PhantomJS
来源:互联网 发布:淘宝如何缴纳保证金 编辑:程序博客网 时间:2024/05/22 03:47
http://blog.binux.me/2015/01/pyspider-tutorial-level-1-html-and-css-selector/
http://segmentfault.com/a/1190000002477863
#!/usr/bin/env python
# -*- encoding: utf-8 -*-
# Created on 2015-08-03 14:33:08
# Project: nimabi
from pyspider.libs.base_handler import *
class Handler(BaseHandler):
crawl_config = {
}
@every(minutes=24 * 60)
def on_start(self):
self.crawl('http://wanimal1983.tumblr.com/', callback=self.index_page)
@config(age=10 * 24 * 60 * 60)
def index_page(self, response):
for each in response.doc('a[href^="http"]').items():
self.crawl(each.attr.href, callback=self.detail_page)
def list_page(self, response):
for each in response.doc('.photoset-grid > img').items():
self.crawl(each.attr.href, callback=self.detail_page)
def detail_page(self, response):
return {
"url": response.url,
"title": response.doc('title').text(),
"rating": response.doc('.photoset-grid > img').text(),
"imgs": [x.attr.src for x in response.doc('.photoset-grid img').items()]
}
# -*- encoding: utf-8 -*-
# Created on 2015-08-03 14:33:08
# Project: nimabi
from pyspider.libs.base_handler import *
class Handler(BaseHandler):
crawl_config = {
}
@every(minutes=24 * 60)
def on_start(self):
self.crawl('http://wanimal1983.tumblr.com/', callback=self.index_page)
@config(age=10 * 24 * 60 * 60)
def index_page(self, response):
for each in response.doc('a[href^="http"]').items():
self.crawl(each.attr.href, callback=self.detail_page)
def list_page(self, response):
for each in response.doc('.photoset-grid > img').items():
self.crawl(each.attr.href, callback=self.detail_page)
def detail_page(self, response):
return {
"url": response.url,
"title": response.doc('title').text(),
"rating": response.doc('.photoset-grid > img').text(),
"imgs": [x.attr.src for x in response.doc('.photoset-grid img').items()]
}
0 0
- phantomjs
- phantomjs
- phantomjs
- PhantomJS
- PhantomJS
- phantomjs
- phantomjs
- PhantomJS
- phantomjs
- 安装phantomjs
- python phantomjs
- 推荐 phantomjs
- phantomjs note
- phantomjs 简介
- phantomjs入门教程
- 安装phantomjs
- phantomjs使用说明
- phantomjs使用说明
- uva10245
- Toast的显示需要的环境
- Android属性动画完全解析(中),ValueAnimator和ObjectAnimator的高级用法
- stdClass类转换成数组
- AndroidStudio导入sdk中的Sample工程
- PhantomJS
- 在windows下直接使用Mysql压缩包的操
- iOS字符串GBK编码转UTF-8
- MySQL慢查询开启及分析方法
- 向Android Studio里导入从Github上面下载的Project
- 去掉Xcode工程中的 某种类型的警告
- lib和dll的区别和联系
- Java中的static关键字解析
- 解决android-support-v4.jar 冲突