ppslist: add methods for parsing long play lists

1 files changed, 90 insertions, 0 deletions

diff --git a/totem/plugin/ppslist.py b/totem/plugin/ppslist.py
index b507801..8510a5c 100644
--- a/totem/plugin/ppslist.py
+++ b/totem/plugin/ppslist.py
@@ -367,6 +367,58 @@ def parseMovieFileList(movie, s):
         ci += 1
     return result
 
+def getMovieFileListFrameUrl(s):
+    s = gbk2utf8(s)
+    soup = BeautifulSoup.BeautifulSoup(s)
+    result = []
+    play_iframe = soup.findAll('iframe', { 'id': 'play_iframe' })
+    if not play_iframe:
+        return ''
+    return play_iframe[0]['src']
+
+def getMovieFileListFrameBaseUrl(s):
+    url = getMovieFileListFrameUrl(s)
+    if not url:
+        return url
+    pos = url.rfind('/')
+    if pos > 0:
+        return url[0:pos]
+    return url
+
+def parseMoviePlayList(s):
+    s = gbk2utf8(s)
+    soup = BeautifulSoup.BeautifulSoup(s)
+    seein = soup.findAll('div', { 'class': 'onseeIn' })
+    if not seein:
+        return ()
+    uls = seein[0].findAll('ul')
+    if not uls:
+        return ()
+    items = uls[0].findAll('li')
+    if not items:
+        return ()
+
+    files = []
+    for item in items:
+        f = PPSFile()
+        fid = extractNumber(item['id'])
+        refs = item.findAll('a')
+        title = refs[0].contents[-1]
+        url = refs[1]['href']
+        f.id = fid
+        f.title = unicode(title).encode('utf-8')
+        f.url = unicode(url).encode('utf-8')
+        files.append(f)
+
+    pagenav = soup.findAll('div', { 'class': 'pageNav' })
+    if not pagenav:
+        return ()
+    refs = pagenav[0].findAll('a')
+    maxpage = int(refs[-1].contents[-1])
+    spans = pagenav[0].findAll('span')
+    curpage = int(spans[0].contents[-1])
+    return (files, max(maxpage, curpage))
+
 def getMovieFileList(movie):
     s = download(movie.playerurl)
     return parseMovieFileList(movie, s)
@@ -467,6 +519,43 @@ if __name__ == '__main__':
 
         sys.exit(0)
 
+    def test_get_file_list_by_iframe():
+        url = 'http://kan.pps.tv/play/298356.html'
+        s = download(url)
+        movie = PPSMovie()
+        file_list = parseMovieFileList(movie, s)
+        for f in file_list:
+            print f
+
+        if file_list:
+            return
+        baseurl = getMovieFileListFrameBaseUrl(s)
+        print 'baseurl = ', baseurl
+
+        first = baseurl + '/0.html'
+        s = download(first)
+        if not s:
+            return
+
+        last_maxpage = 0
+        cur_page = 0
+        while True:
+            url = baseurl + '/%d.html' % cur_page
+            s = download(url)
+            if not s:
+                break
+            result = parseMoviePlayList(s)
+            if not result:
+                break
+            files, max_page = result
+            print 'maxpage = ', max_page, cur_page
+            for f in files:
+                print f
+
+            if max_page == cur_page:
+                break
+            cur_page += 1
+
     def test_search ():
         ppslist = PPSList()
         s = ppslist.searchMovieList('周星驰')
@@ -520,3 +609,4 @@ if __name__ == '__main__':
     #test_ppslist()
     #test_search()
     #test_get_file_list()
+    #test_get_file_list_by_iframe()