def get_vod(self):
global QULIST
global RUN_COUNT
vinfo = {}
while not QULIST.empty():
vinfo = QULIST.get()
video_url = av911_root + vinfo['yuan_url']
video_html = download_html(video_url)
if video_html:
soup = BeautifulSoup(video_html, 'lxml')
video_script = soup.find('div', id="playview")
video_id = re.findall(r'mac_url=unescape\(\'(.*?)\'\)',
str(video_script), re.S)
if video_id:
video_url = av911_video_api + video_id[0]
# vinfo['play_url'] = location(video_url)
vinfo['play_url'] = video_url
vinfo['en_title'] = en(vinfo['title'])
vinfo['vkey'] = ikey()
vinfo['description'] = "暂无简介"
vinfo['vod_long'] = ''
vinfo['play_type'] = online_type[1]
vinfo['inputtime'] = getTime()
# 插入到数据库
sql = get_sql(vinfo, vod_type[0])
insert(sql)
RUN_COUNT += 1
time.sleep(1)
QULIST.task_done()
def get_vodbt_2(self):
global QULIST
global RUN_COUNT
vinfo = {}
while not QULIST.empty():
vinfo = QULIST.get()
vodbt_url = sex8_root + '/' + vinfo['yuan_url']
vodbt_html = download_html(vodbt_url, result_type='sex8')
if vodbt_html:
soup = BeautifulSoup(vodbt_html, 'lxml')
vinfo['title'] = soup.find('span',
id="thread_subject").get_text()
vodbt_html = str(
soup.find('td',
attrs={'id': re.compile('postmessage_[0-9]*')}))
description = re.findall(r'【影片(.*?)</div>', vodbt_html, re.S)
if description:
vinfo['description'] = html("【影片{0}".format(
description[0]))
else:
vinfo['description'] = '暂无简介'
#预览图片
vinfo['images'] = ''
images_arr = soup.find_all('img',
attrs={
'class': 'zoom',
'lazyloadthumb': '1'
})[0:-2]
if images_arr:
if len(images_arr) > 0:
try:
for img in images_arr:
vinfo['images'] += img['file'] + '$'
# bt 种子
vinfo['bt_url'] = soup.find(
'span',
attrs={'id': re.compile('attach_[0-9]*')})
if vinfo['bt_url']:
vinfo['bt_url'] = vinfo['bt_url'].a['href']
vinfo['vkey'] = ikey()
vinfo['en_title'] = en(vinfo['title'])
vinfo['inputtime'] = getTime()
# 插入到数据库
sql = get_sql(vinfo, vod_type[1])
insert(sql)
RUN_COUNT += 1
except KeyError as e:
pass
time.sleep(1)
QULIST.task_done()
def get_vodbt(self):
global QULIST
global RUN_COUNT
vinfo = {}
while not QULIST.empty():
vinfo = QULIST.get()
vodbt_url = taohuazu_root + '/' + vinfo['yuan_url']
vodbt_html = download_html(vodbt_url)
if vodbt_html:
soup = BeautifulSoup(vodbt_html, 'lxml')
vinfo['title'] = soup.find('span',
id="thread_subject").get_text()
vodbt_html = str(soup.find('div', class_="t_fsz"))
soup = BeautifulSoup(vodbt_html, 'lxml')
vinfo['vkey'] = ikey()
vinfo['en_title'] = en(vinfo['title'])
description = re.findall(
r'<td class="t_f" id="postmessage_[0-9]*">(.*?)<ignore_js_op>',
vodbt_html, re.S)
if description:
vinfo['description'] = html(strip(description[0]))
else:
vinfo['description'] = '暂无简介'
# 预览图片
vinfo['images'] = ''
images_arr = soup.find_all('img', attrs={'class': 'zoom'})
for img in images_arr:
vinfo['images'] += img['file'] + '$'
# bt 种子链接
bt_html = soup.find_all("dl", class_="tattl")
vinfo['bt_url'] = ''
for item_bt in bt_html:
soup = BeautifulSoup(str(item_bt), "lxml")
aid = str(soup.find("a")['href']).split('?')[1]
vinfo['bt_url'] += taohuazu_bt_api + aid + "$"
vinfo['inputtime'] = getTime()
# 插入到数据库
sql = get_sql(vinfo, vod_type[1])
insert(sql)
RUN_COUNT += 1
time.sleep(1)
QULIST.task_done()
def pron91_do(self):
global QULIST
global RUN_COUNT
while not QULIST.empty():
vinfo = QULIST.get()
play_html = download_html(vinfo['yuan_url'])
if play_html != '' and len(play_html) > 0:
v_url = re.findall(r'<source src="(.*?)" type=\'video\/mp4\'>',
play_html, re.S)
if v_url:
vinfo['play_url'] = v_url[0]
vinfo['description'] = "暂无简介"
# 插入数据
sql = get_sql(vinfo, vod_type[0])
insert(sql=sql)
RUN_COUNT += 1
time.sleep(1)
QULIST.task_done()
def get_vod_av(self):
global QULIST
global RUN_COUNT
while not QULIST.empty():
vinfo = {}
vod_url = QULIST.get()
url = taoyin_root + '/' + vod_url
# 解析单个视频
html = download_html(url=url)
if html:
soup = BeautifulSoup(html, 'lxml')
vid_html1 = soup.find_all('div', id="tylongvideo")
vid = 0
if vid_html1:
vid = vid_html1[0]['datav']
else:
vid_html2 = soup.find_all('div', id="tylongvideo")
if vid_html2:
vid = vid_html2[0]['datav']
title_html = soup.find_all(id="thread_subject")
if title_html and vid != 0:
vinfo['vkey'] = ikey()
vinfo['title'] = title_html[0].get_text()
vinfo['en_title'] = en(vinfo['title'])
vinfo['description'] = "暂无简介"
vinfo['images'] = taoyin_image_av(vid)
vinfo['vod_long'] = ""
vinfo['yuan_url'] = vod_url
vinfo['play_url'] = taoyin_video_av(vid)
vinfo['play_type'] = online_type[1]
vinfo['movie_type'] = movie_type[3]
vinfo['inputtime'] = getTime()
# 插入数据
sql = get_sql(vinfo, vod_type[0])
insert(sql=sql)
RUN_COUNT += 1
time.sleep(1)
QULIST.task_done()
def get_vod(self):
global QULIST
global RUN_COUNT
while not QULIST.empty():
vinfo = QULIST.get()
vod_url = papax_root + vinfo['yuan_url']
html = download_html(vod_url)
if html:
soup = BeautifulSoup(html, 'lxml')
vod_iframe = soup.find('iframe')
if vod_iframe:
play_iframe_url = papax_root + vod_iframe['src']
play_iframe_html = download_html(play_iframe_url)
if play_iframe_html:
soup = BeautifulSoup(play_iframe_html, 'lxml')
video_url = soup.find('video')
if video_url:
video_url = video_url['src']
video_url = papax_root + video_url.replace(
'../../..', '')
vinfo['vkey'] = ikey()
vinfo['play_url'] = video_url
vinfo['play_type'] = online_type[1]
vinfo['en_title'] = en(vinfo['title'])
vinfo['description'] = "暂无简介"
vinfo['vod_long'] = ''
vinfo['inputtime'] = getTime()
sql = get_sql(vinfo, vod_type[0])
# 插入到数据库
insert(sql=sql)
RUN_COUNT += 1
time.sleep(1)
QULIST.task_done()