python爬虫selenium和phantomJs使用方法解析

pip install selenium

#使用下面的方法，查找指定的元素进行操作即可
find_element_by_id 根据id找节点
find_elements_by_name 根据name找
find_elements_by_xpath 根据xpath查找
find_elements_by_tag_name 根据标签名找
find_elements_by_class_name 根据class名字查找
# 通过id定位:
dr.find_element_by_id("kw")

# 通过name定位:
dr.find_element_by_name("wd")

# 通过class name定位:
dr.find_element_by_class_name("s_ipt")

# 通过tag name定位:
dr.find_element_by_tag_name("input")

# 通过xpath定位，xpath定位有N种写法，这里列几个常用写法:
dr.find_element_by_xpath("//*[@id='kw']")
dr.find_element_by_xpath("//*[@name='wd']")
dr.find_element_by_xpath("//input[@class='s_ipt']")
dr.find_element_by_xpath("/html/body/form/span/input")
dr.find_element_by_xpath("//span[@class='soutu-btn']/input")
dr.find_element_by_xpath("//form[@id='form']/span/input")
dr.find_element_by_xpath("//input[@id='kw' and @name='wd']")

# 通过css定位，css定位有N种写法，这里列几个常用写法:
dr.find_element_by_css_selector("#kw")
dr.find_element_by_css_selector("[name=wd]")
dr.find_element_by_css_selector(".s_ipt")
dr.find_element_by_css_selector("html > body > form > span > input")
dr.find_element_by_css_selector("span.soutu-btn> input#kw")
dr.find_element_by_css_selector("form#form > span > input")

<a class="mnav" href="http://news.baidu.com" rel="external nofollow" name="tj_trnews">新闻</a>
<a class="mnav" href="http://www.hao123.com" rel="external nofollow" name="tj_trhao123">hao123</a>

# 通过link text定位:
dr.find_element_by_link_text("新闻")
dr.find_element_by_link_text("hao123")

# 通过partial link text定位:
dr.find_element_by_partial_link_text("新")
dr.find_element_by_partial_link_text("hao")
dr.find_element_by_partial_link_text("123")

from selenium import webdriver
from time import sleep
# 创建浏览器对象 驱动为浏览器的路径
bro = webdriver.Chrome("./chromedriver.exe")
url = "https://www.baidu.com"7 # 发送请求
bro.get(url)
# 让百度指定词条的搜索
text = bro.find_element_by_id('kw')
# 发送关键字
text.send_keys('python')
# 点击搜索按钮
button = bro.find_element_by_id('su')
button.click()
# 关闭浏览器
bro.quit()

from selenium import webdriver
from time import sleep
bro = webdriver.PhantomJS('E:/BaiduNetdiskDownload/爬虫课件/5. 动态数据加载
爬取\phantomjs‐2.1.1‐windows/bin/phantomjs.exe')
url = "https://www.baidu.com"
# 发送请求
bro.get(url)
bro.save_screenshot('./1.png')
# 让百度指定词条的搜索
text = bro.find_element_by_id('kw')
# 发送关键字
text.send_keys('python')
bro.save_screenshot('./2.png')
# 点击搜索按钮
button = bro.find_element_by_id('su')
button.click()
sleep(3)
bro.save_screenshot('./3.png')
# 关闭浏览器
bro.quit()

from selenium import webdriver
from time import sleep3 url = 'https://movie.douban.com/typerank?type_name=%E5%96%9C%E5%89%A7&typ
e=24&interval_id=100:90&action='
bro = webdriver.PhantomJS('E:/BaiduNetdiskDownload/爬虫课件/5. 动态数据加载
爬取\phantomjs‐2.1.1‐windows/bin/phantomjs.exe')
bro.get(url)
sleep(1)
bro.save_screenshot("./1.png")
js = 'window.scrollTo(0,document.body.scrollHeight)'
# 执行js代码 滚动条
bro.execute_script(js)
sleep(1)
bro.save_screenshot('./2.png')
# 获取页面数据
page_source = bro.page_source
print(page_source)