mirror of
https://github.com/crawlab-team/crawlab.git
synced 2026-01-26 17:49:15 +01:00
更新可配置爬虫,修复一些问题
This commit is contained in:
@@ -1,5 +1,6 @@
|
||||
version: 0.4.0
|
||||
start_url: "https://baidu.com/s?wd=crawlab"
|
||||
start_stage: "stage_4"
|
||||
engine: "scrapy"
|
||||
stages:
|
||||
stage_1:
|
||||
@@ -14,6 +15,7 @@ stages:
|
||||
attr: "href"
|
||||
next_stage: "stage_2"
|
||||
stage_2:
|
||||
list: false
|
||||
is_list: false
|
||||
fields:
|
||||
- name: ""
|
||||
- name: "stage_2_field_1"
|
||||
css: "a"
|
||||
|
||||
@@ -9,5 +9,4 @@ import scrapy
|
||||
|
||||
|
||||
class Item(scrapy.Item):
|
||||
###ITEMS###
|
||||
pass
|
||||
###ITEMS###
|
||||
|
||||
Reference in New Issue
Block a user