def getVideoByUrl(url):
# url=r'http://tv.sohu.com/20140904/n404054190.shtml'
html = getHtml(url)
if not html:
return
vid = r1(r'share.vrs.sohu.com/(.*?)/',html)
streamTypes = ["norVid", "highVid", "superVid", "oriVid"]
streamType_url = "http://hot.vrs.sohu.com/vrs_flash.action?vid=" + vid
content=getHtml(streamType_url)
if not content:
return
jsonContent = json.loads(content)['data']
videos=[]
for streamType in streamTypes:
# print streamType
streamType_id = jsonContent[streamType]
try:
allot, prot, clipsURL, su = getPram(streamType_id)
if(len(clipsURL)!=len(su)):
continue
else:
video=[]
for i in range(len(clipsURL)):
allot_url = "http://%s/?prot=%s&file=%s&new=%s"%(allot, prot, clipsURL[i], su[i])
prefix, key = getKey(allot_url)
realUrl = "%s%s?key=%s"%(prefix[0:-1], su[i], key)
# print realUrl
video.append(realUrl)
if video:
videos.append(video)
except:
pass
if len(videos)>0:
return videos[0]
return videos
def getVideoByUrl(url):
# tDir=r'e:\tmp'
# fileName=r'v1.html'
# filePath=os.path.join(tDir,fileName)
content=getHtml(url)
# if content:
# fileKit.writeFileBinary(filePath, content)
# content=fileKit.readFileBinary(filePath)
videoUrl=None
if content:
# video, all type should be considered at the last
videoUrl=r1(r'<source src="(.*?)"',content)
if not videoUrl:
# audio
videoUrl=r1(r'audio src="(.*?)"',content)
if not videoUrl:
# all type
videoUrl=getVideoInfoByUrl(url)
# if videoUrl:
# if not os.path.splitext(videoUrl)[1] in suffix:
# print videoUrl
# videoUrl=None
return videoUrl
def getVideoByVid(vid):
url = 'http://vv.video.qq.com/geturl?otype=xml&platform=1&vid=%s&format=2' % vid
content=getHtml(url)
videoUrl=None
if content:
videoUrl=r1(r'<url>(.*?)</url>',content)
return videoUrl
def getPram(streamType_id):
url = "http://hot.vrs.sohu.com/vrs_flash.action?vid=" + str(streamType_id)
jsonContent = json.loads(getHtml(url))
allot = jsonContent['allot']
prot = jsonContent['prot']
clipsURL = jsonContent['data']["clipsURL"]
su = jsonContent['data']["su"]
return allot, prot, clipsURL, su
def download(self,url,filepath): #获取名称 name = self.getName(url) html = common.getHtml(url) m3u8 = self.getM3u8(html) common.download(urllib.unquote(m3u8),filepath,name + '.m3u8') url = self.URL_PIRFIX + self.getSinavideoUrl(filepath+name+'.m3u8') common.download(url,filepath,name+'.mp4')
def getVideoByUrl(url):
# http://dp.sina.cn/dpool/video/pad/play.php?url=http://video.sina.com.cn/p/news/c/v/2014-09-03/214064108827.html
ipad_url=r'http://dp.sina.cn/dpool/video/pad/play.php?url='
# r_url=ipad_url+urllib.quote(url)
r_url=ipad_url+url
# print r_url
content=getHtml(r_url)
if content:
url=r1(r'<source.*?src="(.*?)"',content)
return url
def getImage(imgurl,lock=fileLock):
content=getHtml(imgurl)
if not content:
print 'getImage failure'
return
imgname=md5(imgurl)+r'.jpg'
saveasImage(imgname,content)
lock.acquire()
savetoDownloaded(imgurl,imgname)
lock.release()
def getVideoInfoByUrl(url):
# url is like : http://domestic.kankanews.com/c/2014-08-04/0015274473.shtml
# xml url is like : http://www.kankanews.com/vxml/2014-08-04/0015274473.xml
part1=r1(r'(/\d{4}-\d{2}-\d{2}/\w*?)\.',url)
xml_url=r'http://www.kankanews.com/vxml%s.xml'%part1
content=getHtml(xml_url)
videoUrl=None
if content:
root=ET.fromstring(content)
resolution=root[0].text.replace('h264_1500k_mp4','h264_450k_mp4') # just a patch
videoUrl= root[1].text+resolution
return videoUrl
def getVideoByUrl(url):
# tDir=r'e:\tmp'
# fileName=r'v1.html'
# filePath=os.path.join(tDir,fileName)
content=getHtml(url)
# if content:
# fileKit.writeFileBinary(filePath, content)
# content=fileKit.readFileBinary(filePath)
videoUrl=None
if content:
# video
videoUrl=r1(r"<video.*?src='(.*?)'",content)
if not videoUrl:
sourceWeb=r1(r'src="(.*?)" data-vid',content)
dataVid=r1(r'data-vid="(.*?)"',content)
if 'ku6' in sourceWeb and dataVid:
videoUrl=getKu6VideoByVid(dataVid)
return videoUrl
def getVideoByUrl(url):
# tDir=r'e:\tmp'
# fileName=r'v1.html'
# filePath=os.path.join(tDir,fileName)
# url is like:http://v.ifeng.com/news/world/201408/015041f2-2979-9982-9fb1-950a9390ac64.shtml
# vInfo_url_prefix=r'http://v.ifeng.com/video_info_new/4/48/01de5902-0b5a-00f1-5154-47d50dda0448.xml'
vInfo_url_prefix = r"http://v.ifeng.com/video_info_new/" # 4/48/01de5902-0b5a-00f1-5154-47d50dda0448.xml'
d1 = r1(r".*/(.*?)\.", url)
# print d1,d1[len(d1)-2],d1[len(d1)-2:len(d1)]
vInfo_url = vInfo_url_prefix + d1[len(d1) - 2] + r"/" + d1[len(d1) - 2 : len(d1)] + r"/" + d1 + r".xml"
# print vInfo_url
content = getHtml(vInfo_url)
# if content:
# fileKit.writeFileBinary(filePath, content)
# content=fileKit.readFileBinary(filePath)
videoUrl = None
if content:
root = ET.fromstring(content)
videoUrl = root[0].attrib.get("VideoPlayUrl")
return videoUrl
def download(self, url, filepath):
jsonUrl = self.URL_PRIFIX + self.getJsonUrl(url)
html = common.getHtml(jsonUrl)
voiceTitle, voiceUrl = self.getVoiceUrl(html)
common.download(voiceUrl, filepath, voiceTitle + '.m4a')
def getKey(allot_url):
content = getHtml(allot_url)
listTmp = content.split('|')
prefix = listTmp[0]
key = listTmp[3]
return prefix, key
