Selenium基于webkit实现爬虫功能

http://www.cnblogs.com/luxiaojun/p/6144748.html

https://www.cnblogs.com/chenqingyang/p/3772673.html

 

现在headless chrome替代 PhantomJS 

 

https://zhuanlan.zhihu.com/p/27100187

 

from selenium import webdriverfrom selenium.webdriver.common.desired_capabilities import DesiredCapabilitiesimport timeimport iodcap = dict(DesiredCapabilities.PHANTOMJS)  #设置userAgentdcap["phantomjs.page.settings.userAgent"] = ("Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:25.0) Gecko/20100101 Firefox/25.0 ") obj = webdriver.PhantomJS(executable_path='C:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\Scripts\phantomjs.exe',desired_capabilities=dcap) #加载网址obj.get('http://chart.icaile.com/sd11x5.php')#打开网址#time.sleep(10)pageSource = obj.page_sourceprint(pageSource)obj.quit()

　　

获取的网页内容后，可以使用beautifulsoup来分析

https://cuiqingcai.com/1319.html

 

 

直接获取表格的文本

from selenium import webdriverfrom selenium.webdriver.common.desired_capabilities import DesiredCapabilitiesimport timeimport iodcap = dict(DesiredCapabilities.PHANTOMJS)  #设置userAgent#dcap["phantomjs.page.settings.userAgent"] = ("Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:25.0) Gecko/20100101 Firefox/25.0 ") obj = webdriver.PhantomJS(executable_path='C:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\Scripts\phantomjs.exe',desired_capabilities=dcap) #加载网址obj.get('http://chart.icaile.com/sd11x5.php')#打开网址text = obj.find_element_by_id("fixedtable").textprint(text)obj.quit()

　　

 

import timeimport ioimport refrom selenium import webdriverfrom selenium.webdriver.common.desired_capabilities import DesiredCapabilitiesdcap = dict(DesiredCapabilities.PHANTOMJS)  #设置userAgentdcap["phantomjs.page.settings.userAgent"] = ("Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:25.0) Gecko/20100101 Firefox/25.0 ") obj = webdriver.PhantomJS(executable_path='C:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\Scripts\phantomjs.exe',desired_capabilities=dcap) #加载网址obj.get('http://chart.icaile.com/sd11x5.php')#打开网址text = obj.find_element_by_id("fixedtable").text#time.sleep(10)#pageSource = obj.page_source#print(pageSource)#print(text)page = obj.page_source    url_context = re.findall('href=\"(.*?)\"',page,re.S)url_list = []for url in url_context:        if 'http'in url:        print(url)obj.quit()