def findinfo(articleid, mode='uid'):
if mode == 'link':
url = articleid
html = get_html_jp(url)
page1 = re.findall(r'/digital/videoa/-/list/=/.*/id=\d+/page=(\d+)/',
html)
title = re.findall(r'<title>(.*) - エロ動画・アダルトビデオ - FANZA動画</title>',
html)
elif mode == 'uid':
url = "https://www.dmm.co.jp/digital/videoa/-/list/=/article=actress/id=%s/" % articleid
html = get_html_jp(url)
page1 = re.findall(
r'/digital/videoa/-/list/=/article=actress/id=\d+/page=(\d+)/',
html)
title = re.findall(r'<title>(.*) - エロ動画・アダルトビデオ - FANZA動画</title>',
html)
if page1 == []:
page1 = 1
else:
page3 = []
for i in page1:
if i not in page3:
page3.append(int(i))
page4 = max(page3)
page1 = page4
return (page1, title[0])
def precid(searchcid):
searchurl = 'https://www.dmm.co.jp/mono/dvd/-/detail/=/cid={}/'.format(
searchcid)
html = get_html_jp(searchurl)
soup = BeautifulSoup(html, 'lxml')
title = soup.title.string
body = soup.find('table', attrs={'class': 'mg-b20'})
title = soup.title.string
red = soup.find('span', attrs={'class': 'red'}).string
title = red + title
photo = soup.find('div', attrs={'class': 'tx10 pd-3 lh4'}).a.get('href')
pushdate = body.find_all('tr')[0].find('td').find_next_sibling().string
time = body.find_all('tr')[1].find('td').find_next_sibling().string
performer = body.find_all('tr')[2].find(
'td').find_next_sibling().span.a.string
num = body.find_all('tr')[-1].find('td').find_next_sibling().string
text = '''
`{}`
[DVD ]({})
*発売日:*{}
*収録時間:*{}
*出演者:*{}
*品番:* `{}`
[官方信息]({})
'''.format(title, photo, pushdate, time, performer, num, searchurl)
return text
def new_work(self):
url = 'https://faleno.jp/top/work/'
response = get_html_jp(url, verify=False)
soup = BeautifulSoup(response, 'lxml')
title = soup.title.string
body = soup.find('div', attrs={'class': 'box_kanren01'})
results = body.find_all('div', attrs={'class': 'waku_kanren01'})
boxlist = []
for i in results:
boxdict = {}
liv = i.find('a')
imgs = i.find('img')
url = liv.get('href')
boxdict['url'] = url
work = re.findall(r'https://faleno.jp/top/works/(.*)/',
str(url))[0]
boxdict['work'] = work
name = imgs.get('alt')
boxdict['name'] = name
img = imgs.get('src')
boxdict['img'] = img
boxlist.append(boxdict)
env = Environment(loader=PackageLoader(__name__,
"templates")) # 创建一个包加载器对象
template = env.get_template('faleno.md') # 获取一个模板文件
temp_out = template.render(data=boxlist, title=str(title))
#print(temp_out) # 渲染
return (temp_out)
def actress(self):
url = 'https://faleno.jp/top/actress/'
response = get_html_jp(url, verify=False)
soup = BeautifulSoup(response, 'lxml')
title = soup.find('section', attrs={'class': 'bread'}).p.contents[1]
group = soup.find_all('li', attrs={'data-mh': 'group01'})
groups = []
for i in group:
box = {}
links = i.a.get('href')
name = i.find('div', attrs={'class': 'text_name'})
id = re.findall(
r'<div class="text_name">(.*)<span>(.*)</span></div>',
str(name))[0]
actress = id[0]
eng_name = id[1]
box['links'] = links
box['name'] = actress
box['eng'] = eng_name
groups.append(box)
env = Environment(loader=PackageLoader(__name__,
"templates")) # 创建一个包加载器对象
template = env.get_template('faleno_actress.md') # 获取一个模板文件
temp_out = template.render(data=groups, title=str(title))
#print(temp_out) # 渲染
return (temp_out)
def photo(self, id):
url = 'https://faleno.jp/top/works/%s' % id
response = get_html_jp(url, verify=False)
soup = BeautifulSoup(response, 'lxml')
photos = soup.find_all('a', attrs={'class': 'pop_img'})
photo = []
for i in photos:
photo.append(i.get('href'))
return (photo)
def dmmonecid(searchcid):
searchcid = searchcid.replace('-', '00')
searchurl = 'https://www.dmm.co.jp/digital/videoa/-/detail/=/cid={}/'.format(
searchcid)
html = get_html_jp(searchurl)
ciddataa, notitle = ciddata(html)
if ciddataa == '指定されたページが見つかりません':
return ciddataa, notitle
temp_out = template_cid(ciddataa)
return temp_out, notitle
def dmmcid(in_q, out_q):
while in_q.empty() is not True:
url = in_q.get()
#url = 'https://www.dmm.co.jp/digital/videoa/-/list/=/article=actress/id=1060823/'
html = get_html_jp(url)
list = re.findall(
r'https://www.dmm.co.jp/digital/videoa/-/detail/=/cid=([_0-9a-z]+)/',
html)
#print(url,list)
out_q.append(list)
in_q.task_done()
def prephotos(searchurl):
#print(searchurl)
html = get_html_jp(searchurl)
soup = BeautifulSoup(html, 'lxml')
photourlss = soup.find_all('img', attrs={'class': 'mg-b6'})
photourls = re.findall(
r'(https://pics.dmm.co.jp/digital/video/.*?/.*?.jpg)', str(photourlss))
photolist = list(photourls)
#print(photolist)
jpg = []
for i in photolist:
ii = list(i)
ii.insert(-6, 'jp')
iii = ''.join(ii)
iii = iii.replace('-jp', 'jp-', 1)
jpg.append(iii)
return (jpg)
def work(self, id):
url = 'https://faleno.jp/top/works/%s' % id
response = get_html_jp(url, verify=False)
soup = BeautifulSoup(response, 'lxml')
box = {}
img = soup.find('a', attrs={'class': 'pop_sample'}).img.get('src')
box['img'] = img
title = soup.find('a', attrs={'class': 'pop_sample'}).img.get('alt')
text = soup.find('div', attrs={'class': 'box_works01_text'}).p.string
box['text'] = text
file = soup.find_all('li', attrs={'class': 'clearfix'})
box['url'] = url
for i in file:
box[i.find(text=True).strip()] = i.p.string
env = Environment(loader=PackageLoader(__name__,
"templates")) # 创建一个包加载器对象
template = env.get_template('faleno_work.md') # 获取一个模板文件
temp_out = template.render(data=box, title=str(title))
#print(temp_out) # 渲染
return (temp_out)
def actress_work(self, name):
name = name.replace(' ', '_').lower()
url = 'https://faleno.jp/top/actress/%s/' % name
response = get_html_jp(url, verify=False)
soup = BeautifulSoup(response, 'lxml')
profile = {}
title = soup.title.string
bar = soup.find('div', attrs={'class': 'bar02'}).h1
barr = re.findall(r'<h1>(.*)<span>(.*)</span></h1>', str(bar))[0]
img = soup.find('div', attrs={
'class': 'box_actress02_left'
}).img.get('src')
files = soup.find('div', attrs={
'class': 'box_actress02_right'
}).find_all('li', attrs={'class': 'clearfix'})
box = {}
for i in files:
box[i.find(text=True).strip()] = i.p.string
body = soup.find('div', attrs={'class': 'box_kanren01'})
results = body.find_all('div', attrs={'class': 'waku_kanren01'})
boxlist = []
for i in results:
boxdict = {}
liv = i.find('a')
imgs = i.find('img')
url = liv.get('href')
work = re.findall(r'https://faleno.jp/top/works/(.*)/',
str(url))[0]
boxdict['work'] = work
boxdict['url'] = url
name = imgs.get('alt')
boxdict['name'] = name
img = imgs.get('src')
boxdict['img'] = img
boxlist.append(boxdict)
env = Environment(loader=PackageLoader(__name__,
"templates")) # 创建一个包加载器对象
template = env.get_template('faleno.md') # 获取一个模板文件
temp_out = template.render(data=boxlist, title=str(title))
#print(temp_out) # 渲染
return (temp_out)
def search(self, word, searchmode='temp'):
url = 'https://faleno.jp/top/?s=%s' % word
response = get_html_jp(url, verify=False)
soup = BeautifulSoup(response, 'lxml')
title = soup.find('section', attrs={'class': 'bread'}).p.contents[1]
try:
ifresult = re.findall(r'に一致する作品は見つかりませんでした', str(soup))
noresult = "{}(没有找到相应内容的作品):{}".format(ifresult, title)
if 'に一致する作品は見つかりませんでした' in ifresult:
return noresult
except Exception as e:
print(e)
results = soup.find_all('div', attrs={'class': 'waku_kanren01'})
#print(title)
boxlist = []
for i in results:
boxdict = {}
liv = i.find('a')
imgs = i.find('img')
url = liv.get('href')
work = re.findall(r'https://faleno.jp/top/works/(.*)/',
str(url))[0]
boxdict['work'] = work
boxdict['url'] = url
name = imgs.get('alt')
boxdict['name'] = name
img = imgs.get('src')
boxdict['img'] = img
boxlist.append(boxdict)
if searchmode == 'search':
return boxlist
if searchmode == 'temp':
env = Environment(loader=PackageLoader(__name__,
"templates")) # 创建一个包加载器对象
template = env.get_template('faleno.md') # 获取一个模板文件
temp_out = template.render(data=boxlist, title=str(title))
#print(temp_out) # 渲染
return (temp_out)
def dmmsearchall_data(searchstr):
#url = 'https://www.dmm.co.jp/digital/videoa/-/list/search/=/?searchstr=乙白さやか'
url = 'https://www.dmm.co.jp/search/=/searchstr={}/sort=rankprofile/'.format(
searchstr)
html = get_html_jp(url)
#判断有无结果
result = re.findall(r'(に一致する商品は見つかりませんでした。)', html)
noresult = 'に一致する商品は見つかりませんでした。'
try:
if noresult in result:
stitle = 1
return (noresult, stitle)
except Exception:
pass
soup = BeautifulSoup(html, 'lxml')
searchbody = soup.find('div', attrs={'class': 'd-area'})
try:
stitle = re.findall(r'<title>(.*?)</title>', html)[0]
except Exception:
stitle = '検索結果'
boxall = searchbody.find('div', attrs={'class': 'd-sect'})
onebox = str(boxall).split('<div>')
boxlist = []
for box in onebox:
boxdict = {}
notitle = 0
if box:
try:
litetitle = re.findall(r'<span class=\"txt\">(.*?)</span>',
box)[0]
#print(litetitle)
if litetitle == None:
notitle = 1
except:
notitle = 1
try:
cid = re.findall(
r'<a href=\"https://www\.dmm\.co\.jp/.*?/cid=(\w+)/\?.*?\">',
box)[0]
boxdict['cid'] = cid
except:
boxdict['cid'] = '-'
try:
keywords = re.findall(
r'<span class=\"ico-\w+-\w+\"><span>(.*?)</span></span>',
box)
keyword = ','.join(keywords)
boxdict['keyword'] = keyword
except:
boxdict['keyword'] = '-'
try:
links = re.findall(
r'<a href=\"(https://www\.dmm\.co\.jp/.*?-/detail/=/cid=\w+/\?.*?)\">',
box)[0]
boxdict['links'] = links
except:
boxdict['links'] = '-'
try:
img = re.findall(r'(pics\.dmm\.co\.jp/.*?/\w+/\w+.jpg)',
box)[0]
boxdict['img'] = img
except Exception as e:
boxdict['img'] = '-'
try:
title = re.findall(r'alt=\"(.*)\" src', box)[0]
boxdict['title'] = title
except Exception as e:
boxdict['title'] = '-'
try:
sublinks = re.findall(
r'<span><a href=\"(.*?)\">.*?</a></span>', box)
boxdict['sublinks'] = sublinks[0]
except Exception as e:
boxdict['sublinks'] = '-'
try:
subtexts = re.findall(
r'<span><a href=\".*?\">(.*?)</a></span>', box)[0]
boxdict['subtexts'] = subtexts
except:
boxdict['subtexts'] = '-'
if notitle == 0:
#print(boxdict)
boxlist.append(boxdict)
return (boxlist, stitle)
def dmmlinks_data(links):
#url = 'https://www.dmm.co.jp/digital/videoa/-/list/search/=/?searchstr=乙白さやか'
url = links
html = get_html_jp(url)
#判断有无结果
soup = BeautifulSoup(html, 'lxml')
searchbody = soup.find('div', attrs={'class': 'd-area'})
try:
stitle = re.findall(r'<title>(.*?)</title>', html)[0]
#print(stitle)
except Exception:
stitle = '検索結果'
boxall = searchbody.find_all('li', attrs={'style': 'width: 130px;'})
onebox = str(boxall).split('</div></li>')
boxlist = []
for box in onebox:
boxdict = {}
notitle = 0
if box:
try:
litetitle = re.findall(r'<span class=\"txt\">(.*?)</span>',
box)[0]
# print(litetitle)
if litetitle == None:
notitle = 1
except:
notitle = 1
try:
cid = re.findall(r'https://www\.dmm\.co\.jp/.*?/cid=(\w+)/',
box)[0]
boxdict['cid'] = cid
except Exception as e:
boxdict['cid'] = '-'
try:
keywords = re.findall(
r'<span class=\"ico-\w+-\w+\"><span>(.*?)</span></span>',
box)
keyword = ','.join(keywords)
boxdict['keyword'] = keyword
except:
boxdict['keyword'] = '-'
try:
links = re.findall(r'(https://www\.dmm\.co\.jp/.*?/cid=\w+/)',
box)[0]
boxdict['links'] = links
except:
boxdict['links'] = '-'
try:
img = re.findall(r'(pics\.dmm\.co\.jp/.*?/\w+/\w+.jpg)', box)
boxdict['img'] = img[0]
except:
boxdict['img'] = '-'
try:
title = re.findall(r'alt=\"(.*)\" src', box)
boxdict['title'] = title[0]
except:
boxdict['title'] = '-'
try:
sublinks = re.findall(r'span><a href=\"(.*?)\">.*?</a></span>',
box)
sublink = 'https://www.dmm.co.jp' + sublinks[0]
boxdict['sublinks'] = sublink
except:
boxdict['sublinks'] = '-'
try:
subtexts = re.findall(
r'<span><a href=\".*?\">(.*?)</a></span>', box)
boxdict['subtexts'] = subtexts[0]
except:
boxdict['subtexts'] = '-'
if notitle == 0:
#print(boxdict)
boxlist.append(boxdict)
return (boxlist, stitle)
def video(self, id):
url = 'https://faleno.jp/top/works/%s' % id
response = get_html_jp(url, verify=False)
soup = BeautifulSoup(response, 'lxml')
video = soup.find('a', attrs={'class': 'pop_sample'}).get('href')
return (video)
