def query_pianyuan_font(mv=None):
global myheaders,BASE_URL
r = BaseHttpGet.getSessionPool().get(mv.pub_font_url, headers=myheaders, timeout=10)
html = r.content.decode("gbk", 'replace')
soup = BeautifulSoup(html, "lxml")
links = soup.find_all("a")
font_name=None
down_url=None
for link in links:
href = link.get("href")
if href is None or href.find("mod=attachment")==-1 :
continue
font_name = link.string
if font_name is None or font_name.find("rar")==-1:
continue
down_url=href
if down_url is None:
print("字幕下载地址获取失败", down_url)
return False
pass
#下载字幕哦
dr = BaseHttpGet.getSessionPool().get(BASE_URL+down_url, headers=myheaders, stream=True)
f = open("D:/temp/"+font_name, "wb")
for chunk in dr.iter_content(chunk_size=512):
if chunk:
f.write(chunk)
f.close()
mv.save()
return True
def query_xp_torrent(mv=None):
try:
#如果下载地址是种子，则截取种子HASH码
#http://www1.downsx.net/torrent/D27DF676675F54E82A2294FE71AAE720F45B6634
if (mv.pub_down_url.find("torrent") != -1):
mv.pub_down_url = "magnet:?xt=urn:btih:" + mv.pub_down_url[
mv.pub_down_url.find("torrent") + 8:]
print(mv.pub_down_url)
return True
#如果是下载地址，则下载种子
if (mv.pub_down_url.find("updowm/file.php/") > 0):
r = BaseHttpGet.getSessionPool().get(mv.pub_down_url,
headers=headers,
timeout=10)
html = r.content.decode("utf-8", 'replace')
soup = BeautifulSoup(html, "lxml")
down_id = soup.find("input", id="id").get("value")
down_name = soup.find("input", id="name").get("value")
down_type = soup.find("input", id="type").get("value")
d = {'id': down_id, 'name': down_name, 'type': down_type}
#下载资源
headers2 = {
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36',
'Referer': mv.pub_down_url
}
down_url = mv.pub_down_url[0:mv.pub_down_url.find("file.php"
)] + "down.php"
print("开始下载种子", down_url)
down_r = BaseHttpGet.getSessionPool().post(down_url,
data=d,
headers=headers2,
timeout=15)
if (len(down_r.content) < 10):
print("下载种子失败")
return False
fileObject = open(
'd:/moviedata/torrent/1024xp_' + mv.pub_id + ".torrent", 'wb')
fileObject.write(down_r.content)
fileObject.flush()
fileObject.close()
#把种子转换成磁性链接
down_r.pub_down_url = BTBencode.BTByteToCode(down_r.content)
print("种子已转换为磁性链接", down_r.pub_down_url)
return True
pass
except Exception as e: # 远程文件不存在
print("下载种子失败", e)
return False
return False
def query_pianyuan_info(mv=None):
global myheaders
r = BaseHttpGet.getSessionPool().get(mv.pub_info_url, headers=myheaders, timeout=10)
html = r.content.decode("gbk", 'replace')
soup = BeautifulSoup(html, "lxml")
hdiv = soup.find("div",class_="showhide")
sidx = hdiv.text.find("magnet:")
if sidx==-1:
sidx = hdiv.text.find("http://gdl.lixian.vip.xunlei.com")
if sidx==-1:
print("下载地址无效",hdiv.text)
return False
mv.pub_down_url = hdiv.text[sidx:]
if(len(mv.pub_down_url)>1000):
print("下载地址无效2" ,len(mv.pub_down_url),mv.pub_down_url)
return False
td = hdiv.parent.parent
links = td.find_all("a")
for link in links:
href = link.get("href")
if href is not None and href.find("thread-")>0:
mv.pub_font_url=href
break
if mv.pub_font_url is None:
#没有字幕，直接保存
mv.save()
return False
else:
query_pianyuan_font(mv)
pass
return True
def getRemoteFileSize(url):
""" 通过content-length头获取远程文件大小
url - 目标文件URL
"""
if url is None or len(url) < 5:
return 0
try:
r = BaseHttpGet.getSessionPool().get(url, headers=headers, timeout=10)
return len(r.content)
except Exception as e: # 远程文件不存在
return 0