Files
crawlab/spiders/amazon_config/Spiderfile
2020-02-03 09:21:41 +08:00

52 lines
1.2 KiB
Plaintext

name: "amazon_config"
display_name: "亚马逊中国(可配置)"
remark: "亚马逊中国搜索手机,列表+分页"
type: "configurable"
col: "results_amazon_config"
engine: scrapy
start_url: https://www.amazon.cn/s?k=%E6%89%8B%E6%9C%BA&__mk_zh_CN=%E4%BA%9A%E9%A9%AC%E9%80%8A%E7%BD%91%E7%AB%99&ref=nb_sb_noss_2
start_stage: list
stages:
- name: list
is_list: true
list_css: .s-result-item
list_xpath: ""
page_css: .a-last > a
page_xpath: ""
page_attr: href
fields:
- name: title
css: span.a-text-normal
xpath: ""
attr: ""
next_stage: ""
remark: ""
- name: url
css: .a-link-normal
xpath: ""
attr: href
next_stage: ""
remark: ""
- name: price
css: ""
xpath: .//*[@class="a-price-whole"]
attr: ""
next_stage: ""
remark: ""
- name: price_fraction
css: ""
xpath: .//*[@class="a-price-fraction"]
attr: ""
next_stage: ""
remark: ""
- name: img
css: .s-image-square-aspect > img
xpath: ""
attr: src
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