def getData(keyWord = '',type = ''):
targetUrl = getUrl(keyWord,type)
todayTime = datetime.date.today()
filePath = FileHelper.getPath(todayTime,'tencent',urls[keyWord])
fileName = '%s/html.txt' % filePath
FileHelper.getContent2FileWithoutProcess(fileName=fileName,targetUrl=targetUrl)
content = open(fileName,'r')
temp = content.read().decode('utf-8')
soup = BeautifulSoup(temp,'html.parser')
count = -1 #过滤第一个
Rank = 0
resultFileName=''
if type == TYPE_DAILY:
resultFileName='%s/RankDaily.txt' % filePath
if type == TYPE_WEEKLY:
resultFileName='%s/RankWeekly.txt' % filePath
if type == TYPE_MONTHLY:
resultFileName='%s/RankMonthly.txt' % filePath
for tag in soup.findAll(True):
if(tag.name == 'a' and tag.has_attr('href') and (''.join(tag['href']).find('cover') > 0)):
Rank = Rank+1
FileHelper.save2File(content = 'Rank.%s %s ' % (Rank,tag['title'] ), fileName=resultFileName,type= FileHelper.TYPE_APPEND)
if (tag.has_attr('class') and tag.name == 'strong' and ''.join(tag['class']) == 'num'):
FileHelper.save2File(content = 'VV : %s \n' % tag.string , fileName=resultFileName,type= FileHelper.TYPE_APPEND)
content.close()
FileHelper.delFile(fileName)
def getData(keyWord = '',page = -1,type = ''):
targetUrl = getUrl(keyWord,page,type)
todayTime = datetime.date.today()
filePath = FileHelper.getPath(todayTime,'youku',urls[keyWord])
fileName = '%s/html.txt' % filePath
FileHelper.getContent2FileWithoutProcess(fileName=fileName,targetUrl=targetUrl)
content = open(fileName,'r')
temp = content.read().decode('utf-8')
soup = BeautifulSoup(temp,'html.parser')
count = -1 #过滤第一个
Rank = (page-1) * 42
resultFileName=''
if type == TYPE_DAILY:
resultFileName='%s/RankDaily.txt' % filePath
if type == TYPE_WEEKLY:
resultFileName='%s/RankWeekly.txt' % filePath
for tag in soup.findAll(True):
if(tag.name == 'img' and tag.has_attr('alt') and tag.has_attr('src') and not tag.has_attr('attr')):
Rank = Rank+1
FileHelper.save2File(content = 'Rank.%s %s ' % (Rank,tag['alt'] ), fileName=resultFileName,type= FileHelper.TYPE_APPEND)
if (tag.has_attr('class') and tag.name == 'span' and ''.join(tag['class']) == 'p-num'):
FileHelper.save2File(content = 'VV : %s \n' % tag.string , fileName=resultFileName,type= FileHelper.TYPE_APPEND)
content.close()
FileHelper.delFile(fileName)
def getData(keyWord = '',type = ''):
targetUrl = getUrl(keyWord,type)
todayTime = datetime.date.today()
filePath = FileHelper.getPath(todayTime,'aqy',urls[keyWord])
fileName = '%s/json.txt' % filePath
FileHelper.getContent2FileWithoutProcess(fileName=fileName,targetUrl=targetUrl)
content = open(fileName,'r')
temp = content.read().decode('utf-8')
dic = json.loads(temp)
key = ''
resultFileName = ''
if type == TYPE_DAILY:
resultFileName='%s/RankDaily.txt' % filePath
key = 'album_count_yesterday'
if type == TYPE_WEEKLY:
resultFileName='%s/RankWeekly.txt' % filePath
key = 'album_count_lastweek'
count = len(dic['data'])
for i in range(count):
FileHelper.save2File(content= 'Rank.%s %s VV : %s \n' % (i+1,dic['data'][i]['album_name'],dic['data'][i][key]), fileName=resultFileName,type= FileHelper.TYPE_APPEND)
content.close()
FileHelper.delFile(fileName)
def getData(keyWord = ''):
targetUrl = getUrl(keyWord)
todayTime = datetime.date.today()
filePath = FileHelper.getPath(todayTime,'letv',urls[keyWord])
fileName = '%s/html.txt' % filePath
FileHelper.getContent2FileWithoutProcess(fileName=fileName,targetUrl=targetUrl)
content = open(fileName,'r')
temp = content.read().decode('utf-8')
soup = BeautifulSoup(temp,'html.parser')
rank = 0
for tag in soup.findAll(True):
# 每50条为分割
if(tag.name == 'a' and tag.has_attr('href') and (''.join(tag['href']).find('www.le.com') > 0) and rank<150):
rank = rank + 1
if rank <= 50:
FileHelper.save2File(content = 'Rank.%s %s ' % (rank,tag.string ), fileName='%s/RankDaily.txt' % filePath,type= FileHelper.TYPE_APPEND)
if rank <=100 and rank >50:
FileHelper.save2File(content = 'Rank.%s %s ' % (rank-50,tag.string ), fileName='%s/RankWeekly.txt' % filePath,type= FileHelper.TYPE_APPEND)
if rank <= 150 and rank > 100:
FileHelper.save2File(content = 'Rank.%s %s ' % (rank-100,tag.string ), fileName='%s/RankMonthly.txt' % filePath,type= FileHelper.TYPE_APPEND)
if (tag.has_attr('class') and tag.name == 'span' and ''.join(tag['class']) == 't-5' and rank<150):
if rank <= 50:
FileHelper.save2File(content = 'VV : %s \n' % tag.string , fileName='%s/RankDaily.txt' % filePath,type= FileHelper.TYPE_APPEND)
if rank <=100 and rank >50:
FileHelper.save2File(content = 'VV : %s \n' % tag.string , fileName='%s/RankWeekly.txt' % filePath,type= FileHelper.TYPE_APPEND)
if rank <= 150 and rank > 100:
FileHelper.save2File(content = 'VV : %s \n' % tag.string , fileName='%s/RankMonthly.txt' % filePath,type= FileHelper.TYPE_APPEND)
content.close()
FileHelper.delFile(fileName)
def getData(keyWord = ''):
if keyWord == '':
print 'params lost'
return False
todayTime = datetime.date.today()
targetUrl = 'http://tv.sohu.com/%s' % keyWord
filePath = FileHelper.getPath(todayTime,'sohu',urls[keyWord])
fileName = '%s/html.txt' % filePath
FileHelper.getContent2FileWithoutProcess(fileName=fileName,targetUrl=targetUrl)
content = open(fileName,'r')
temp = content.read().decode('utf-8')
soup = BeautifulSoup(temp,'html.parser')
count = -1 #过滤第一个
for tag in soup.findAll(True):
if tag.has_attr('class'):
#print ''.join(tag['class'])
if (''.join(tag['class']) == 'at' and tag.name == 'a') or (tag.name == 'span' and ''.join(tag['class']) == 'vTotal'):
count = count + 1
if count <= 200 and count >= 1 :
if count == 1:
FileHelper.save2File(content= 'RankDaily \n' , fileName=('%s/RankDaily.txt'% filePath),type= FileHelper.TYPE_APPEND)
#日榜数据
FileHelper.save2File(content= '%s \n' %tag.string , fileName=('%s/RankDaily.txt'% filePath ) ,type= FileHelper.TYPE_APPEND)
if count > 200 and count <= 400 :
if count == 201:
FileHelper.save2File(content= 'RankWeekly \n' , fileName=('%s/RankWeekly.txt'% filePath ) ,type= FileHelper.TYPE_APPEND)
#周榜数据
FileHelper.save2File(content= '%s \n' %tag.string , fileName=('%s/RankWeekly.txt'% filePath ) ,type= FileHelper.TYPE_APPEND)
if count > 400 and count <= 600 :
if count == 401:
FileHelper.save2File(content= 'RankMonth \n' , fileName=('%s/RankMonthly.txt'% filePath ) ,type= FileHelper.TYPE_APPEND)
#月榜数据
FileHelper.save2File(content= '%s \n' %tag.string , fileName=('%s/RankMonthly.txt'% filePath ) ,type= FileHelper.TYPE_APPEND)
if count > 600 :
if count == 601:
FileHelper.save2File(content= 'RankTotal \n' , fileName=('%s/RankTotal.txt'% filePath ) ,type= FileHelper.TYPE_APPEND)
#总计数据
FileHelper.save2File(content= '%s \n' %tag.string , fileName=('%s/RankTotal.txt'% filePath) ,type= FileHelper.TYPE_APPEND)
#print tag.string
content.close()
FileHelper.delFile(fileName)
