def insertArticleSampleText(articleSampleText):
try:
conToMysql()
cur.execute('CREATE DATABASE IF NOT EXISTS autohome')
conn.select_db('autohome')
cur.execute(
'CREATE TABLE IF NOT EXISTS autohome_sample_text('
'article_url VARCHAR(100) PRIMARY KEY COMMENT"文章的url",'
'article_cover_url VARCHAR(200) COMMENT"文章封面url",'
'article_title VARCHAR(100) COMMENT"文章标题",'
'article_viewer_num VARCHAR(20) COMMENT"查看文章人数",'
'article_short_text VARCHAR(500) COMMENT"文章简略信息",'
'insert_time DATETIME COMMENT"插入时间",'
'change_time TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP COMMENT"更新时间"'
')COMMENT"文章简述"')
cur.execute(
'INSERT INTO autohome_sample_text VALUES('
'%s,%s,%s,%s,%s,CURRENT_TIMESTAMP,CURRENT_TIMESTAMP)',
articleSampleText)
closeMysql()
except MySQLdb.Error, e:
writeLog.writeErrorLog(
'fail optMysqldb insertArticleSampleText Mysql Error %d: %s' %
(e.args[0], e.args[1]), 'autohome') #写入总日志文件
writeLog.writeErrorLog(
'fail optMysqldb insertArticleSampleText Mysql Error %d: %s' %
(e.args[0], e.args[1]), 'autohome_error') #写入错误日志文
def insertPageUrl(pageUrl):
try:
conToMysql()
#---创建autohome 创建表结构---#
#使用execute方法执行SQL语句
cur.execute('CREATE DATABASE IF NOT EXISTS autohome')
conn.select_db('autohome')
cur.execute(
'CREATE TABLE IF NOT EXISTS autohome_page_url('
'page_url VARCHAR(100) PRIMARY KEY COMMENT"汽车之家页面url",'
'insert_time DATETIME COMMENT"插入时间",'
'change_time TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP COMMENT"更新时间"'
')COMMENT"页面url"')
cur.execute(
'INSERT INTO autohome_page_url VALUES(%s,CURRENT_TIMESTAMP,CURRENT_TIMESTAMP)',
pageUrl)
closeMysql()
except MySQLdb.Error, e:
writeLog.writeErrorLog(
'fail optMysqldb insertPageUrl Mysql Error %d: %s' %
(e.args[0], e.args[1]), 'autohome') #写入总日志文件
writeLog.writeErrorLog(
'fail optMysqldb insertPageUrl Mysql Error %d: %s' %
(e.args[0], e.args[1]), 'autohome_error') #写入错误日志文
def getSoupFromUrl(url):
params = {
'Accept': '*/*',
'Accept-Encoding': 'gzip, deflate, sdch',
'Accept-Language': 'zh-CN,zh;q=0.8',
'Cache-Control': 'no-cache',
'Connection': 'keep-alive',
'Host': 'www.autohome.com.cn',
'Pragma': 'no-cache',
'User-Agent': changeUA.getUA()
}
try:
m_str_content = requests.get(url, params=params, timeout=30).content
m_soup = BeautifulSoup(m_str_content, "html5lib")
#判断正文是否有翻页，并解决
if (m_soup.find(name='div', attrs={'class': 'page'})):
#正则表达式解决方案
if (re.search('-', url)): #判断是否有'-'，有是第一页，没有不是第一页
m_str_url = re.sub('-.*\.', '-all.', url) #有的替换方式
else:
m_str_url = re.sub('\.html', '-all.html', url) #没有的替换方式
m_str_content = requests.get(m_str_url, params=params,
timeout=30).content
m_soup = BeautifulSoup(m_str_content, "html5lib")
return m_soup
except Exception, e:
writeLog.writeErrorLog(
'fail detailText getSoupFromUrl %s : %s' % (Exception, e),
'autohome')
writeLog.writeErrorLog(
'fail detailText getSoupFromUrl %s : %s' % (Exception, e),
'autohome_error')
def dropDatabase(databaseName):
try:
conToMysql()
cur.execute('DROP DATABASE IF EXISTS autohome')
closeMysql()
except MySQLdb.Error, e:
writeLog.writeErrorLog(
'fail optMysqldb dropDatabase Mysql Error %d: %s' %
(e.args[0], e.args[1]), 'autohome') #写入总日志文件
writeLog.writeErrorLog(
'fail optMysqldb dropDatabase Mysql Error %d: %s' %
(e.args[0], e.args[1]), 'autohome_error') #写入错误日志文
def closeMysql():
try:
conn.commit() #提交事务
cur.close() #关闭游标
conn.close() #关闭连接
except MySQLdb.Error, e:
writeLog.writeErrorLog(
'fail optMysqldb closeMysql Mysql Error %d: %s' %
(e.args[0], e.args[1]), 'autohome') #写入总日志文件
writeLog.writeErrorLog(
'fail optMysqldb closeMysql Mysql Error %d: %s' %
(e.args[0], e.args[1]), 'autohome_error') #写入错误日志文
def getArticleUrl(database, table, field):
try:
m_ay_fieldValue = []
#自定义库conToMysql
m_tup_fieldValue = optMysqldb.getValues(database, table, field)
for m_str_eachValue in m_tup_fieldValue:
m_ay_fieldValue.append(m_str_eachValue[0])
return m_ay_fieldValue
except Exception, e:
writeLog.writeErrorLog(
'fail detailText getArticleUrl %s : %s' % (Exception, e),
'autohome')
writeLog.writeErrorLog(
'fail detailText getArticleUrl %s : %s' % (Exception, e),
'autohome_error')
def getValues(database, table, field):
try:
conToMysql()
conn.select_db(database)
#生成mysql语句
m_str_selectSql = 'SELECT %s FROM %s' % (field, table)
m_str_allValue = cur.execute(m_str_selectSql)
m_str_getAllVal = cur.fetchmany(m_str_allValue)
closeMysql()
return m_str_getAllVal
except MySQLdb.Error, e:
writeLog.writeErrorLog('fail optMysqldb getValues Mysql Error %d: %s' %
(e.args[0], e.args[1]), 'autohome') #写入总日志文件
writeLog.writeErrorLog('fail optMysqldb getValues Mysql Error %d: %s' %
(e.args[0], e.args[1]),
'autohome_error') #写入错误日志文
def conToMysql():
try:
#打开数据库连接
global conn
conn = MySQLdb.connect(host='localhost',
user='******',
passwd='mysql',
port=3306,
use_unicode=True,
charset='utf8')
#使用cursor()方法获取操作游标
global cur
cur = conn.cursor()
except MySQLdb.Error, e:
writeLog.writeErrorLog(
'fail optMysqldb conToMysql Mysql Error %d: %s' %
(e.args[0], e.args[1]), 'autohome') #写入总日志文件
writeLog.writeErrorLog(
'fail optMysqldb conToMysql Mysql Error %d: %s' %
(e.args[0], e.args[1]), 'autohome_error') #写入错误日志文
def insertCommentDetail(commentDetail):
try:
conToMysql()
cur.execute('CREATE DATABASE IF NOT EXISTS autohome')
conn.select_db('autohome')
cur.execute(
'CREATE TABLE IF NOT EXISTS autohome_comment_detail('
'article_url VARCHAR(100) COMMENT"评论文章的url",'
'article_title VARCHAR(55) COMMENT"评论文章的标题",'
'reply_id VARCHAR(20) PRIMARY KEY COMMENT"该评论在汽车之家的sk",'
'repler_homePage VARCHAR(45) COMMENT"评论者的个人主页",'
'repler_logo VARCHAR(150) COMMENT"评论者的头像",'
'repler_name VARCHAR(35) COMMENT"评论者的名字",'
'repler_device VARCHAR(30) COMMENT"评论者所用的设备",'
'reply_timeAndFloor VARCHAR(55) COMMENT"评论时间和楼层",'
'reply_content TEXT COMMENT"评论发布内容",'
'reply_like VARCHAR(20) COMMENT"该评论获得的赞",'
'preRepler_logo VARCHAR(150) COMMENT"原评论者的头像",'
'preRepler_homePage VARCHAR(45) COMMENT"原评论者的个人主页",'
'preRepler_name VARCHAR(35) COMMENT"原评论者的名字",'
'preReply_date VARCHAR(25) COMMENT"原评论的日期",'
'preReply_floor VARCHAR(15) COMMENT"原评论的楼层",'
'preReply_content TEXT COMMENT"原评论的内容",'
'insert_time DATETIME COMMENT"插入时间",'
'change_time TIMESTAMP DEFAULT CURRENT_TIMESTAMP COMMENT"更新时间"'
')COMMENT"评论页面表"')
cur.execute(
'INSERT INTO autohome_comment_detail VALUES('
'%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,CURRENT_TIMESTAMP,CURRENT_TIMESTAMP)',
commentDetail)
closeMysql()
except MySQLdb.Error, e:
writeLog.writeErrorLog(
'fail optMysqldb insertCommentDetail Mysql Error %d: %s' %
(e.args[0], e.args[1]), 'autohome') #写入总日志文件
writeLog.writeErrorLog(
'fail optMysqldb insertCommentDetail Mysql Error %d: %s' %
(e.args[0], e.args[1]), 'autohome_error') #写入错误日志文
def insertArticleDetailText(articleDetailText):
try:
conToMysql()
cur.execute('CREATE DATABASE IF NOT EXISTS autohome')
conn.select_db('autohome')
cur.execute(
'CREATE TABLE IF NOT EXISTS autohome_detail_text('
'article_url VARCHAR(100) PRIMARY KEY COMMENT"文章url",'
'article_classify VARCHAR(30) COMMENT"文章分类",'
'article_carClassify VARCHAR(40) COMMENT"文章描述的汽车分类",'
'article_title VARCHAR(55) COMMENT"文章标题",'
'article_pubTime VARCHAR(25) COMMENT"发布时间",'
'article_pubSrcsys VARCHAR(20) COMMENT"发布系统",'
'article_pubType VARCHAR(15) COMMENT"发布类型",'
'article_pubAuthor VARCHAR(10) COMMENT"文章作者",'
'article_detailText MEDIUMTEXT COMMENT"正文",'
'article_commentPage VARCHAR(100) COMMENT"评论页面url",'
'article_picUrlList MEDIUMTEXT COMMENT"文章图片列表",'
'insert_time DATETIME COMMENT"插入时间",'
'change_time TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP COMMENT"更新时间"'
')COMMENT"文章详情表"')
cur.execute(
'INSERT INTO autohome_detail_text VALUES('
'%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,CURRENT_TIMESTAMP,CURRENT_TIMESTAMP)',
articleDetailText)
closeMysql()
except MySQLdb.Error, e:
writeLog.writeErrorLog(
'fail optMysqldb insertArticleDetailText Mysql Error %d: %s' %
(e.args[0], e.args[1]), 'autohome') #写入总日志文件
writeLog.writeErrorLog(
'fail optMysqldb insertArticleDetailText Mysql Error %d: %s' %
(e.args[0], e.args[1]), 'autohome_error') #写入错误日志文
def getCommentPage(firstPageUrl, soup):
try:
#存放评论页面
m_queue_commentPage = Queue.Queue(maxsize=-1)
m_url_nextPage = firstPageUrl
while True:
m_queue_commentPage.put(m_url_nextPage) #进队
#获得下一页连接
m_url_nextPage = soup.find(name='div',
attrs={
'class': 'page page-small'
}).find(name='a',
attrs={
'class': 'current'
}).next_sibling['href']
soup = getSoupFromUrl(m_url_nextPage) #解析url
#判断是否到达评论最后一页
if (soup.find(name='div', attrs={
'class': 'page page-small'
}).find(name='a', attrs={
'class': 'current'
}).next_sibling['href'] == 'javascript:void(0);'):
m_queue_commentPage.put(m_url_nextPage) #最后一页进队
break
print 'succeed to get comment page ' + firstPageUrl
return m_queue_commentPage
except Exception, e:
print 'fail to get comment page ' + firstPageUrl + ' [%s,%s]' % (
Exception, e)
writeLog.writeErrorLog('fail commentDetail getCommentPage %s : %s' %
(Exception, e), 'autohome') #写入总日志文件
writeLog.writeErrorLog('fail commentDetail getCommentPage %s : %s' %
(Exception, e), 'autohome_error') #写入错误日志文件
return 0
def getUrlAndShort():
#---变量声明---#
s_n_isloop = 0 #0循环 1退出
m_str_tempPage = '/all/2/#liststart' #开始页面
#===获取autohome所有页面链接 文章简介===#
#---所有页面链接 m_str_tempUrlList---#
#---所有文章简介 m_str_articleSampleText---#
#删除已存在的数据库
optMysqldb.dropDatabase('autohome')
while (s_n_isloop == 0):
try:
#拼接网页连接 放进数组
m_str_tempPageUrl = "http://www.autohome.com.cn%s" % m_str_tempPage
#---m_str_tempUrlList导入Mysql的autohome_page_url表---#
optMysqldb.insertPageUrl(m_str_tempPageUrl)
writeLog.writerNormalLog(
'succeed get page url %s' % m_str_tempPageUrl, 'autohome')
#获取网页源代码 用bs4解析
params = {
'Accept': '*/*',
'Accept-Encoding': 'gzip, deflate, sdch',
'Accept-Language': 'zh-CN,zh;q=0.8',
'Cache-Control': 'no-cache',
'Connection': 'keep-alive',
'Host': 'www.autohome.com.cn',
'Pragma': 'no-cache',
'User-Agent': changeUA.getUA()
}
m_str_tempContent = requests.get(m_str_tempPageUrl,
params=params,
timeout=30).content
m_str_tempSoup = BeautifulSoup(m_str_tempContent, "html5lib")
#获取下一个页面的连接 用bs4的下一个兄弟节点的方法
m_str_tempPage = m_str_tempSoup.find(
name='div', attrs={
'id': 'channelPage'
}).find(name='a', attrs='current').next_sibling['href']
#获取文章的标题等信息（简略）
m_str_articleHtml = m_str_tempSoup.find(
id="auto-channel-lazyload-article").find_all(name='li')
for m_n_rankOfList in range(len(m_str_articleHtml)):
m_str_part_1 = m_str_articleHtml[m_n_rankOfList].a[
"href"] #文章连接 article_url
m_str_part_2 = m_str_articleHtml[m_n_rankOfList].div.img[
"src"].strip() #图片地址 article_cover_url
m_str_part_3 = m_str_articleHtml[
m_n_rankOfList].h3.string #文章标题 article_title
m_str_part_4 = m_str_articleHtml[m_n_rankOfList].em.contents[
1].strip() #阅读数 article_viewer
m_str_part_5 = m_str_articleHtml[
m_n_rankOfList].p.string #文章征文部分
m_str_articleSampleText = (m_str_part_1, m_str_part_2,
m_str_part_3, m_str_part_4,
m_str_part_5)
#---m_str_articleSampleText导入Mysql的autohome_sample_text表---#
optMysqldb.insertArticleSampleText(m_str_articleSampleText)
writeLog.writerNormalLog(
'succeed get article%s,%s' % (m_str_part_1, m_str_part_3),
'autohome')
except Exception, e:
s_n_isloop = 1
writeLog.writeErrorLog(
'fail allUrlAndShort getUrlAndShort %s : %s' % (Exception, e),
'autohome') #写入总日志文件
writeLog.writeErrorLog(
'fail allUrlAndShort getUrlAndShort %s : %s' % (Exception, e),
'autohome_error') #写入错误日志文件
import optMysqldb
#===设置全局UTF-8格式===#
reload(sys)
sys.setdefaultencoding( "utf-8" )
try:
#===获取autohome所有url和简介===#
allUrlAndShort.getUrlAndShort()
#===获取autohome文章的详细信息===#
m_list_articleUrl = detailText.getArticleUrl('autohome','autohome_sample_text','article_url')
for str_eachArticleUrl in m_list_articleUrl:
m_str_soup = detailText.getSoupFromUrl(str_eachArticleUrl)
m_str_detailText = detailText.getArticleDetail(str_eachArticleUrl, m_str_soup)
optMysqldb.insertArticleDetailText(m_str_detailText)
#===获取autohome评论详情===#
m_list_articleCommentPage = commentDetail.getArticleUrl('autohome','autohome_detail_text','article_commentPage')
for m_str_articleCommentPage in m_list_articleCommentPage:
try:
m_str_soup = commentDetail.getSoupFromUrl(m_str_articleCommentPage)
m_queue_commentPage = commentDetail.getCommentPage(m_str_articleCommentPage, m_str_soup)
commentDetail.getCommentDetail(m_queue_commentPage)
except Exception,e:
writeLog.writeErrorLog('fail main %s : %s'%(Exception,e),'autohome') #写入总日志文件
writeLog.writeErrorLog('fail main %s : %s'%(Exception,e),'autohome_error') #写入错误日志文件
continue
except Exception,e:
writeLog.writeErrorLog('fail main %s : %s'%(Exception,e),'autohome') #写入总日志文件
writeLog.writeErrorLog('fail main %s : %s'%(Exception,e),'autohome_error') #写入错误日志文件
def getCommentDetail(queue):
while (queue.empty() != True):
try:
m_url_eachCommentPage = queue.get()
#解析评论页面成soup
m_soup_eachCommentPage = getSoupFromUrl(m_url_eachCommentPage)
#评论文章url
m_url_srcArticle = m_soup_eachCommentPage.find(
name='h1', attrs={
'class': 'tit_rev'
}).a['href'] #.h1.get_text(strip=True)
#评论文章标题
m_str_srcArticleTitle = m_soup_eachCommentPage.find(name='h1',
attrs={
'class':
'tit_rev'
}).a.string
#获取评论页面所有的dt标签
m_list_eachPageDt = m_soup_eachCommentPage.find(
name='dl', attrs={
'id': 'reply-list'
}).find_all(name='dt')
#获取评论页面所有的dd标签
m_list_eachPageDd = m_soup_eachCommentPage.find(
name='dl', attrs={
'id': 'reply-list'
}).find_all(name='dd')
for number in range(0, len(m_list_eachPageDt)):
#---dt模块---#
#回复者的sk
try:
m_str_skReply = m_list_eachPageDt[number].a['name']
except:
m_str_skReply = 'null'
#回复者的主页
try:
m_url_replerPage = m_list_eachPageDt[number].find(
name='a', attrs={'class': 'user-fl'})['href']
except:
m_url_replerPage = 'null'
#回复人头像
try:
m_url_replerLogo = m_list_eachPageDt[number].img['src']
except:
m_url_replerLogo = 'null'
#回复人昵称
try:
m_str_replerName = m_list_eachPageDt[number].find(
name='a', attrs={
'class': 'user-fl'
}).text
except:
m_str_replerName = 'null'
#通过什么设备回复
try:
m_str_replerDevice = m_list_eachPageDt[number].find(
name='a', attrs={
'class': 'revgrey'
}).text
except:
m_str_replerDevice = 'null'
#几分钟前，楼层数
try:
m_str_replerTimeAndFloor = m_list_eachPageDt[number].find(
name='span', attrs={
'class': 'fn-right'
}).text
except:
m_str_replerTimeAndFloor = 'null'
#---dd模块---#
#当前用户回复内容
try:
m_str_replyContent = m_list_eachPageDd[number].p.text
except:
m_str_replyContent = 'null'
# 当前用户获得赞的数量
try:
m_n_likeNum = m_list_eachPageDd[number].find(
name='div', attrs={
'class': 'text-right'
}).find(name='a', attrs={
'target': '_self'
}).text
except:
m_n_likeNum = 'null'
#--当前用户回复以往用户 以往用户的个人信息--#
#原评论部分
try:
m_str_preReplyPart = m_list_eachPageDd[number].find(
name='div', attrs={'class': 'reply'})
except:
m_str_preReplyPart = 'null'
#原评论用户头像
try:
m_url_preReplerLogo = m_str_preReplyPart.img['src']
except:
m_url_preReplerLogo = 'null'
#原评论用户主页
try:
m_url_preReplerPage = m_str_preReplyPart.find(
name='a', attrs={'class': 'grey666'})['href']
except:
m_url_preReplerPage = 'null'
#原评论用户昵称
try:
m_str_preReplerName = m_str_preReplyPart.find(name='a',
attrs={
'class':
'grey666'
}).text
except:
m_str_preReplerName = 'null'
#原评论用户回复日期
try:
m_str_preReplyDate = m_str_preReplyPart.find(
name='span', attrs={
'class': 'grey'
}, text='于').next_sibling
except:
m_str_preReplyDate = 'null'
#原评论评论所在楼数
try:
m_n_preReplyFloor = m_str_preReplyPart.find(name='span',
attrs={
'class':
'grey666'
}).text
except:
m_n_preReplyFloor = 'null'
#原评论的回复
try:
m_str_preReplyContent = m_str_preReplyPart.find(
name='p', attrs={
'class': 'reply-name'
}).next_sibling.text
except:
m_str_preReplyContent = 'null'
#---返回顺序：评论文章url,评论文章标题,回复者的sk，回复者的主页，回复人头像，回复人昵称，通过什么设备回复，几分钟前楼层数，
# 当前用户回复内容，当前用户获得赞的数量,原评论用户头像，原评论用户回复日期，原评论评论所在楼数，原评论的回复
m_str_CommentConnent = (m_url_srcArticle,
m_str_srcArticleTitle, m_str_skReply,
m_url_replerPage, m_url_replerLogo,
m_str_replerName, m_str_replerDevice,
m_str_replerTimeAndFloor,
m_str_replyContent, m_n_likeNum,
m_url_preReplerLogo,
m_url_preReplerPage,
m_str_preReplerName,
m_str_preReplyDate, m_n_preReplyFloor,
m_str_preReplyContent)
optMysqldb.insertCommentDetail(m_str_CommentConnent)
writeLog.writerNormalLog(
'succeed get comment skReplay %s' % m_str_skReply,
'autohome')
print 'succeed to get comment detail ' + m_url_eachCommentPage
except Exception, e:
print 'fail to get comment page ' + m_url_srcArticle + ' [%s,%s]' % (
Exception, e)
writeLog.writeErrorLog(
'fail commentDetail getCommentDetail %s : %s' % (Exception, e),
'autohome') #写入总日志文件
writeLog.writeErrorLog(
'fail commentDetail getCommentDetail %s : %s' % (Exception, e),
'autohome_error') #写入错误日志文件
def getArticleDetail(srcUrl, soup):
try:
global m_str_returnContent
#--附加信息--#
#文章所属分类
try:
m_str_articleClassify = soup.find(name='div',
attrs={
'class': 'breadnav fn-left'
}).get_text(strip=True)[0:-12]
except:
m_str_articleClassify = 'null'
#所属车系
try:
m_str_articleCarClassify = soup.find(name='div',
attrs={
'class':
'subnav-title-name'
}).get_text(strip=True)
except:
m_str_articleCarClassify = 'null'
#文章标题
try:
m_str_articleTitle = soup.find(name='div',
attrs={
'class': 'area article'
}).h1.get_text(strip=True)
except:
m_str_articleTitle = 'null'
#---发布详情---#
#时间
try:
m_str_articlePubInfo = [
text for text in soup.find(name='div',
attrs={
'class': 'article-info'
}).stripped_strings
]
m_str_articlePubTime = m_str_articlePubInfo[0]
except:
m_str_articlePubTime = 'null'
#来源
try:
m_str_articlePubSrcsys = m_str_articlePubInfo[2]
except:
m_str_articlePubSrcsys = 'null'
#类型
try:
m_str_articlePubType = m_str_articlePubInfo[3]
except:
m_str_articlePubType = 'null'
#作者
try:
m_str_articlePubAuthor = m_str_articlePubInfo[5]
except:
m_str_articlePubAuthor = 'null'
#---正文---#
#粗略版 要删减
try:
m_str_articleDetail = soup.find(name='div',
attrs={
'class': 'article-content'
}).get_text(strip=True)
except:
m_str_articleDetail = 'null'
#---正文的图片---#
#list以|P|为分隔符，以picStart开始，以picEnd结束
try:
target = soup.find(name='div', attrs={
'class': 'area article'
}).find_all(name='img')
m_list_pictureUrl = 'picStart'
for i in range(0, len(target)):
m_list_pictureUrl = m_list_pictureUrl + '|P|' + target[i]['src']
m_list_pictureUrl = m_list_pictureUrl + '|P|' + 'picEnd'
except:
m_list_pictureUrl = 'null'
try:
#--评论页面--#
m_str_articleCommentPage = soup.find(
name='a',
attrs={'id':
'reply-all-btn1'})['href'] #.href#.get_text(strip=True)
except:
m_str_articleCommentPage = 'null'
#--返回顺序：文章分类，文章车系，文章标题，时间，来源，类型，作者，正文，评论页面,图片字符串--#
m_str_returnContent = (srcUrl, m_str_articleClassify,
m_str_articleCarClassify, m_str_articleTitle,
m_str_articlePubTime, m_str_articlePubSrcsys,
m_str_articlePubType, m_str_articlePubAuthor,
m_str_articleDetail, m_str_articleCommentPage,
m_list_pictureUrl)
writeLog.writerNormalLog('succeed get article %s detail' % srcUrl,
'autohome')
return m_str_returnContent
except Exception, e:
writeLog.writeErrorLog(
'fail detailText getArticleDetail %s : %s' % (Exception, e),
'autohome')
writeLog.writeErrorLog(
'fail detailText getArticleDetail %s : %s' % (Exception, e),
'autohome_error')
