def get_channels(source):
lst = []
page = get_page(
"http://www.desi-tashan.com/%s/" % (source.replace(" ", "-").lower()))
if not page:
return lst
content = page.find("div", {"id": "content"})
if not content:
return lst
for link in content.find_all('a'):
href = link.get("href")
if not href:
continue
mo = re_source.search(href)
if not mo:
continue
th = None
img = link.find("img")
if img and img.has_attr("src"):
th = img.get("src")
lst.append((
_to_channel_name(mo.group(1)),
plugin.url_for('show_channel', url=mo.group(0)),
th,
False))
return lst
def search(request):
hit = 15 #每页结果数
os = SearchAPI()
kw = request.GET.get('keywords').encode('utf-8')
if kw == "":
return HttpResponse("关键字不能为空!<a href=\"../index\">返回</a>")
page = helper.get_page(request.GET.get('page'))
start = (page - 1) * hit
helper.save_search_log(kw, page)
res = os.search(kw, start, hit)
if res is None:
return HttpResponse("内部错误,请联系 砺诚")
num = res['num']
nextPage = page + 1
if not (res['total'] > page * hit):
nextPage = 0
prePage = page - 1
f = open("mysite/result.html")
t = template.Template(f.read())
for item in res['items']:
item['id'] = int(item['id'])
c = template.Context({
"keyword": kw,
"all_result": res['items'],
"total": res['total'],
"num": res['num'],
"searchtime": res['searchtime'],
"page": page,
"nextPage": nextPage,
"prePage": prePage
})
return HttpResponse(t.render(c))
def _jwplayer(page, domain):
urls = []
url = None
for iframe in page.find_all("iframe"):
if not iframe.has_attr("src"):
continue
if domain not in iframe.get("src"):
continue
url = iframe.get("src")
break
if not url:
return urls
page = get_page(url)
for script in page.find_all("script", {"type": "text/javascript"}):
mo = re_jwplayer.search(script.text)
if not mo:
continue
urls.append(mo.group(1))
break
return urls
def search(request):
hit = 15 #每页结果数
kw = request.GET.get('keywords').encode('utf-8')
if kw == "":
return HttpResponse("关键字不能为空!<a href=\"../index\">返回</a>")
page = helper.get_page( request.GET.get('page') )
start = (page - 1) * hit
helper.save_search_log(kw, page)
res = searcher.search(kw.replace("'",""), start, hit, WEB_TAG)
if res is None:
return HttpResponse("内部错误,请联系 砺诚")
num = res['num']
nextPage = page + 1
if not (res['total'] > page * hit):
nextPage = 0
prePage = page -1
helper.save_search_result_info(kw, res['total'])
f = open(search_page_template)
t = template.Template(f.read())
for item in res['items']:
item['id'] = int(item['id'])
c = template.Context({
"keyword":kw,
"all_result":res['items'],
"total":res['total'],
"num":res['num'],
"searchtime":res['searchtime'],
"page":page,
"nextPage":nextPage,
"prePage":prePage,
"urlPrefix":URL_PREFIX
})
return HttpResponse(t.render(c))
def search(request):
hit = 15 #每页结果数
os = SearchAPI()
kw = request.GET.get('keywords').encode('utf-8')
if kw == "":
return HttpResponse("关键字不能为空!<a href=\"../index\">返回</a>")
page = helper.get_page( request.GET.get('page') )
start = (page - 1) * hit
helper.save_search_log(kw, page)
res = os.search(kw, start, hit)
if res is None:
return HttpResponse("内部错误,请联系 砺诚")
num = res['num']
nextPage = page + 1
if not (res['total'] > page * hit):
nextPage = 0
prePage = page -1
f = open("mysite/result.html")
t = template.Template(f.read())
for item in res['items']:
item['id'] = int(item['id'])
c = template.Context({
"keyword":kw,
"all_result":res['items'],
"total":res['total'],
"num":res['num'],
"searchtime":res['searchtime'],
"page":page,
"nextPage":nextPage,
"prePage":prePage
})
return HttpResponse(t.render(c))
def get_links(url, name):
lst = []
page = get_page(url)
if not page:
return lst
urls = resolvers.youtube(page)
urls.extend(resolvers.playwire(page))
urls.extend(resolvers.vodlocker(page))
urls.extend(resolvers.dailymotion(page))
for u in urls:
lst.append((
name,
plugin.url_for('play_video', video=u, name=name),
None,
True))
if not urls:
for link in page.find_all("a", {"target":"_blank"}):
if not link.has_attr("href"):
continue
href = link.get("href")
if href.startswith("http://www.desi-tashan.com/"):
player = None
if "youtube" in href:
player = "Youtube"
elif "/pw-" in href or "/pw/" in href:
player = "Playwire"
elif "dailymotion" in href:
player = "Dailymotion"
elif "vodlocker" in href:
player = "Vodlocker"
if player:
part = ""
mo = re_part.search(link.text)
if mo:
part = mo.group(1)
lst.append((
"%s %s" % (player, part.strip()),
plugin.url_for(
'show_part', url=link.get("href"), name=name),
None,
True))
return lst
def get_episodes(show):
lst = []
page = get_page(show)
if not page:
return lst
content = page.find("div", {"id": "left-inside"})
if not content:
return lst
for a in content.find_all("a"):
if a.get("id") == "nav-home":
continue
name = a.text.strip()
name = re_char.sub(' ', name)
if "Older Entries" in name:
url = None
mo = re_page.search(show)
if not mo:
continue
if mo.group(2):
url = "%spage/%d%s" % (
mo.group(1), int(mo.group(2)) + 1, mo.group(3))
else:
url = "%s/page/2%s" % (mo.group(1), mo.group(3))
lst.insert(0, (
"Next Page",
plugin.url_for(
"show_show", show=url),
None, False))
continue
if "Next Entries" in name:
continue
lst.append((
name,
plugin.url_for(
'show_links',
link=a.get("href"),
name=name),
None, False))
return lst
def get_shows(channel):
lst = []
page = get_page(channel)
if not page:
return lst
categories = page.find("li", {"class": "categories"})
if not categories:
return lst
for a in categories.find_all("a"):
lst.append((
a.text,
plugin.url_for('show_show', show=a.get("href") + "?tag=video"),
None, False))
return lst
def play_video(video, name, mode):
page = get_page(video)
url = None
if page:
if mode == "flash":
mode = "playwire"
resolver = get_resolver(mode)
if resolver:
urls = resolver(page)
if urls:
url = urls[0]
if url:
return plugin.play_video(dict(label=name, path=url))
return None
def get_links(link, name):
lst = []
page = get_page(link)
if not page:
return lst
content = page.find("div", {"id": "left-inside"})
if not content:
return lst
content = content.find("center")
if not content:
return lst
group = ""
for p in content.find_all("p"):
if not p.text:
continue
span = p.find("span")
if span:
group = span.text
mo = re_group.search(group)
if mo:
group = mo.group(1).replace(" ", "").capitalize()
else:
group = ""
elif group:
for a in p.find_all("a"):
part = ""
mo = re_part.search(a.text)
if mo:
part = mo.group(1)
lst.append((
"%s %s" % (group, part.strip()),
plugin.url_for(
'play_video',
video=a.get("href"),
name=name,
mode=group.lower()),
None, True))
return lst
def get_episodes(mode, url, page=None):
lst = []
if not page:
page = get_page(url)
if not page:
return lst
pagenavi = page.find("div", {"class": "wp-pagenavi"})
if pagenavi:
a_next = pagenavi.find("a", {"class": "nextpostslink"})
if a_next:
mo = re_page.search(url)
if mo:
url_next = "%s%d/" % (mo.group(1), int(mo.group(2)) + 1)
else:
url_next = url.strip() + "page/2/"
lst.append((
"Next Page",
plugin.url_for(mode, url=url_next),
None, False))
for article in page.find_all("article"):
if not article.find(
"div",
{"class": ["videoPost", "videoClip"]}):
continue
title = article.get("title")
link = article.find("a")
if not link or not link.has_attr("href"):
continue
th = None
img = article.find("img")
if img and img.has_attr("src"):
th = img.get("src")
lst.append((
title,
plugin.url_for('show_episode', url=link.get("href"), name=title),
th,
False))
return lst
def get_tvshows(url, newshows=True):
lst = []
page = get_page(url)
if not page:
return lst
cat = "mainNewcat" if newshows else "mainOldcat"
select = page.find("select", {"class": cat})
for option in select.find_all("option"):
value = option.get("value")
if not value:
continue
lst.append((
option.text,
plugin.url_for('show_show', url=value),
None,
False))
return lst
def get_channels():
lst = []
page = get_page("http://www.desitvbox.me/")
if not page:
return lst
categories = page.find("div", {"id": "categories"})
if not categories:
return lst
for a in categories.find_all("a"):
if "DTB" in a.text or "TRP" in a.text:
continue
lst.append((
a.text,
plugin.url_for('show_channel', channel=a.get("href")),
None, False))
return lst
#!/usr/bin/env python3
import sys
import helper
import re
from urllib.parse import urlparse
if len(sys.argv) < 2:
print("Usage: {} url".format(sys.argv[0]))
sys.exit(1)
URL = sys.argv[1]
(browser, page) = helper.get_page(URL)
DOMAIN = "{uri.scheme}://{uri.netloc}".format(uri=urlparse(URL))
lecture_links = page.soup.select('a.medialink')
for index, lecture_link in enumerate(lecture_links):
lecture_title = lecture_link.string
link = "{}/{}".format(DOMAIN, lecture_link.attrs['href'])
video_page = browser.get(link)
script = [
script for script in video_page.soup.select('script')
if 'ocw_embed_chapter_media' in str(script)
]
if len(script) < 1:
print(":(")
continue
youtube_url = re.findall(r'(https:\/\/www.youtube.com\/v\/.*?)\'',
str(script[0]))
def getTopicsPager(self):
pages = self.getTopicsLength()/settings.TOPICS_PER_PAGE
page = get_page(pages)
return {'page':page, 'pages':pages}
def show_channel(url):
items.clear()
page = get_page(url)
items.add_all(get_channel_items(url, page))
items.add_all(get_episodes('show_channel', url, page))
return items