info%2Crelationship.is_authorized%2Cvoting%2Cis_author%2Cis_thanked%2Cis_nothelp%2Cis_recognized%3Bdata%5B*%5D.author.badge%5B%3F(type%3Dbest_answerer)%5D.topics%3Bdata%5B*%5D.question.has_publishing_draft%2Crelationship&offset={0}&limit=20&sort_by=created'
# ARTICLE_URL = 'https://www.zhihu.com/api/v4/members/geng-mei-suo-chang/articles?include=data%5B*%5D.comment_count%2Csuggest_edit%2Cis_normal%2Cthumbnail_extra_info%2Cthumbnail%2Ccan_comment%2Ccomment_permission%2Cadmin_closed_comment%2Ccontent%2Cvoteup_count%2Ccreated%2Cupdated%2Cupvoted_followees%2Cvoting%2Creview_info%2Cis_labeled%2Clabel_info%3Bdata%5B*%5D.author.badge%5B%3F(type%3Dbest_answerer)%5D.topics&offset={0}&limit=20&sort_by=created'
# THOUGHT_URL = 'https://www.zhihu.com/api/v4/members/geng-mei-suo-chang/pins?offset={0}&limit=20&includes=data%5B*%5D.upvoted_followees%2Cadmin_closed_comment'
# ANSWER_ROOT_COMMENT_URL = 'https://www.zhihu.com/api/v4/answers/{0}/root_comments?order=normal&limit=20&offset={1}&status=open'
# ARTICLE_ROOT_COMMENT_URL = 'https://www.zhihu.com/api/v4/articles/{0}/root_comments?order=normal&limit=20&offset={1}&status=open'
# CHILD_COMMENT_START_URL = 'https://www.zhihu.com/api/v4/comments/{0}/child_comments'
# CHILD_COMMENT_OFFSET_URL = 'https://www.zhihu.com/api/v4/comments/{0}/child_comments?limit=20&offset={1}'
# THOUGHT_COMMENT_URL = 'https://www.zhihu.com/api/v4/pins/{0}/comments?order=normal&limit=20&offset={1}&status=open'
def
retry_get_url_no_proxies
(
url
,
retrys
=
3
,
timeout
=
10
,
**
kwargs
):
...
...
@@ -76,7 +67,8 @@ class Spider(object):
self
.
cur
=
self
.
conn
.
cursor
()
self
.
spider_url
=
spider_url
self
.
ANSWER_URL
=
self
.
spider_url
.
replace
(
"https://www.zhihu.com/people"
,
"https://www.zhihu.com/api/v4/members"
)
+
'/answers?include=data
%5
B*
%5
D.is_normal
%2
Cadmin_closed_comment
%2
Creward_info
%2
Cis_collapsed
%2
Cannotation_action
%2
Cannotation_detail
%2
Ccollapse_reason
%2
Ccollapsed_by
%2
Csuggest_edit
%2
Ccomment_count
%2
Ccan_comment
%2
Ccontent
%2
Ceditable_content
%2
Cvoteup_count
%2
Creshipment_settings
%2
Ccomment_permission
%2
Cmark_infos
%2
Ccreated_time
%2
Cupdated_time
%2
Creview_info
%2
Cexcerpt
%2
Cis_labeled
%2
Clabel_info
%2
Crelationship.is_authorized
%2
Cvoting
%2
Cis_author
%2
Cis_thanked
%2
Cis_nothelp
%2
Cis_recognized
%3
Bdata
%5
B*
%5
D.author.badge
%5
B
%3
F(type
%3
Dbest_answerer)
%5
D.topics
%3
Bdata
%5
B*
%5
D.question.has_publishing_draft
%2
Crelationship&offset={0}&limit=20&sort_by=created'
detail_url
=
'/answers?include=data
%5
B*
%5
D.is_normal
%2
Cadmin_closed_comment
%2
Creward_info
%2
Cis_collapsed
%2
Cannotation_action
%2
Cannotation_detail
%2
Ccollapse_reason
%2
Ccollapsed_by
%2
Csuggest_edit
%2
Ccomment_count
%2
Ccan_comment
%2
Ccontent
%2
Ceditable_content
%2
Cattachment
%2
Cvoteup_count
%2
Creshipment_settings
%2
Ccomment_permission
%2
Cmark_infos
%2
Ccreated_time
%2
Cupdated_time
%2
Creview_info
%2
Cexcerpt
%2
Cis_labeled
%2
Clabel_info
%2
Crelationship.is_authorized
%2
Cvoting
%2
Cis_author
%2
Cis_thanked
%2
Cis_nothelp
%2
Cis_recognized
%3
Bdata
%5
B*
%5
D.author.badge
%5
B
%3
F(type
%3
Dbest_answerer)
%5
D.topics
%3
Bdata
%5
B*
%5
D.question.has_publishing_draft
%2
Crelationship&offset=20&limit=20&sort_by=created'
self
.
ANSWER_URL
=
self
.
spider_url
.
replace
(
"https://www.zhihu.com/people"
,
"https://www.zhihu.com/api/v4/members"
)
+
detail_url
os
.
environ
[
"EXECJS_RUNTIME"
]
=
'Node'
try
:
...
...
@@ -86,6 +78,7 @@ class Spider(object):
with
open
(
JS_FILE_PATH
,
'r'
,
encoding
=
'utf-8'
)
as
f
:
js
=
f
.
read
()
self
.
exec_js
=
execjs
.
compile
(
js
)
# self.exec_js = execjs.compile(js, cwd='/home/gmuser/node_modules')
def
get_serach_page_cookies
(
self
):
'''
...
...
@@ -97,7 +90,7 @@ class Spider(object):
"accept-encoding"
:
"gzip, deflate, br"
,
"accept-language"
:
"zh-CN,zh;q=0.9"
,
"cache-control"
:
"max-age=0"
,
"cookie"
:
'_
SESSIONID=rvJz2mbRjCqJFwvD79ADGb8gpdpRkWXAsdVDqOVALgh; JOID=UVkSBEtHLEUgV_KGUUMd3fULiLJHZglmBHfTo3JnDWADc9KndNqP8XtW9oBWoLo5jsAnAcPG0-JwbPp8rD1JsFI=; osd=W1gdB05NLUojUviHXkAY1_QEi7dNZwZlAX3SrHFiB2EMcNetddWM9HFX-YNTqrs2jcUtAMzF1uhxY_l5pjxGs1c=; _zap=cc1330a6-d6e9-4b25-8232-0b0481e37ea2; _xsrf=4798d610-1db7-489f-8c14-d608c0bbcf08; d_c0="AOCcdS0CNBKPToRkxgVd-8qBKKgTDM9yF4Y=|1605507877"; capsion_ticket="2|1:0|10:1605684439|14:capsion_ticket|44:MzdiN2JlOTZlNWE2NGU5Zjg0MDNiODFlN2ViMjQzNGU=|b84d77e03b5e9447a3740a614d208ca5f3bc1e4fe15fe9b46f1a2a5702da5f99"; SESSIONID=nplCMucg2EXp8xNQAz74jmaLovUS9CG4rVtcFY4jWLT; JOID=V1sUBk8zRBeITtMgLDNzj10QrRI6WzZ_ygKgQU8AB038d6pof-COptdJ1yYpGa7oR9-1bgHql0Hfs4FvUF_YW-A=; osd=Ul4XBkI2QRSIQ9YlLzN-ilgTrR8_XjV_xwelQk8NAkj_d6dteuOOq9JM1CYkHKvrR9KwawLqmkTasIFiVVrbW-0=; Hm_lvt_98beee57fd2ef70ccdd5ca52b9740c49=1605608394,1605684435,1605684439,1605684455; Hm_lpvt_98beee57fd2ef70ccdd5ca52b9740c49=1605684522; KLBRSID=fe0fceb358d671fa6cc33898c8c48b48|1605685245|1605683234
'
,
"cookie"
:
'_
xsrf=vTWamiEoaOQszAl6fjdlxOtqyhDvOen9; d_c0="AADj9V7Fuw6PTkTnxjUXHGA8UqXz_bkbAN4=|1545899265"; q_c1=3e9e37a46b1d4bfd87f7d1fcb084daad|1545899267000|1545899267000; _ga=GA1.2.929033900.1582626815; capsion_ticket="2|1:0|10:1608602928|14:capsion_ticket|44:MmRhNDdmYWJhZjU3NGQ4ODg3NDAzNGIwNDNiMTdlNDE=|7924fa0d0e36d3ed2a4af65dafa4684c9b36a70d586ec3adb1963c8df5f55e81"; _zap=6fd2d768-daa1-4be1-9a96-43d86c1bbc75; Hm_lvt_98beee57fd2ef70ccdd5ca52b9740c49=1609321344,1609321689,1609321744,1609322777; Hm_lpvt_98beee57fd2ef70ccdd5ca52b9740c49=1609322777; KLBRSID=d017ffedd50a8c265f0e648afe355952|1609323283|1609315999
'
,
"referer"
:
self
.
spider_url
,
"sec-fetch-dest"
:
"document"
,
"sec-fetch-mode"
:
"navigate"
,
...
...
@@ -113,7 +106,7 @@ class Spider(object):
'''
数据插入前检测
'''
sql
=
"select id from {table} where id = {id_}"
sql
=
"select id from {table} where
answer_
id = {id_}"
exist
=
None
if
mark
==
0
:
select_sql
=
sql
.
format
(
table
=
'zhihu_answer'
,
id_
=
data_dict
[
"id"
])
...
...
@@ -188,7 +181,8 @@ class Spider(object):
self
.
search_thought_page
(
offset
)
offset
=
offset
+
20
time
.
sleep
(
10
)
self
.
conn
.
close
()
return
...
...
@@ -208,7 +202,7 @@ class Spider(object):
# retry once
get_page
=
requests
.
get
(
url
)
if
get_page
.
status_code
!=
200
:
print
(
"article_error
"
)
print
(
"article_error
, url : "
,
url
,
" status_code: "
,
get_page
.
status_code
)
page_dict
=
get_page
.
json
()
if
page_dict
.
get
(
"data"
):
for
one_line
in
page_dict
[
'data'
]:
...
...
@@ -221,7 +215,7 @@ class Spider(object):
# The search api just return something seems related to search
continue
else
:
print
(
"article_data_error
"
)
print
(
"article_data_error
, offset: "
,
offset
,
" url: "
,
url
)
return
...
...
@@ -357,7 +351,7 @@ class Spider(object):
}
cookies_dict
=
{
"d_c0"
:
'"A
OCcdS0CNBKPToRkxgVd-8qBKKgTDM9yF4Y=|1605507877
"'
,
"d_c0"
:
'"A
ADj9V7Fuw6PTkTnxjUXHGA8UqXz_bkbAN4=|1545899265
"'
,
"KLBRSID"
:
None
}
...
...
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