def search(meta_info, user_setting):
plugin_name = config.get_info('en').get('name')
meta_data_list = []
video_title = meta_info.get('video_title')
part_file = meta_info.get('part_file')
movie_type = ''
title_style = ''
log('info', 'title:%s' % video_title, plugin_name)
# code is the formatted media name which is used to check if it is already in cache
code = 'formatted file name'
cache_data = check_cache(code, get_info('en').get('name'))
if cache_data:
meta_data_list.append(cache_data)
else:
# search for meta data from internet
meta_data = MetaData()
meta_data_list.append(meta_data)
return meta_data_list
def analysis_media_html_byxpath(self, html, q):
"""
根据html对象与xpath解析数据
html:<object>
html_xpath_dict:<dict>
return:<dict{issuccess,ex,dict}>
"""
'''
xpath_number = "//div[@class='item_register']//table[@class='item']//tr[8]/td[2]/text()"
number = html.xpath(xpath_number)
if len(number) > 0:
number = self.tools.cleanstr(number[0])
media.number = number
'''
media = MetaData()
number = self.tools.cleanstr(q.upper())
media.number = number
xpath_title = "//div[@class='detail_title_new2']/table/tr/td[2]/h1"
title = html.xpath(xpath_title)
if len(title) > 0:
title = self.tools.cleanstr(title[0].text)
media.title = title
xpath_poster = "//table[@class='item_detail']//tr[1]//td[1]//a//img[@class='item_img']/@src"
poster = html.xpath(xpath_poster)
if len(poster) > 0:
poster = self.tools.cleanstr(poster[0])
media.poster = 'https:%s' % poster
media.thumbnail = 'https:%s' % poster
xpath_summary = "//table[@class='item_detail']//tr[2]//td[@class='text']//div[@class='item_text']/text()"
summary = html.xpath(xpath_summary)
if len(summary) > 0:
summary = self.tools.cleanstr(summary[1])
media.summary = summary
xpath_studio = "//div[@class='item_register']/table[@class='item']//tr[2]/td[2]/a"
studio = html.xpath(xpath_studio)
if len(studio) > 0:
studio = self.tools.cleanstr(studio[0].text)
media.studio = studio
xpath_directors = "//table[@class='item']//tr[5]//td[2]/a"
directors = html.xpath(xpath_directors)
if len(directors) > 0:
directors = self.tools.cleanstr(directors[0].text)
media.directors = directors
xpath_collections = "//table[@class='item']//tr[4]//td[2]//a"
collections = html.xpath(xpath_collections)
if collections[0].text is not None:
collections = self.tools.cleanstr(collections[0].text)
media.collections = collections
xpath_year = "//table[@class='item']//tr[6]/td[2]/text()"
year = html.xpath(xpath_year)
if len(year) > 0:
year = self.tools.cleanstr(year[0])
media.year = self.tools.formatdatetime(year)
xpath_originally_available_at = "//table[@class='item']//tr[6]/td[2]/text()"
originally_available_at = html.xpath(xpath_originally_available_at)
if len(originally_available_at) > 0:
originally_available_at = self.tools.cleanstr(
originally_available_at[0])
media.originally_available_at = self.tools.formatdatetime(
originally_available_at)
xpath_category = "//div[@id='adultgenre2']//table//tr/td[2]//ul//li/a"
categorys = html.xpath(xpath_category)
category_list = []
for category in categorys:
category_list.append(self.tools.cleanstr(category.text))
categorys = ','.join(category_list)
if len(categorys) > 0:
media.category = categorys
actor = {}
xpath_actor_name = "//div[@class='item_register']//table[@class='item']//tr[1]/td[2]//a"
xpath_actor_url = "//div[@class='item_register']//table[@class='item']//tr[1]/td[2]/a/@href"
actor_name = html.xpath(xpath_actor_name)
actor_url = html.xpath(xpath_actor_url)
if len(actor_name) > 0:
for i, actorname in enumerate(actor_name):
html = self.get_html_byurl('https://www.arzon.jp%s' %
actor_url[i])
if html['issuccess']:
xpath_actor_image = "//table[@class='p_list1']//img/@src"
actorimageurl = html['html'].xpath(xpath_actor_image)
actor.update({actorname.text: 'https:%s' % actorimageurl[0]})
media.actor = actor
return media
def analysisMediaHtmlByxpath(self, html, q):
"""
根据html对象与xpath解析数据
html:<object>
html_xpath_dict:<dict>
return:<dict{issuccess,ex,dict}>
"""
media = MetaData()
number = self.tools.cleanstr(q.upper())
media.number = number
xpath_title = "/html/body/div[2]/div/div[1]/h3"
title = html.xpath(xpath_title)[0].text
media.title = title
summary = title
media.summary = summary
xpath_poster_url = "//*[@id='slider']/ul[1]/li[1]/img"
poster_url = 'https://' + self.basicUrl + html.xpath(
xpath_poster_url)[0].attrib['src']
media.poster = poster_url
media.thumbnail = poster_url
studio = 'FC2'
media.studio = studio
directors = ''
media.directors = directors
xpath_collections = "/html/body/div[2]/div/div[1]/h5[3]/a[1]"
collections = html.xpath(xpath_collections)[0].text
media.collections = collections
year = ''
media.year = year
media.originally_available_at = year
xpath_category = "/html/body/div[2]/div/div[1]/h5[6]/a"
categorys = html.xpath(xpath_category)
category_list = []
for category in categorys:
category_list.append(self.tools.cleanstr(category.text))
categorys = ','.join(category_list)
if len(categorys) > 0:
media.category = categorys
xpath_actor_name = "/html/body/div[2]/div/div[1]/h5[5]/a"
actor_name = html.xpath(xpath_actor_name)[0].text
if actor_name != '':
media.actor = actor_name
return media
def analysis_media_html_byxpath(self, html, q):
"""
根据html对象与xpath解析数据
html:<object>
html_xpath_dict:<dict>
return:<dict{issuccess,ex,dict}>
"""
'''
xpath_number = "//div[@class='col-md-3 info']/p[1]/span[2]/text()"
number = html.xpath(xpath_number)
if len(number) > 0:
number = self.tools.cleanstr(number[0])
self.media.number = number
'''
media = MetaData()
number = self.tools.cleanstr(q.upper())
media.number = number
xpath_title = "//div[@class='container']/h3/text()"
title = html.xpath(xpath_title)
if len(title) > 0:
title = self.tools.cleantitlenumber(self.tools.cleanstr(title[0]),
number)
media.title = title
xpath_poster = "//div[@class='col-md-9 screencap']/a[@class='bigImage']/img/@src"
poster = html.xpath(xpath_poster)
if len(poster) > 0:
poster = self.checkUrl + self.tools.cleanstr(poster[0])
media.poster = poster
media.thumbnail = poster
xpath_studio = "//div[@class='col-md-3 info']/p[5]/a/text()"
studio = html.xpath(xpath_studio)
if len(studio) > 0:
studio = self.tools.cleanstr(studio[0])
media.studio = studio
xpath_directors = "//div[@class='col-md-3 info']/p[4]/a/text()"
directors = html.xpath(xpath_directors)
if len(directors) > 0:
directors = self.tools.cleanstr(directors[0])
media.directors = directors
xpath_collections = "//div[@class='col-md-3 info']/p[6]/a/text()"
collections = html.xpath(xpath_collections)
if len(collections) > 0:
collections = self.tools.cleanstr(collections[0])
media.collections = collections
xpath_year = "/html/body/div[@class='container']/div[@class='row movie']/div[@class='col-md-3 info']/p[2]/text()"
year = html.xpath(xpath_year)
if len(year) > 0:
year = self.tools.cleanstr(year[0])
media.originally_available_at = year
media.year = year
xpath_category = "/html/body/div[@class='container']/div[@class='row movie']/div[@class='col-md-3 info']/p[8]/span[@class='genre']/a"
categorys = html.xpath(xpath_category)
category_list = []
for category in categorys:
category_list.append(self.tools.cleanstr(category.text))
categorys = ','.join(category_list)
if len(categorys) > 0:
media.category = categorys
actor = {}
xpath_actor_name = "/html/body/div[5]/div[1]/div[2]/p/span/a"
xpath_actor_url = "//div[@id='star-div']//img/@src"
actor_name = html.xpath(xpath_actor_name)
actor_url = html.xpath(xpath_actor_url)
if len(actor_name) > 0:
for i, actorname in enumerate(actor_name):
if actor_url[i].find('nowprinting') > 0:
actor.update({actorname.text: ''})
else:
actor.update(
{actorname.text: self.checkUrl + actor_url[i]})
media.actor = actor
return media
def analysisMediaHtmlByxpath(self, html, q):
"""
根据html对象与xpath解析数据
html:<object>
html_xpath_dict:<dict>
return:<dict{issuccess,ex,dict}>
"""
media = MetaData()
number = self.tools.cleanstr(q.upper())
media.number = number
media.web = 'caribbean'
xpath_title = "//*[@id='moviepages']/div/div[1]/div[1]/div[2]/h1"
title = html.xpath(xpath_title)[0].text
media.title = title
xpath_summary = "//*[@id='moviepages']/div/div[1]/div[1]/p"
summary = html.xpath(xpath_summary)[0].text
media.summary = summary
media.poster = 'https://%s/moviepages/%s/images/l_l.jpg' % (self.basicUrl, number)
media.thumbnail = 'https://%s/moviepages/%s/images/l_l.jpg' % (self.basicUrl, number)
studio = 'Caribbeancom'
media.studio = studio
directors = ''
media.directors = directors
collections = 'Caribbeancom'
media.collections = collections
xpath_year = "//*[@id='moviepages']/div/div[1]/div[1]/ul/li[2]/span[2]"
year = html.xpath(xpath_year)[0].text
media.year = year
media.originally_available_at = year
xpath_category = "//*[@id='moviepages']/div/div[1]/div[1]/ul/li[4]/span[2]/a"
categorys = html.xpath(xpath_category)
category_list = []
for category in categorys:
category_list.append(self.tools.cleanstr(category.text))
categorys = ','.join(category_list)
if len(categorys) > 0:
media.category = categorys
xpath_actor_name = "//*[@id='moviepages']/div/div[1]/div[1]/ul/li[1]/span[2]/a/span"
actor_name = html.xpath(xpath_actor_name)
actor_dict = {}
for actor in actor_name:
actor_dict[actor.text] = 'https://images.d2pass.com/images/d2p_toolbar/images/d2p_logo.png'
media.actor = actor_dict
return media
def analysisMediaHtmlByxpath(self, html, q):
"""
根据html对象与xpath解析数据
html:<object>
html_xpath_dict:<dict>
return:<dict{issuccess,ex,dict}>
"""
media = MetaData()
number = self.tools.cleanstr(q.upper())
media.number = number
media.web = 'caribbeancompr'
xpath_title = "//*[@id='moviepages']/div/div[2]/div[1]/div/div[2]/h1"
title = html.xpath(xpath_title)[0].text
# if len(title) > 0:
# title = self.tools.cleantitlenumber(
# self.tools.cleanstr(title[0]), number)
media.title = title
xpath_summary = "//*[@id='moviepages']/div/div[2]/div[1]/div/p"
summary = html.xpath(xpath_summary)[0].text
media.summary = summary
media.poster = 'https://%s/moviepages/%s/images/l_l.jpg' % (
self.basicUrl, number)
media.thumbnail = 'https://%s/moviepages/%s/images/l_l.jpg' % (
self.basicUrl, number)
studio = 'Caribbeancompr'
media.studio = studio
directors = ''
media.directors = directors
collections = 'Caribbeancompr'
media.collections = collections
xpath_year = "//li[@class='movie-spec'][2]/span[@class='spec-content']/text()"
year = html.xpath(xpath_year)
if len(year) > 0:
year = self.tools.cleanstr(year[0])
media.year = year
media.originally_available_at = year
xpath_category = "//li[@class='movie-spec'][5]/span[@class='spec-content']/a/text()"
categorys = html.xpath(xpath_category)
category_list = []
for category in categorys:
category_list.append(self.tools.cleanstr(category))
categorys = ','.join(category_list)
if len(categorys) > 0:
media.category = categorys
actor = {}
xpath_actor_name = "//li[@class='movie-spec'][1]/span[@class='spec-content']/a"
actor_name = html.xpath(xpath_actor_name)
if len(actor_name) > 0:
for i, actorname in enumerate(actor_name):
actor.update({actorname.text: ''})
media.actor = actor
return media
def analysis_media_html_byxpath(self, html, q):
"""
根据html对象与xpath解析数据
html:<object>
html_xpath_dict:<dict>
return:<dict{issuccess,ex,dict}>
"""
media = MetaData()
number = self.tools.cleanstr(q.upper())
media.number = number
xpath_title = "//div[@id='main']/h1/text()"
title = html.xpath(xpath_title)
if len(title) > 0:
title = self.tools.cleantitlenumber(self.tools.cleanstr(title[0]),
number)
media.title = title
xpath_summary = "//dd[@class='comment']/div/text()"
summary = html.xpath(xpath_summary)
if len(summary) > 0:
summary = summary[0]
media.summary = summary
# xpath_poster = "//img/@src"
# poster = html.xpath(xpath_poster)
# if len(poster) > 0:
# poster = self.tools.cleanstr(poster[0])
media.poster = 'https://www.pacopacomama.com/moviepages/%s/images/poster_en.jpg' % number
media.thumbnail = 'https://www.pacopacomama.com/moviepages/%s/images/l/1.jpg' % number
# xpath_studio = "//div[@class='col-md-3 info']/p[5]/a/text()"
# studio = html.xpath(xpath_studio)
# if len(studio) > 0:
studio = 'PacoPacoMama'
media.studio = studio
# xpath_directors = "//div[@class='col-md-3 info']/p[4]/a/text()"
# directors = html.xpath(xpath_directors)
# if len(directors) > 0:
directors = ''
media.directors = directors
# xpath_collections = "//div[@class='col-md-3 info']/p[6]/a/text()"
# collections = html.xpath(xpath_collections)
# if len(collections) > 0:
collections = 'PacoPacoMama'
media.collections = collections
xpath_year = "//div[@class='movie-info']/dl[3]/dd"
year = html.xpath(xpath_year)
if len(year) > 0:
year = self.tools.cleanstr(year[0].text)
media.year = year
media.originally_available_at = year
xpath_category = "//div[@class='clearfix']/table/tr[4]/td[2]/a/text()"
categorys = html.xpath(xpath_category)
category_list = []
for category in categorys:
category_list.append(self.tools.cleanstr(category))
categorys = ','.join(category_list)
if len(categorys) > 0:
media.category = categorys
actor = {}
xpath_actor_name = "//div[@class='clearfix']/table/tr[1]/td[2]/a/text()"
xpath_actor_url = "//div[@class='clearfix']/img[@class='lefty']/@src"
actor_name = html.xpath(xpath_actor_name)
actor_url = 'https://www.pacopacomama.com%s' % html.xpath(
xpath_actor_url)[0]
if len(actor_name) > 0:
for i, actorname in enumerate(actor_name):
actorimageurl = actor_url
actor.update({self.tools.cleanstr2(actorname): actorimageurl})
# actor.update({self.tools.cleanstr2(
# actorname): ''})
media.actor = actor
return media
def analysis_media_html_byxpath(self, html, q):
"""
根据html对象与xpath解析数据
html:<object>
html_xpath_dict:<dict>
return:<dict{issuccess,ex,dict}>
"""
'''
xpath_number = "//div[@class='col-md-3 info']/p[1]/span[2]/text()"
number = html.xpath(xpath_number)
if len(number) > 0:
number = self.tools.cleanstr(number[0])
self.media.number = number
'''
media = MetaData()
number = 'heyzo-%s' % self.tools.cleanstr(q.upper())
media.number = number
xpath_title = "//div[@id='wrapper']/article/section[1]/div[@id='movie']/h1/text()"
title = html.xpath(xpath_title)
if len(title) > 0:
title = self.tools.cleantitlenumber(self.tools.cleanstr(title[0]),
number)
media.title = title
xpath_summary = "//p[@class='memo']/text()"
summary = html.xpath(xpath_summary)
if len(summary) > 0:
summary = summary[0]
media.summary = summary
media.poster = 'https://www.heyzo.com/contents/3000/%s/images/player_thumbnail.jpg' % q
media.thumbnail = 'https://www.heyzo.com/contents/3000/%s/gallery/001.jpg' % q
media.studio = 'Heyzo'
xpath_collections = "//tr[@class='table-series']/td[2]/text()"
collections = html.xpath(xpath_collections)
if len(collections) > 0:
collections = self.tools.cleanstr(collections[0])
if not collections == '-----':
media.collections = collections
xpath_year = "//tr[@class='table-release-day']/td[2]/text()"
year = html.xpath(xpath_year)
if len(year) > 0:
year = self.tools.cleanstr(year[0])
media.year = year
media.originally_available_at = year
xpath_category = "//ul[@class='tag-keyword-list']/li/a/text()"
categorys = html.xpath(xpath_category)
category_list = []
for category in categorys:
category_list.append(self.tools.cleanstr(category))
categorys = ','.join(category_list)
if len(categorys) > 0:
media.category = categorys
actor = {}
xpath_actor_name = "//tr[@class='table-actor']/td//a/span/text()"
#xpath_actor_url = "//tr[@class='table-actor']/td//a/@href"
actor_name = html.xpath(xpath_actor_name)
#actor_url = html.xpath(xpath_actor_url)
if len(actor_name) > 0:
for i, actorname in enumerate(actor_name):
# if actor_url[i].find('nowprinting') > 0:
# actor.update({actorname: ''})
# else:
actor.update({actorname: ''})
media.actor = actor
return media
def analysis_media_html_byxpath(self, html, q):
"""
根据html对象与xpath解析数据
html:<object>
html_xpath_dict:<dict>
return:<dict{issuccess,ex,dict}>
"""
media = MetaData()
title = q.upper()
media.title = title
number = self.tools.cleanstr(q.upper())
media.number = number
xpath_poster = "//div[@class='column']/img[@class='image']/@src"
poster = html.xpath(xpath_poster)
if len(poster) > 0:
poster = self.tools.cleanstr(poster[0])
media.poster = poster
media.thumbnail = poster
xpath_summary = "//p[@class='level has-text-grey-dark']/text()"
summary = html.xpath(xpath_summary)
if len(summary) > 0:
summary = summary[0]
media.summary = summary + ''
xpath_year = "//p[@class='subtitle is-6']/a/text()"
year = html.xpath(xpath_year)
if len(year) > 0:
year = self.tools.dateconvert(year[0])
media.year = year
media.originally_available_at = year
xpath_category = "//div[@class='tags']//a/text()"
categorys = html.xpath(xpath_category)
category_list = []
for category in categorys:
category_list.append(self.tools.cleanstr(category))
categorys = ','.join(category_list)
if len(categorys) > 0:
media.category = categorys
actor = {}
xpath_actor_name = "//a[@class='panel-block']"
actor_name = html.xpath(xpath_actor_name)
if len(actor_name) > 0:
for i, actorname in enumerate(actor_name):
actor.update({actorname.text: ''})
media.actor = actor
return media
def analysis_media_html_byxpath(self, browser, q):
media = MetaData()
browser.get("https://www.1pondo.tv/movies/%s/" % q)
btn_xpath = "//button[@class='button-flat button-medium button-icon--right see-more']"
btn = browser.find_elements_by_xpath(btn_xpath)
if len(btn) == 0:
return []
btn[0].click()
time.sleep(1)
number = self.tools.cleanstr(q.upper())
media.number = number
media.web = 'onePondo'
# title
title_xpath = "//h1[@class='h1--dense']"
title = browser.find_elements_by_xpath(title_xpath)
media.title = title[0].text
summary_xpath = "//div[@class='movie-info section divider']/div[@class='movie-detail']/p"
summary = browser.find_elements_by_xpath(summary_xpath)
media.summary = summary[0].text
media.poster = 'https://www.1pondo.tv/assets/sample/%s/str.jpg' % number
media.thumbnail = 'https://www.1pondo.tv/assets/sample/%s/str.jpg' % number
media.studio = '一本道'
# Collection
collection_xpath = "//li[@class='movie-detail__spec'][3]/span[@class='spec-content']"
Collection = browser.find_elements_by_xpath(collection_xpath)
media.collections = Collection[0].text
# datatime
datatime_xpath = "//li[@class='movie-detail__spec'][1]/span[@class='spec-content']"
datatime = browser.find_elements_by_xpath(datatime_xpath)
media.year = datatime[0].text
media.originally_available_at = datatime[0].text
# types
categorys_xpath = "//span[@class='spec-content']/a[@class='spec__tag']"
categorys = browser.find_elements_by_xpath(categorys_xpath)
categorys_list = []
for item in categorys:
categorys_list.append(self.tools.cleanstr(item.text))
categorys = ','.join(categorys_list)
if len(categorys) > 0:
media.category = categorys
# actor
actor = {}
xpath_actor_name = "//li[@class='movie-detail__spec'][2]/span[@class='spec-content']"
actor_name = browser.find_elements_by_xpath(xpath_actor_name)
if len(actor_name) > 0:
for i, actorname in enumerate(actor_name):
actor.update({self.tools.cleanstr2(
actorname.text): ''})
media.actor = actor
return media
def analysis_media_html_byxpath(self, browser, q):
media = MetaData()
infos_xpath = "//div[@class='detail_data']"
infos = browser.find_elements_by_xpath(infos_xpath)
info_list = infos[0].text.split('\n')
for info in info_list:
tmp = info.split('：')
if len(tmp) > 1:
keyword = self.tools.cleanstr(tmp[0])
value = tmp[1]
if keyword == '出演': # actor
actor = {}
actor_name = []
actor_name.append(self.tools.cleanstr(value))
if len(actor_name) > 0:
for i, actorname in enumerate(actor_name):
actor.update(
{self.tools.cleanstr2(actorname): ''})
media.actor = actor
if keyword == 'メーカー': # 工作室
media.studio = self.tools.cleanstr(value)
if keyword == '品番': # 番号
media.number = self.tools.cleanstr(value)
if keyword == '配信開始日': # 日期
media.year = self.tools.formatdatetime(self.tools.cleanstr(value))
media.originally_available_at = self.tools.formatdatetime(self.tools.cleanstr(value))
if keyword == 'シリーズ': # 系列
media.collections = self.tools.cleanstr2(self.tools.cleanstr(value))
if keyword == 'ジャンル': # 类型
# types
categorys = value.split(' ')
while '' in categorys:
categorys.remove('')
categorys_list = []
for item in categorys:
categorys_list.append(self.tools.cleanstr(item))
categorys = ','.join(categorys_list)
if len(categorys) > 0:
media.category = categorys
# title
title_xpath = "//h1[@class='tag']"
title = browser.find_elements_by_xpath(title_xpath)
media.title = self.tools.cleanstr(title[0].text)
more_xpath = "//p[@id='introduction_all']"
more = browser.find_elements_by_xpath(more_xpath)
if not more[0].get_attribute("style") == 'display: none;':
more[0].click()
summary_xpath = "//p[@class='txt introduction']"
summary = browser.find_elements_by_xpath(summary_xpath)
media.summary = summary[0].text
poster_xpath = "//a[@id='EnlargeImage']"
poster = browser.find_elements_by_xpath(poster_xpath)
media.poster = poster[0].get_attribute('href')
art_xpath = "//div[@class='detail_left']/dl[@id='sample-photo']/dd/ul/li[1]/a[@class='sample_image']"
art = browser.find_elements_by_xpath(art_xpath)
media.thumbnail = art[0].get_attribute('href')
return media
def search(meta_info, user_setting):
score = MATCH_SCORE
plugin_name = config.get_info('en').get('name')
meta_data_list = []
if meta_info.get('media_type') == 'album':
if meta_info.get('name'):
file_name = meta_info.get('name')
score = MATCH_ALBUM
else:
file_name = clear_file_name(meta_info.get('file_name'))
elif meta_info.get('media_type') == 'artist':
if meta_info.get('file_name'):
file_name = clear_file_name(meta_info.get('file_name'))
else:
file_name = ''
score = MATCH_ARTIST
else:
return meta_data_list
log('info', 'title:%s' % file_name, plugin_name)
code = get_code(file_name, meta_info)
result = None
cache_data = check_cache(code, get_info('en').get('name'))
if cache_data:
return cache_data
else:
# search for meta data from internet
results = search_song_by_code(code)
sort_result(results, code)
highest_result = get_highest_result(results)
if not highest_result:
return meta_data_list
if highest_result.get('score') >= score:
result = highest_result
if not result:
return meta_data_list
get_artist_info(result)
get_album_info(result)
get_hot_comment(result)
meta_data = MetaData()
# Album
album = Album()
album.title = result.get('album').get('name')
if result.get('album').get('description'):
album.summary = result.get('album').get('description')
album.studio = result.get('album').get('company')
album.tags = result.get('album').get('tags')
album.collections = result.get('album').get('subType')
album.poster = get_picture_base64(result.get('album').get('picUrl'))
album.originally_available_at = datetime.datetime.fromtimestamp(
result.get('album').get('publishTime') / 1000).strftime('%Y-%m-%d')
for review in result['reviews'].get('topComments'):
album.reviews.append(
review.get('user').get('nickname') + ': ' + review.get('content'))
for review in result['reviews'].get('hotComments'):
album.reviews.append(
review.get('user').get('nickname') + ': ' + review.get('content'))
if user_setting.get('hotComment'):
album.summary += '\n 网易云热门评论： '
for review in album.reviews:
album.summary += '\n ' + review.replace('\n', '')
meta_data.album = album
# Artist
for result_artist in result.get('artists'):
artist = Artist()
artist.poster = get_picture_base64(result_artist.get('cover'))
artist.art = get_picture_base64(result_artist.get('cover'))
title = result_artist.get('name')
if title == 'Various Artists' or title == '[Unknown Artist]':
title = '未知艺术家'
artist.title = title
if result_artist.get('identifyTag'):
artist.tags = ','.join(result_artist.get('identifyTag'))
artist.summary = ''
if result_artist.get('briefDesc'):
artist.summary = result_artist.get('briefDesc')
if result_artist.get('rank'):
rank = result_artist.get('rank')
rank_type = ['', '华语', '欧美', '韩国', '日本']
rank_string = '\n歌手排行：' + str(
rank_type[rank.get('type')]) + '地区：' + str(rank.get('rank'))
artist.summary += rank_string
if result_artist.get('albumSize'):
artist.summary += '\n歌手专辑数：' + str(result_artist.get('albumSize'))
if result_artist.get('musicSize'):
artist.summary += '\n歌手音乐数：' + str(result_artist.get('musicSize'))
if result_artist.get('mvSize'):
artist.summary += '\n歌手MV数：' + str(result_artist.get('mvSize'))
meta_data.artist.append(artist)
meta_data.code = code
meta_data_list.append(meta_data)
return meta_data_list
def analysis_media_html_byxpath(self, browser, q):
"""
根据html对象与xpath解析数据
html:<object>
html_xpath_dict:<dict>
return:<dict{issuccess,ex,dict}>
"""
codeList = []
imgnumber = ''
re_list = re.finditer(
r'[0-9]{4}\D[0-9]{1,5}|[0-9]{4}\D(Q|q)[0-9]{1,5}|[0-9]{4}\D(.{3})\D[0-9]{4}|[0-9]{4}\D(.{3})\D[0-9]{6}\D[0-9]{3}',
q, re.IGNORECASE)
for item in re_list:
imgnumber = item.group()
codeList.append(item.group())
browser.get('https://www.heydouga.com/moviepages/%s/index.html' % q)
media = MetaData()
media.number = q.replace('/', '-')
xpath_title = "//div[@id='title-bg']/h1"
title = browser.find_elements_by_xpath(xpath_title)[0].text
if len(title) > 0:
title = self.tools.cleanstr(title)
media.title = title
xpath_summary = "//div[@class='movie-description']/p"
summary = browser.find_elements_by_xpath(xpath_summary)[0].text
if len(summary) > 0:
summary = self.tools.cleanstr(summary)
media.summary = summary
media.poster = 'https://www.heydouga.com/contents/%s/player_thumb.jpg' % self.format(
imgnumber)
media.thumbnail = 'https://www.heydouga.com/contents/%s/player_thumb.jpg' % self.format(
imgnumber)
#xpath_studio = "//div[@class='col-md-3 info']/p[5]/a/text()"
#studio = html.xpath(xpath_studio)
# if len(studio) > 0:
#studio = self.tools.cleanstr(studio[0])
media.studio = 'heydouga'
# xpath_directors = "//div[@class='col-md-3 info']/p[4]/a/text()"
# directors = html.xpath(xpath_directors)
# if len(directors) > 0:
# directors = self.tools.cleanstr(directors[0])
# media.directors = directors
# xpath_collections = "//div[@class='col-md-3 info']/p[6]/a/text()"
# collections = html.xpath(xpath_collections)
# if len(collections) > 0:
# collections = self.tools.cleanstr(collections[0])
media.collections = 'heydouga'
xpath_year = "//div[@id='movie-info']//li[1]/span[2]"
year = browser.find_elements_by_xpath(xpath_year)[0].text
if len(year) > 0:
media.year = year
media.originally_available_at = year
xpath_category = "//ul[@id='movie_tag_list']/li/a"
categorys = browser.find_elements_by_xpath(xpath_category)
category_list = []
for category in categorys:
category_list.append(self.tools.cleanstr(category.text))
categorys = ','.join(category_list)
if len(categorys) > 0:
media.category = categorys
actor = {}
xpath_actor_name = "//div[@id='movie-info']/ul/li[2]/span[2]/a"
#xpath_actor_url = "//div[@id='star-div']//img/@src"
actor_name = browser.find_elements_by_xpath(xpath_actor_name)
#actor_url = html.xpath(xpath_actor_url)
if len(actor_name) > 0:
actor_names = actor_name[0].text.split(' ')
for actorname in actor_names:
# if actor_url[i].find('nowprinting') > 0:
# actor.update({actorname: ''})
# else:
actor.update({actorname: ''})
media.actor = actor
return media
def analysis_media_html_byxpath(self, html, q):
"""
根据html对象与xpath解析数据
html:<object>
html_xpath_dict:<dict>
return:<dict{issuccess,ex,dict}>
"""
media = MetaData()
number = self.tools.cleanstr(q.upper())
media.number = number
media.web = 'javr'
studio_text = ''
xpath_p = "//div[@class='post-metadata']/p"
p_list = html.xpath(xpath_p)
for i in range(len(p_list)):
lab = html.xpath('%s[%s]/b/text()' % (xpath_p, (i + 1)))
if lab[0] == 'Studio:':
studio = html.xpath('%s[%s]//text()' % (xpath_p, (i + 1)))[2]
xpath_title = "//h1[@class='entry-title1']/text()"
title = html.xpath(xpath_title)
title = title[0].replace('Watch XXX Japanese P**n - ',
'').replace(studio, '')
media.title = title
media.summary = title
xpath_poster = "//img[@id='myvidcover']/@src"
post_url_list = html.xpath(xpath_poster)
for post_url in post_url_list:
if len(re.findall('data:image', post_url)) < 1:
media.poster = post_url
media.thumbnail = post_url
media.studio = studio
directors = ''
media.directors = directors
xpath_category = "//div[@class='categories tags cactus-info']/a/text()"
categorys = html.xpath(xpath_category)
category_list = []
for category in categorys:
category_list.append(self.tools.cleanstr(category))
categorys = ','.join(category_list)
if len(categorys) > 0:
media.category = categorys
actor = {}
xpath_actor_name = "//div[@class='channel-content']//a/h4/text()"
xpath_actor_url = "//div[@class='post-metadata sp-style style-5']//a/img/@data-src"
actor_name = html.xpath(xpath_actor_name)
actor_url = html.xpath(xpath_actor_url)
if len(actor_name) > 0:
for i, actorname in enumerate(actor_name):
try:
actor.update({actorname: actor_url[i]})
except Exception as ex:
actor.update({
actorname:
'https://ravecloud.xyz/2019/02/javraveclublogo_41.png'
})
media.actor = actor
return media
def analysis_media_html_byxpath(self, html, q):
"""
根据html对象与xpath解析数据
html:<object>
html_xpath_dict:<dict>
return:<dict{issuccess,ex,dict}>
"""
number = self.tools.cleanstr(q.upper())
media = MetaData()
xpath_title = "//dl[@class='list-spec cf']/dd[1]/text()"
title = html.xpath(xpath_title)
if len(title) > 0:
title = self.tools.cleantitlenumber(
self.tools.cleanstr(title[0]), number)
media.title = title
xpath_summary = "//div[@class='detail-info__item'][2]/p[@class='detail-info__comment']/text()"
summary = html.xpath(xpath_summary)
if len(summary) > 0:
summary = summary[0]
media.summary = summary
# xpath_poster = "//img/@src"
# poster = html.xpath(xpath_poster)
# if len(poster) > 0:
# poster = self.tools.cleanstr(poster[0])
media.poster = 'https://www.10musume.com/moviepages//%s/images/list1.jpg' % number
media.thumbnail = 'https://www.10musume.com/moviepages//%s/images/g_b001.jpg' % number
# xpath_studio = "//div[@class='col-md-3 info']/p[5]/a/text()"
# studio = html.xpath(xpath_studio)
# if len(studio) > 0:
studio = '素人専門アダルト動画'
media.studio = studio
# xpath_directors = "//div[@class='col-md-3 info']/p[4]/a/text()"
# directors = html.xpath(xpath_directors)
# if len(directors) > 0:
directors = ''
media.directors = directors
# xpath_collections = "//div[@class='col-md-3 info']/p[6]/a/text()"
# collections = html.xpath(xpath_collections)
# if len(collections) > 0:
collections = '天然むすめ'
media.collections = collections
xpath_year = "//dl[@class='list-spec cf']/dd[2]/text()"
year = html.xpath(xpath_year)
if len(year) > 0:
year = self.tools.cleanstr(year[0])
self.media.year = year
self.media.originally_available_at = year
xpath_category = "//dl[@class='list-spec cf']/dd[7]/a/text()"
categorys = html.xpath(xpath_category)
category_list = []
for category in categorys:
category_list.append(self.tools.cleanstr(category))
categorys = ','.join(category_list)
if len(categorys) > 0:
media.category = categorys
actor = {}
xpath_actor_name = "//dl[@class='list-spec cf']/dd[4]/a/text()"
# xpath_actor_url = "//div[@class='video-performer']/a/img/@style"
actor_name = html.xpath(xpath_actor_name)
# actor_url = html.xpath(xpath_actor_url)
if len(actor_name) > 0:
for i, actorname in enumerate(actor_name):
# actorimageurl = actor_url[i].replace('background-image:url(', '').replace(');', '')
'''
actor.update({self.tools.cleanstr2(
actorname): actorimageurl})
'''
actor.update({self.tools.cleanstr2(
actorname): ''})
media.actor = actor
return media