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 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:
videoUrl=r1(r'<param.*?videoUrl=(.*?)"',content)
return videoUrl
def getVideoByUrl(url):
if re.match(r'http://share.vrs.sohu.com', url):
vid = r1('id=(\d+)', url)
else:
html = getHtml(url)#.decode('gbk')
vid = r1(r'\Wvid\s*[\:=]\s*[\'"]?(\d+)[\'"]?', html)
assert vid
if re.match(r'http://tv.sohu.com/', url):
info = json.loads(getHtml('http://hot.vrs.sohu.com/vrs_flash.action?vid=%s' % vid))
for qtyp in ["oriVid","superVid","highVid" ,"norVid","relativeId"]:
hqvid = info['data'][qtyp]
if hqvid != 0 and hqvid != vid :
info = json.loads(getHtml('http://hot.vrs.sohu.com/vrs_flash.action?vid=%s' % hqvid))
break
host = info['allot']
tvid = info['tvid']
urls = []
data = info['data']
assert len(data['clipsURL']) == len(data['clipsBytes']) == len(data['su'])
for new,clip,ck, in zip(data['su'], data['clipsURL'], data['ck']):
clipURL = urlparse(clip).path
urls.append(real_url(host,hqvid,tvid,new,clipURL,ck))
# assert data['clipsURL'][0].endswith('.mp4')
else:
info = json.loads(getHtml('http://my.tv.sohu.com/play/videonew.do?vid=%s&referer=http://my.tv.sohu.com' % vid))
host = info['allot']
tvid = info['tvid']
urls = []
data = info['data']
assert len(data['clipsURL']) == len(data['clipsBytes']) == len(data['su'])
for new,clip,ck, in zip(data['su'], data['clipsURL'], data['ck']):
clipURL = urlparse(clip).path
urls.append(real_url(host,vid,tvid,new,clipURL,ck))
return urls
def getHtmlInfo():
url = r"http://www.huxiu.com"
wap_url = "http://m.huxiu.com"
content = getHtml(url)
# print content
newsList = []
if content:
soup = BeautifulSoup(content, "html.parser", from_encoding="utf-8")
itemList = soup.find_all("div", {"class": "mod-b mod-art "})
itemList += soup.find_all("div", {"class": "mod-b mod-art mod-b-push"})
for item in itemList:
nInfo = {}
head = item.find("", {"class": "mob-ctt"})
if not head:
continue
title = head.find("h3")
if not title:
continue
title = title.find("a")
nInfo["url"] = url + title.get("href")
nInfo["title"] = title.getText()
nInfo["newsid"] = getMd5(nInfo["url"])
nInfo["summary"] = item.find("div", {"class": "mob-sub"}).getText()
nInfo["description"] = nInfo["summary"]
nInfo["thumb"] = item.find("img", {"class": "lazy"}).get("data-original")
nInfo["keywords"] = ""
timeStr = head.find("span", {"class": "time"}).getText()
timeSec = time.time()
min_num = r1(u"(\d{1,2})分钟前", timeStr)
if min_num:
timeSec -= 60 * long(min_num)
else:
hour_num = r1(u"(\d{1,2})小时前", timeStr)
if hour_num:
timeSec -= 3600 * long(hour_num)
else:
day_num = r1(u"(\d{1,2})天前", timeStr)
timeSec = timeSec - long(day_num) * 24 * 3600 if day_num else timeSec
nInfo["ctime"] = timeSec
author_div = item.find("div", {"class": "mob-author"})
nInfo["author"] = ""
if author_div:
author_span = author_div.find("span", {"class": "author-name "})
nInfo["author"] = author_span.getText() if author_span else ""
nInfo["source"] = ctable
newsList.append(nInfo)
return newsList
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 real_url(host,vid,tvid,new,clipURL,ck):
url = 'http://'+host+'/?prot=9&prod=flash&pt=1&file='+clipURL+'&new='+new +'&key='+ ck+'&vid='+str(vid)+'&uid='+str(int(time.time()*1000))+'&t='+str(random.random())
return json.loads(getHtml(url))['url']