def getCommentIqiyi(cls, playlink, moviename):
if playlink != '':
source = Request.getSource(playlink)
if source is not None:
m = re.search(r'qitanid="\w+"', source)
vid = m.group(0).split('"')[1]
for page in range(1, 50):
jslink = 'http://api.t.iqiyi.com/qx_api/comment/get_video_comments?page='+str(page)+'&qitanid='+str(vid)
commentsource = Request.getSource(jslink)
pat = re.compile(r'content":"(.*?)"')
try:
commentlist = pat.findall(commentsource)
for comm in commentlist:
unescomm = pyunescape.pyunescape(comm)
if unescomm is not None and unescomm != "":
db.insert((moviename, 'iqiyi', unescomm))
except:
continue
def resolveSohu(cls, movielink, moviename):
"""
sohu:从电影搜索页提取该搜索结果的播放页地址
"""
try:
f = Request.getSource(movielink)
source = BeautifulSoup(f)
links = source.find_all('a', title='点击观看')
playurl = links[0].get('href')
Comments.Comments.getCommentSohu(playurl, moviename)
except:
pass
def getCommentSohu(cls, playlink, moviename):
if playlink != '':
source = Request.getSource(playlink)
if source is not None:
m = re.search(r'vid\s*=\s*[\"\']\w+[\"\']', source)
vid = m.group(0).split('"')[1]
n = re.search(r'playlistId\s*=\s*[\"\']\w+[\"\']', source)
playlistid = n.group(0).split('"')[1]
jslink = 'http://access.tv.sohu.com/reply/list/1000_' + \
str(playlistid) + '_' + str(vid) + '_0_2000.js'
commentsource = Request.getSource(jslink)
try:
comments = re.search(r'\[.*\]', commentsource)
comments = comments.group(0).replace("'",'"')
pat = re.compile(r'content":"(.*?)"')
commentlist = pat.findall(comments)
for comm in commentlist:
unescomm = pyunescape.pyunescape(comm)
if unescomm is not None and unescomm != "":
db.insert((moviename, 'sohu', unescomm))
except:
pass
def resolveFunshion(cls, movielink):
"""
funshion:从电影搜索页提取该搜索结果的播放页地址
"""
try:
f = Request.getSource(movielink)
source = BeautifulSoup(f)
links = source.find_all('ul', "search_list")
if(len(links) != 0):
playurl = 'http://www.funshion.com' + \
links[0].find('a').get('href')
print playurl
except:
print '从搜索结果提取播放地址失败'
def resolveTudou(cls, movielink):
"""
tudou:从电影搜索页提取该搜索结果的播放页地址
和优酷一样，都是从搜库提取数据，忽略之
"""
try:
f = Request.getSource(movielink)
source = BeautifulSoup(f)
links = source.find_all('div', "btnplay_s")
if(len(links) != 0):
playurl = links[0].find('a').get('href')
# if playurl[:7] != '/search':
print playurl
except:
print '从搜索结果提取播放地址失败'
def resolveYouku(cls, movielink):
"""
youku:从电影搜索页提取该搜索结果的播放页地址
去掉重定向到其他视频网站的链接，以及不存在的链接
"""
try:
f = Request.getSource(movielink)
source = BeautifulSoup(f)
links = source.find_all('div', "btnplay_s")
if(len(links) != 0):
playurl = links[0].find('a').get('href')
if playurl[:7] != '/search':
print playurl
except:
print '从搜索结果提取播放地址失败'
def getCommentLetv(cls, playlink, moviename):
if playlink != '':
vid = playlink.split('/')[-1].split('.')[0]
for i in range(1, 120):
jslink = 'http://api.my.letv.com/vcm/api/g?type=video&xid='+str(vid)+'&page='+str(i)
source = Request.getSource(jslink)
try:
pat = re.compile(r'content":"(.*?)"')
commentlist = pat.findall(source)
for comm in commentlist:
unescomm = pyunescape.pyunescape(comm)
if unescomm is not None and unescomm != "":
db.insert((moviename, 'letv', unescomm))
except:
continue
def getCommentFunshion(cls, playlink, moviename):
if playlink != '':
vid = playlink.split('/')[-2]
for page in range(1, 31):
jslink = 'http://q.funshion.com/ajax/get_comment/media/'+vid+'/all?pg='+str(page)
source = Request.getSource(jslink)
try:
pat = re.compile(r'content":"(.*?)"')
commentlist = pat.findall(source)
for comm in commentlist:
unescomm = pyunescape.pyunescape(comm)
if unescomm is not None and unescomm != "":
db.insert((moviename, 'funshion', unescomm))
except:
continue
def getCommentYouku(cls, playlink, moviename):
if playlink != '':
vid = playlink.split('_')[-1].split('.')[0]
for page in range(1, 100):
jslink = 'http://comments.youku.com/comments/~ajax/vpcommentContent.html?__ap={%22videoid%22:%22'+vid+'%22,'+'%22page%22:'+str(page)+'}'
commentsource = Request.getSource(jslink)
try:
pat = re.compile(r'content_(.*?)<br')
commentlist = pat.findall(commentsource)
for comm in commentlist:
comm = comm.split('">')
unescomm = pyunescape.pyunescape(comm[2])
if unescomm is not None and unescomm != "":
db.insert((moviename, 'youku', unescomm))
except:
continue
