使用pythonSelenium爬取内容并存储MySQL数据库的实例图解

这篇文章主要介绍了python Selenium爬取内容并存储至MySQL数据库的实现代码,需要的朋友可以参考下

# coding=utf-8 
 
from selenium import webdriver 
from selenium.webdriver.common.keys import Keys 
import selenium.webdriver.support.ui as ui   
import re
import time
import os
import codecs
import MySQLdb
 
#打开Firefox浏览器 设定等待加载时间 
driver = webdriver.Firefox()
wait = ui.WebDriverWait(driver,10) 

#获取每个博主的博客页面低端总页码  
def getPage():
 print 'getPage'
 number = 0  
 texts = driver.find_element_by_xpath("//p[@id='papelist']").text  
 print '页码', texts  
 m = re.findall(r'(\w*[0-9]+)\w*',texts) #正则表达式寻找数字  
 print '页数：' + str(m[1])  
 return int(m[1]) 
 
#主函数 
def main():
 #获取txt文件总行数
 count = len(open("Blog_URL.txt",'rU').readlines())
 print count
 n = 0
 urlfile = open("Blog_URL.txt",'r')

 #循环获取每个博主的文章摘信息 
 while n < count: #这里爬取2个人博客信息，正常情况count个博主信息
  url = urlfile.readline()
  url = url.strip("\n")
  print url
  driver.get(url)
  #获取总页码
  allPage = getPage()
  print u'页码总数为:', allPage
  time.sleep(2)

  #数据库操作结合
  try:
   conn=MySQLdb.connect(host='localhost',user='root',
         passwd='123456',port=3306, db='test01')
   cur=conn.cursor() #数据库游标

   #报错:UnicodeEncodeError: 'latin-1' codec can't encode character
   conn.set_character_set('utf8')
   cur.execute('SET NAMES utf8;')
   cur.execute('SET CHARACTER SET utf8;')
   cur.execute('SET character_set_connection=utf8;')
   
   #具体内容处理
   m = 1 #第1页
   while m <= allPage:
    ur = url + "/article/list/" + str(m)
    print ur
    driver.get(ur)
    
    #标题
    article_title = driver.find_elements_by_xpath("//p[@class='article_title']")
    for title in article_title:
     #print url
     con = title.text
     con = con.strip("\n")
     #print con + '\n'
    
    #摘要
    article_description = driver.find_elements_by_xpath("//p[@class='article_description']")
    for description in article_description:
     con = description.text
     con = con.strip("\n")
     #print con + '\n'

    #信息
    article_manage = driver.find_elements_by_xpath("//p[@class='article_manage']")
    for manage in article_manage:
     con = manage.text
     con = con.strip("\n")
     #print con + '\n'

    num = 0
    print u'长度', len(article_title)
    while num < len(article_title):
     #插入数据 8个值
     sql = '''insert into csdn_blog
        (URL,Author,Artitle,Description,Manage,FBTime,YDNum,PLNum)
       values(%s, %s, %s, %s, %s, %s, %s, %s)'''
     Artitle = article_title[num].text
     Description = article_description[num].text
     Manage = article_manage[num].text
     print Artitle
     print Description
     print Manage
     #获取作者
     Author = url.split('/')[-1]
     #获取阅读数和评论数
     mode = re.compile(r'\d+\.?\d*')
     YDNum = mode.findall(Manage)[-2]
     PLNum = mode.findall(Manage)[-1]
     print YDNum
     print PLNum
     #获取发布时间
     end = Manage.find(u' 阅读')
     FBTime = Manage[:end]
     cur.execute(sql, (url, Author, Artitle, Description, Manage,FBTime,YDNum,PLNum)) 
     
     num = num + 1
    else:
     print u'数据库插入成功'    
    m = m + 1
     
  
  #异常处理
  except MySQLdb.Error,e:
   print "Mysql Error %d: %s" % (e.args[0], e.args[1])
  finally:
   cur.close() 
   conn.commit() 
   conn.close()
  
  n = n + 1
    
 else:
  urlfile.close()
  print 'Load Over'
   
main() 

#获取每个博主的博客页面低端总页码  
def getPage():
 print 'getPage'
 number = 0  
 texts = driver.find_element_by_xpath("//p[@id='papelist']").text  
 print '页码', texts  
 m = re.findall(r'(\w*[0-9]+)\w*',texts) #正则表达式寻找数字  
 print '页数：' + str(m[1])  
 return int(m[1]) 

#标题
article_title = driver.find_elements_by_xpath("//p[@class='article_title']")
for title in article_title:
 con = title.text
 con = con.strip("\n")
 print con + '\n'
    
#摘要
article_description = driver.find_elements_by_xpath("//p[@class='article_description']")
for description in article_description:
 con = description.text
 con = con.strip("\n")
 print con + '\n'

#信息
article_manage = driver.find_elements_by_xpath("//p[@class='article_manage']")
for manage in article_manage:
 con = manage.text
 con = con.strip("\n")
 print con + '\n'

num = 0
print u'长度', len(article_title)
while num < len(article_title):
 Artitle = article_title[num].text
 Description = article_description[num].text
 Manage = article_manage[num].text
 print Artitle, Description, Manage 

#获取博主姓名
url = "http://blog.csdn.net/Eastmount"
print url.split('/')[-1]
# 

输出: Eastmount #获取数字 name = "2015-09-08 18:06 阅读(909) 评论(0)" print name import re mode = re.compile(r'\d+\.?\d*') print mode.findall(name) # 输出: ['2015', '09', '08', '18', '06', '909', '0'] print mode.findall(name)[-2] # 输出: 909 #获取时间 end = name.find(r' 阅读') print name[:end] # 输出: 2015-09-08 18:06 import time, datetime a = time.strptime(name[:end],'%Y-%m-%d %H:%M') print a # 输出: time.struct_time(tm_year=2015, tm_mon=9, tm_mday=8, tm_hour=18, tm_min=6, # tm_sec=0, tm_wday=1, tm_yday=251, tm_isdst=-1)

CREATE TABLE `csdn` (
 `ID` int(11) NOT NULL AUTO_INCREMENT,
 `URL` varchar(100) COLLATE utf8_bin DEFAULT NULL,
 `Author` varchar(50) COLLATE utf8_bin DEFAULT NULL COMMENT '作者',
 `Artitle` varchar(100) COLLATE utf8_bin DEFAULT NULL COMMENT '标题',
 `Description` varchar(400) COLLATE utf8_bin DEFAULT NULL COMMENT '摘要',
 `Manage` varchar(100) COLLATE utf8_bin DEFAULT NULL COMMENT '信息',
 `FBTime` datetime DEFAULT NULL COMMENT '发布日期',
 `YDNum` int(11) DEFAULT NULL COMMENT '阅读数',
 `PLNum` int(11) DEFAULT NULL COMMENT '评论数',
 `DZNum` int(11) DEFAULT NULL COMMENT '点赞数',
 PRIMARY KEY (`ID`)
) ENGINE=InnoDB AUTO_INCREMENT=9371 DEFAULT CHARSET=utf8 COLLATE=utf8_bin; 

# coding:utf-8 
import MySQLdb
 
try:
 conn=MySQLdb.connect(host='localhost',user='root',passwd='123456',port=3306, db='test01')
 cur=conn.cursor()
 
 #插入数据
 sql = '''insert into student values(%s, %s, %s)'''
 cur.execute(sql, ('yxz','111111', '10'))

 #查看数据
 print u'\n插入数据:'
 cur.execute('select * from student')
 for data in cur.fetchall():
  print '%s %s %s' % data
 cur.close()
 conn.commit()
 conn.close()
except MySQLdb.Error,e:
  print "Mysql Error %d: %s" % (e.args[0], e.args[1]) 

#获取每个博主的博客页面低端总页码  
def getPage():
 print 'getPage'
 number = 0  
 #texts = driver.find_element_by_xpath("//p[@id='papelist']").text
 texts = driver.find_element_by_xpath("//p[@class='pagelist']").text
 print 'testsss'
 print u'页码', texts
 if texts=="":
  print u'页码为0 网站错误'
  return 0
 m = re.findall(r'(\w*[0-9]+)\w*',texts) #正则表达式寻找数字  
 print u'页数：' + str(m[1])  
 return int(m[1]) 

 error = codecs.open("Blog_Error.txt", 'a', 'utf-8')

 #循环获取每个博主的文章摘信息 
 while n < count: #这里爬取2个人博客信息，正常情况count个博主信息
  url = urlfile.readline()
  url = url.strip("\n")
  print url
  driver.get(url+"/article/list/1")
  #print driver.page_source
  #获取总页码
  allPage = getPage()
  print u'页码总数为:', allPage
  #返回错误，否则程序总截住
  if allPage==0:
   error.write(url + "\r\n")
   print u'错误URL'
   continue; #跳过进入下一个博主
  time.sleep(2)
  #数据库操作结合
  try:
    ..... 

以上就是使用python Selenium爬取内容并存储MySQL数据库的实例图解的详细内容，更多请关注Gxl网其它相关文章！

查看更多关于使用pythonSelenium爬取内容并存储MySQL数据库的实例图解的详细内容...