def get_real_url(self):
for i, play_page_url in enumerate(self.play_page_urls):
# logging.info('[当前资源第：] %s/%s [项]', i + 1, self.num)
play_page_url = 'https://www.yszxwang.com' + play_page_url
# logging.info('[播放页链接：] %s', play_page_url)
resp1 = get_response(play_page_url)
if resp1:
self.data_url = re.search('var now="(http.*?)"',
resp1).group(1).strip()
# logging.info('[数据链接：] %s', self.data_url)
resp2 = get_response(self.data_url)
if resp2:
u2 = ''
if 'm3u8' in self.data_url:
if self.type == 'w':
break
host = re.sub('index.*', '', self.data_url)
resp3 = get_response(self.data_url)
if resp3:
m3u8text = resp3.split('\n')
for text in m3u8text:
if 'm3u8' in text:
u2 = text
else:
s = self.data_url.split('/')
host1 = s[0] + '//' + s[2]
u1 = re.search('var main = "(.*?)"',
resp2).group(1).strip()
m3u8_url1 = host1 + u1
# logging.info('[第一个m3u8：] %s', m3u8_url1)
host = re.sub('index.*', '', m3u8_url1)
# 读取第一个m3u8链接，获取真实m3u8链接
resp3 = get_response(m3u8_url1)
if resp3:
m3u8text = resp3.split('\n')
for text in m3u8text:
if 'm3u8' in text:
u2 = text
if u2:
if u2[0] == '/':
real_url = host + u2[1:]
else:
real_url = host + u2
# logging.info('[真实m3u8：] %s', real_url)
resp = get_response(real_url)
if resp:
return real_url
logging.info('[播放页异常：] %s', play_page_url)
return '全部资源尝试完毕，解析失败'
def get_all_source(self):
max_num = 0
max_play = 0
resp = get_response(self.many_detail_url)
all_source = re.findall("href='(/video.*?)'", resp)
for s in all_source:
num = int(re.search('-(\d+?)-', s).group(1).strip())
play_num = int(re.search('-\d+?-(\d+?)\.html', s).group(1).strip())
if num > max_num:
max_num = num
if play_num > max_play:
max_play = play_num
# 最大资源数
source_num = max_num + 1
# 最大集数，有些资源更新慢集数不足，弃用
self.play_num = max_play + 1
all_play_list = []
for i in range(source_num):
soruce_list = []
for s in all_source:
# 资源分类
cate = int(re.search('-(\d+?)-', s).group(1).strip())
if cate == i:
soruce_list.append(s)
# 获取集数最大的所有资源
if len(soruce_list) == self.play_num:
all_play_list.append(soruce_list)
# 弃用集数不足的资源
logging.info('[共有资源]%s[项]，[每项资源]%s[集]', len(all_play_list),
self.play_num)
return all_play_list
def get_play_urls(self):
# 进入详情页，找到播放页链接
resp = get_response(self.detail_url)
if not resp:
return "ERROR, 请求失败"
play_page_urls = re.findall(
'a title=.*? href=\'(.*?)\' target="_self"', resp)
return play_page_urls
def down_m3u8_thread(url, file_name, host=None, headers=None):
mkdir()
file_name = file_name + '.mp4'
logging.info('[url] %s [file_name] %s', url, file_name)
host = host
# 预下载，获取链接并写文件
resp = get_response(url)
m3u8_text = resp
# 开链接队列
ts_queue = Queue(10000)
lines = m3u8_text.split('\n')
concatfile = 'cache/' + "s" + '.txt'
for i, line in enumerate(lines):
if '.ts' in line:
if 'http' in line:
ts_queue.put(line)
else:
if line[0] == '/':
line = host + line
else:
line = host + '/' + line
ts_queue.put(line)
filename = re.search('([a-zA-Z0-9-_]+.ts)', line).group(1).strip()
open(concatfile, 'a+').write('file %s\n' % filename)
num = ts_queue.qsize()
logging.info('[下载开始，队列任务数：] %s', num)
if num > 5:
t_num = num // 5
else:
t_num = 1
if t_num > 50:
t_num = 50
threads = []
logging.info('下载开始')
for i in range(t_num):
t = threading.Thread(target=down,
name='th-' + str(i),
kwargs={
'ts_queue': ts_queue,
'headers': headers
})
t.setDaemon(True)
threads.append(t)
for t in threads:
logging.info('[线程开始]')
time.sleep(0.4)
t.start()
for t in threads:
logging.info('[线程停止]')
t.join()
logging.info('下载完成，合并开始')
merge(concatfile, file_name)
logging.info('合并完成，删除冗余文件')
remove()
result = getLength(file_name)
return result
def get_many_real_url(self):
for i, play_list in enumerate(self.all_play_list):
many_data_url = []
many_real_url = []
# logging.info('[当前资源第：] %s/%s [项]', i + 1, self.source_num)
for j, play_page_url in enumerate(play_list):
# logging.info('[当前解析第：] %s/%s [集]', j + 1, self.play_num)
play_page_url = 'https://www.yszxwang.com' + play_page_url
# logging.info('[播放页链接：] %s', play_page_url)
resp1 = get_response(play_page_url)
if resp1:
data_url = re.search('var now="(http.*?)"',
resp1).group(1).strip()
# logging.info('[数据链接：] %s', data_url)
resp2 = get_response(data_url)
many_data_url.append(data_url)
if resp2:
u2 = ''
if 'm3u8' in data_url:
if self.type == 'w':
break
host = re.sub('index.*', '', data_url)
resp3 = get_response(data_url)
if resp3:
m3u8text = resp3.split('\n')
for text in m3u8text:
if 'm3u8' in text:
u2 = text
else:
# host = re.search('var redirecturl = "(http.*?)"', resp2).group(1).strip()
s = data_url.split('/')
host1 = s[0] + '//' + s[2]
u1 = re.search('var main = "(.*?)"',
resp2).group(1).strip()
m3u8_url1 = host1 + u1
# logging.info('[第一个m3u8：] %s', m3u8_url1)
host = re.sub('index.*', '', m3u8_url1)
# 读取第一个m3u8链接，获取真实m3u8链接
resp3 = get_response(m3u8_url1)
if resp3:
m3u8text = resp3.split('\n')
for text in m3u8text:
if 'm3u8' in text:
u2 = text
else:
break
if u2:
if u2[0] == '/':
real_url = host + u2[1:]
else:
real_url = host + u2
if not real_url:
break
# logging.info('[真实m3u8：] %s', real_url)
resp = get_response(real_url)
# 简单测试链接可用性
if resp:
many_real_url.append(real_url)
else:
break
else:
break
else:
break
if len(many_real_url) == self.play_num and len(
many_data_url) == self.play_num:
return many_real_url, many_data_url
return 'defeat', 'defeat'