python爬虫抓取微博数据_[Python爬虫] 之四：Selenium 抓取微博数据

抓取代码：

# coding=utf-8

import os

import re

from selenium import webdriver

import selenium.webdriver.support.ui as ui

from selenium.webdriver.common.keys import Keys

import time

from selenium.webdriver.common.action_chains import ActionChains

import IniFile

class weibo:

def __init__(self):

#通过配置文件获取IEDriverServer.exe路径

configfile = os.path.join(os.getcwd(),‘config.conf‘)

cf = IniFile.ConfigFile(configfile)

IEDriverServer = cf.GetValue("section", "IEDriverServer")

#每抓取一页数据延迟的时间，单位为秒，默认为5秒

self.pageDelay = 5

pageInteralDelay = cf.GetValue("section", "pageInteralDelay")

if pageInteralDelay:

self.pageDelay = int(pageInteralDelay)

os.environ["webdriver.ie.driver"] = IEDriverServer

self.driver = webdriver.Ie(IEDriverServer)

def printTop(self,topic):

items = topic.split(‘@‘)

ht = items[0].replace(‘\n‘, ‘‘)

print ‘话题： %s‘ % ht

its = items[1].split(‘ñ‘)

author_time_nums = items[1].split(‘ñ‘)

author_time = author_time_nums[0]

nums = author_time_nums[1] #今天 00:14

pattern1 = re.compile(r‘今天\s{1}\d{2}:\d{2}|\d{1,2}月\d{1,2}日\s{1}\d{2}:\d{2}‘)

time1 = re.findall(pattern1, author_time)

print ‘话题作者： @%s‘ % author_time.split(‘ ‘)[0]

print ‘时间： %s‘ % time1[0]

print ‘点赞： %s‘ % nums.split(‘ ‘)[0]

print ‘评论： %s‘ % nums.split(‘ ‘)[1]

print ‘转发： %s‘ % nums.split(‘ ‘)[2]

print ‘ ‘

def CatchData(self,classname,firstUrl):

‘‘‘

抓取数据

:param id: 要获取元素标签的ID

:param firstUrl: 首页Url

:return:

‘‘‘

start = time.clock()

#加载首页

wait = ui.WebDriverWait(self.driver, 10)

self.driver.get(firstUrl)

#打印标题

print self.driver.title

time.sleep(20)

wait.until(lambda driver: self.driver.find_elements_by_xpath(classname))

Elements = self.driver.find_elements_by_xpath(classname)

for element in Elements:

print ‘ ‘

txt = element.text.encode(‘utf8‘)

self.printTop(txt)

self.driver.close()

self.driver.quit()

end = time.clock()

print ‘ ‘

print "整个过程用时间: %f 秒" % (end - start)

# #测试抓取微博数据

obj = weibo()

firstUrl = "http://weibo.com/?category=0"

obj.CatchData("//li[@class=‘pt_li pt_li_1 S_bg2‘]",firstUrl)