def get_movie_streams(movie_url):
movie_html = utils.fetch_html(movie_url)
player_link = parsers.get_player_link(movie_html)
player_frame = utils.fetch_html(player_link)
player_frame_src = parsers.get_player_iframe_src(player_frame)
player_html = utils.fetch_html(player_frame_src)
return parsers.parse_player(player_html)
def __prepare_comments(self,url):
html=fetch_html(url)
soup = BeautifulSoup(html, 'lxml')
pid = soup.select_one('#ifcomment')['data']
url = 'https://cmt.ithome.com/comment/' + pid
html=fetch_html(url)
soup = BeautifulSoup(html, 'lxml')
script = soup.select_one('#commentlist script').string
hash = script[-18:-2]
return hash
def get_down_url(self, item):
id = item['id']
url = self.base_url + '/p/d.php?aid=' + id
doc = lxml.html.fromstring(fetch_html(url))
ul = doc.cssselect("ul.down")[0]
down_urls = ul.xpath("li/a/@href")
item['down_url'] = [self.yp_url(x) for x in down_urls]
def get_ppt_list(self, cat="", page=1):
if page > 1:
page_str = f"/list-{page}.html"
else:
page_str = "/"
url = self.base_url + '/moban/' + cat + page_str
html = fetch_html(url)
doc = lxml.html.fromstring(html)
ul = doc.cssselect("ul.posts")[0]
items = [{
'name': x.text,
'url': self.yp_url(x.get("href")),
'id': x.get("href")[x.get("href").rfind("/") + 1:-5]
} for x in ul.xpath("li/a[2]")]
return items
def list_movies(page):
html = utils.fetch_html(MOVIES_URL % page)
return parsers.parse_movie_page(html)
def search(q):
search_url = SEARCH_URL % urllib.quote_plus(q)
html_result = utils.fetch_html(search_url)
return parsers.parse_search(html_result)
def get_movie_stream_from_player(player_url):
player_frame = utils.fetch_html(player_url)
player_frame_src = parsers.get_player_iframe_src(player_frame)
player_html = utils.fetch_html(player_frame_src)
return parsers.parse_player(player_html)
def list_episodes(url):
movie_html = utils.fetch_html(url)
player_link = parsers.get_player_link(movie_html)
html = utils.fetch_html(player_link)
return parsers.parse_episodes(html)
def list_genre(genre, page):
url = GENRES[genre]
url += '?page-%s' % page
html = utils.fetch_html(url)
return parsers.parse_movie_page(html)
def list_series(page, order='view'):
html = utils.fetch_html(SERIES_URL % (order, page))
return parsers.parse_movie_page(html)
def list_genre(genre, page):
url = GENRES[genre]
url += "?page-%s" % page
html = utils.fetch_html(url)
return parsers.parse_movie_page(html)
def list_series(page, order="view"):
html = utils.fetch_html(SERIES_URL % (order, page))
return parsers.parse_movie_page(html)
def get_news_content(self,news_item):
html=fetch_html(news_item['url'])
soup=BeautifulSoup(html,'lxml')
news_item['content']=soup.select_one("#paragraph").text
