def parse(self, soup_obj):
assert soup_obj is not None
tr_list = soup_obj.select("table.torrents tr")
seeds = []
cnt = 0
for tr in tr_list:
cnt += 1
if cnt == 1:
# skip the caption tr
continue
seed = SeedInfo()
td_list = tr.select("td.rowfollow")
if len(td_list) < 9:
# skip embedded contents
continue
seed.sticky = len(
td_list[1].select("table td img[alt=\"Sticky\"]")) > 0
seed.title = td_list[1].select("table td a")[0]["title"]
seed.url = td_list[1].select("table td a")[0]['href']
seed.free = len(td_list[1].select("table font.free")) > 0
seed.hot = len(td_list[1].select("table font.hot")) > 0
seed.since = HttpUtils.get_content(td_list[3], "span")
seed.size = float(self.parse_size(td_list[4]))
seed.upload_num = int(self.clean_tag(td_list[5]))
seed.download_num = int(self.clean_tag(td_list[6]))
seed.finish_num = int(self.clean_tag(td_list[7]))
seed.id = self.parse_id(seed.url)
seeds.append(seed)
return seeds
def parse(self, soup_obj):
assert soup_obj is not None
tr_list = soup_obj.select("table.torrents tr")
seeds = []
cnt = 0
for tr in tr_list:
cnt += 1
if cnt == 1:
# skip the caption tr
continue
seed = SeedInfo()
td_list = tr.select("td.rowfollow")
if len(td_list) < 9:
# skip embedded contents
continue
seed.since = HttpUtils.get_content(td_list[2], "span")
seed.size = float(self.parse_size(td_list[3]))
seed.upload_num = int(self.clean_tag(td_list[4]))
seed.download_num = int(self.clean_tag(td_list[5]))
seed.finish_num = int(self.clean_tag(td_list[6]))
seed.done = self.clean_tag(td_list[7])
seed.working = "peer-active" in td_list[7]['class']
td_title = tr.select("td.torrenttr tr td")
seed.sticky = len(td_title[0].select("img[alt=\"Sticky\"]"))
seed.title = td_title[0].select("a")[0]["title"]
seed.url = td_title[0].select("a")[0]['href']
seed.free = len(td_title[0].select("img[alt=\"Free\"]")) > 0
seed.hot = len(td_title[0].select("font.hot")) > 0
if len(td_title[0].select("img[alt=\"50%\"]")) > 0:
seed.discount = 50
elif len(td_title[0].select("img[alt=\"30%\"]")) > 0:
seed.discount = 30
elif seed.free:
seed.discount = 0
else:
seed.discount = 100
seed.id = self.parse_id(seed.url)
seeds.append(seed)
print("Crawl: " + str(len(seeds)))
if len(seeds) < 10:
EmailSender.send(u"无法解析页面", Config.get("mteam_username"))
return seeds
def parse_page(self, soup_obj):
tr_list = soup_obj.select("#torrent_table tr")
seeds = []
cnt = 0
for tr in tr_list:
cnt += 1
if cnt == 1:
# skip the caption tr
continue
seed = SeedInfo()
td_list = tr.select("td")
if len(td_list) < 10:
continue
seed.sticky = len(td_list[1].select("div img[alt=\"置顶\"]"))
seed.title = HttpUtils.get_content(td_list[1].select("div a b"))
seed.url = td_list[1].select("div a")[0]['href']
seed.free = len(td_list[1].select("div a img[alt=\"free\"]")) > 0
seed.since = HttpUtils.get_content(td_list[3], "span")
seed.size = float(self.parse_size(td_list[4]))
seed.upload_num = int(self.clean_tag(td_list[5]))
seed.download_num = int(self.clean_tag(td_list[6]))
seed.finish_num = int(self.clean_tag(td_list[7]))
seed.id = self.parse_id(seed.url)
# parse discount
if len(td_list[1].select("table td font.halfdown")) > 0:
seed.discount = 50
elif len(td_list[1].select("table td font.d30down")) > 0:
seed.discount = 30
else:
seed.discount = 100
seeds.append(seed)
return seeds