mirror of
https://github.com/crawlab-team/crawlab.git
synced 2026-01-24 17:41:03 +01:00
58 lines
1.2 KiB
Plaintext
58 lines
1.2 KiB
Plaintext
name: "autohome_config"
|
|
display_name: "汽车之家(可配置)"
|
|
remark: "汽车之家文章,列表+详情+分页"
|
|
type: "configurable"
|
|
col: "results_autohome_config"
|
|
engine: scrapy
|
|
start_url: https://www.autohome.com.cn/all/
|
|
start_stage: list
|
|
stages:
|
|
- name: list
|
|
is_list: true
|
|
list_css: ul.article > li
|
|
list_xpath: ""
|
|
page_css: a.page-item-next
|
|
page_xpath: ""
|
|
page_attr: href
|
|
fields:
|
|
- name: title
|
|
css: li > a > h3
|
|
xpath: ""
|
|
attr: ""
|
|
next_stage: ""
|
|
remark: ""
|
|
- name: url
|
|
css: li > a
|
|
xpath: ""
|
|
attr: href
|
|
next_stage: ""
|
|
remark: ""
|
|
- name: abstract
|
|
css: li > a > p
|
|
xpath: ""
|
|
attr: ""
|
|
next_stage: ""
|
|
remark: ""
|
|
- name: time
|
|
css: li > a .fn-left
|
|
xpath: ""
|
|
attr: ""
|
|
next_stage: ""
|
|
remark: ""
|
|
- name: views
|
|
css: li > a .fn-right > em:first-child
|
|
xpath: ""
|
|
attr: ""
|
|
next_stage: ""
|
|
remark: ""
|
|
- name: comments
|
|
css: li > a .fn-right > em:last-child
|
|
xpath: ""
|
|
attr: ""
|
|
next_stage: ""
|
|
remark: ""
|
|
settings:
|
|
ROBOTSTXT_OBEY: "false"
|
|
USER_AGENT: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML,
|
|
like Gecko) Chrome/78.0.3904.108 Safari/537.36
|