mirror of
https://github.com/crawlab-team/crawlab.git
synced 2026-01-27 17:50:53 +01:00
58 lines
1.1 KiB
Plaintext
58 lines
1.1 KiB
Plaintext
name: "douban_config"
|
|
display_name: "豆瓣读书(可配置)"
|
|
remark: "豆瓣读书新书推荐,列表"
|
|
type: "configurable"
|
|
col: "results_douban_config"
|
|
engine: scrapy
|
|
start_url: https://book.douban.com/latest
|
|
start_stage: list
|
|
stages:
|
|
- name: list
|
|
is_list: true
|
|
list_css: ul.cover-col-4 > li
|
|
list_xpath: ""
|
|
page_css: ""
|
|
page_xpath: ""
|
|
page_attr: ""
|
|
fields:
|
|
- name: title
|
|
css: h2 > a
|
|
xpath: ""
|
|
attr: ""
|
|
next_stage: ""
|
|
remark: ""
|
|
- name: url
|
|
css: h2 > a
|
|
xpath: ""
|
|
attr: href
|
|
next_stage: ""
|
|
remark: ""
|
|
- name: img
|
|
css: a.cover img
|
|
xpath: ""
|
|
attr: src
|
|
next_stage: ""
|
|
remark: ""
|
|
- name: rating
|
|
css: p.rating > .color-lightgray
|
|
xpath: ""
|
|
attr: ""
|
|
next_stage: ""
|
|
remark: ""
|
|
- name: abstract
|
|
css: p:last-child
|
|
xpath: ""
|
|
attr: ""
|
|
next_stage: ""
|
|
remark: ""
|
|
- name: info
|
|
css: .color-gray
|
|
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
|