def parse_photos(self, r, id):
data = []
page = etree.HTML(r)
lis = page.xpath(
u'//div[@class="article"]/ul[@class="poster-col3 clearfix"]/li')
if len(lis) > 0:
for x in lis:
temp = {}
temp['doubanvid'] = id
temp['doubanid'] = x.get('data-id')
name_el = x.find('div[@class="name"]')
prop_el = x.find('div[@class="prop"]')
cover = x.find('div[@class="cover"]/a')
if name_el != None:
temp['name'] = name_el.text.replace(u'\n', '')
temp['name'] = parse_simple(temp['name'])
if prop_el != None:
temp['prop'] = prop_el.text.replace(u'\n', '')
temp['prop'] = temp['prop'].strip(u' ')
m = re.search(u'(\d{1,})x(\d{1,})',
temp['prop'].replace(" ", ""))
if m:
temp['width'] = m.group(1)
temp['height'] = m.group(2)
if cover != None:
temp['photos_page'] = cover.get("href")
temp['url'] = cover.find('img').get("src")
temp['url'] = re.sub(u'/photo/m/', '/photo/l/',
temp['url'])
data.append(temp)
nextpage = page.xpath(u'//a[contains(text(),"后页")]')
if len(nextpage) > 0:
return {"data": data, "next": nextpage[0].get("href")}
return {"data": data}
def parse_star_show(self, r, url):
"""
解析明星主页
return:dic
"""
try:
# r.decode('utf-8')
page = etree.HTML(r)
except Exception as e:
return None
info_el = page.xpath('//div[@id="starInfo"]/dl/dd[@class="info"]/span')
sub_list = {
u"别名": u'alias',
u"性别": u'gender',
u"地区": u'area',
u"出生地": u'birthplace',
u'生日': u'birthday',
u'星座': u'constellation',
u"血型": u'blood',
u"职业": u'occupation'
}
info_list = [re.split(u'：', parse_simple(x.text)) for x in info_el]
for x in xrange(0, len(info_list)):
info_list[x][0] = re.sub(info_list[x][0],
sub_list[info_list[x][0]],
info_list[x][0])
info_data = {x[0]: x[1] for x in info_list}
avatar = page.xpath(u'.//div[@class="box-avatar"]/img')
if len(avatar) > 0:
info_data['avatar'] = avatar[0].get("src")
info_data.name = page.xpath('//div[@id="starInfo"]')[0].get(
'data-name')
info_data.youku_starid = page.xpath('//div[@id="starInfo"]')[0].get(
'data-starid')
m = re.search(u'\/(uid_\w*\d*=*)\.html', url)
info_data['youku_uid'] = m.group(1) if m != None else None
info_data['created_at'] = int(time.time() * 1000)
intro = page.xpath('//dd[@class="intro"]/span[@class="long noshow"]')
info_data['youku_url'] = url
if len(intro) > 0:
info_data['intro'] = intro[0].text
return info_data
def vdetail_parser(self, r, url=None):
"""视频详情页面"""
try:
page = etree.HTML(r)
except Exception as e:
return False
L = Contents()
result_div = page.xpath(u'//div[@class="mod_search_topic"]')
if result_div:
result_div = page.xpath(u'//div[@class="mod_reuslt"]')
title = result_div.xpath(u'//h1[@class="main_title"]/a')
if len(title) > 0:
L.title = title[0].text
sub_title = result_div.xpath(u'//span[@class="sub_title"]')
if len(sub_title) > 0:
L.sub_title = sub_title[0].text
if re.search(u'(\d{4})', L.sub_title):
L.year = re.search(u'(\d{4})', L.sub_title).group(1)
category = page.xpath(u'//a[@class="channelTag"]')
if len(category) > 0:
L.category = category[0].text
area = result_div.xpath(u'//em[contains(text(),"地区")]/a')
if len(area) > 0:
L.area = area[0].text
L.iqiyi_tvId = self.get_vid_by_url(url)
language = result_div.xpath(u'//em[contains(text(),"语言")]/a')
if len(language) > 0:
L.language = language[0].text
tags = result_div.xpath(u'//em[contains(text(),"类型")]/a')
if len(tags) > 0:
_temp = [x.text for x in tags]
L.tags = ",".join(set(_temp))
banben = result_div.xpath(u'//em[contains(text(),"版本")]/a')
if len(banben) > 0:
L.banben = banben[0].text
summary = result_div.xpath(u'//em[contains(text(),"简介")]')
if len(summary) > 0:
L.summary = result_div.xpath(
u'//em[contains(text(),"简介")]/following::text()[1]')[0]
L.summary = parse_simple(L.summary)
all_episode = result_div.xpath(u'//em[contains(text(),"集数")]/a')
if len(all_episode) > 0:
L.all_episode = self.parse_all_episode(all_episode[0].text)
iqiyi_play_url = result_div.xpath(u'//a[contains(text(),"立即播放")]')
if len(iqiyi_play_url) > 0:
L.iqiyi_play_url = iqiyi_play_url[0].get("href")
iqiyi_plays_num = result_div.xpath(u'//i[@id="widget-playcount"]')
if len(iqiyi_plays_num) > 0:
L.iqiyi_plays_num = iqiyi_plays_num[0].text
peiyin = result_div.xpath(u'//em[contains(text(),"配音")]/a')
if len(peiyin) > 0:
L.peiyin_list = []
_temp = []
for x in peiyin:
_temp.append(peiyin[0].text)
L.peiyin_list.append({"name": peiyin[0].text, "iqiyi_url": x.get(
"href"), "iqiyi_id": self.get_starId_by_url(x.get("href"))})
L.peiyin = ",".join(set(_temp))
iqiyi_rating = page.xpath(u'//span[@class="score_font"]')
if len(iqiyi_rating) > 0:
L.iqiyi_rating = iqiyi_rating[0].get("snsscore")
poster = page.xpath(u'//div[@contains(@_stat,"result_pic"]/img')
if len(poster) > 0:
L.poster = {"url": poster[0].get("src"), "width": poster[0].get(
"width"), "height": poster[0].get("height"), "name": poster[0].get("alt")}
L.img_url = L.poster['url']
# 导演演员
# actor_list = page.xpath(u'//ul[@class="actor_list cf"]/li/')
# starring_list = []
# starring = []
# directors_list = []
# directors = []
return L.__dict__
def start_detail(self, r, url=None):
'''明星信息解析'''
try:
page = etree.HTML(r)
except Exception as e:
return False
S = Star()
S.iqiyi_url = url
m = re.search(u'"circleId"\:(\d*)', r) # paopao id
if m:
S.iqiyi_circleId = m.group(1)
avatar = page.xpath(u'.//div[@class="result_pic"]/img')
if len(avatar) > 0:
S.avatar = avatar[0].get("src")
S.name = avatar[0].get("alt")
result_detail = page.xpath(u'.//div[@class="result_detail"]')
if len(result_detail) > 0:
name = result_detail[0].xpath(u'.//h1[@itemprop="name"]')
if len(name) > 0:
S.name = parse_simple(name[0].text)
occupation = page.xpath(u'//span[contains(text(),"职业")]')
if len(occupation) > 0:
S.occupation = page.xpath(
u'//span[contains(text(),"职业")]/following::text()[1]')[0]
S.occupation = self.parse_occupation(S.occupation)
date_birth = page.xpath(u'//span[contains(text(),"生日")]')
if len(date_birth) > 0:
S.date_birth = page.xpath(
u'//span[contains(text(),"生日")]/following::text()[1]')[0]
S.date_birth = parse_simple(self.parse_date_birth(S.date_birth))
area = page.xpath(u'//span[contains(text(),"地区")]')
if len(area) > 0:
S.area = page.xpath(
u'//span[contains(text(),"地区")]/following::text()[1]')[0]
S.area = self.parse_area(S.area)
body_weight = page.xpath(u'//span[contains(text(),"体重")]')
if len(body_weight) > 0:
S.body_weight = page.xpath(
u'//span[contains(text(),"体重")]/following::text()[1]')[0]
S.body_weight = self.parse_weight(S.body_weight)
foreign_name = page.xpath(u'//dt[contains(text(),"外文名")]')
if len(foreign_name) > 0:
S.foreign_name = parse_simple(foreign_name[0].getnext().text)
gender = page.xpath(u'//dt[contains(text(),"性别")]')
if len(gender) > 0:
S.gender = parse_simple(gender[0].getnext().text)
body_height = page.xpath(u'//dt[contains(text(),"身高")]')
if len(body_height) > 0:
S.body_height = parse_simple(body_height[0].getnext().text)
birthplace = page.xpath(u'//dt[contains(text(),"出生地")]')
if len(birthplace) > 0:
S.birthplace = parse_simple(birthplace[0].getnext().text)
date_birth = page.xpath(u'//dt[contains(text(),"出生日期")]')
if len(date_birth) > 0:
S.date_birth = parse_simple(date_birth[0].getnext().text)
graduated_school = page.xpath(u'//dt[contains(text(),"毕业院校")]')
if len(graduated_school) > 0:
S.graduated_school = parse_simple(
graduated_school[0].getnext().text)
famous_times = page.xpath(u'//dt[contains(text(),"成名年代")]')
if len(famous_times) > 0:
S.famous_times = parse_simple(famous_times[0].getnext().text)
alias = page.xpath(u'//dt[contains(text(),"别名")]')
if len(alias) > 0:
S.alias = parse_simple(alias[0].getnext().text)
blood = page.xpath(u'//dt[contains(text(),"血型")]')
if len(blood) > 0:
S.blood = parse_simple(blood[0].getnext().text)
constellation = page.xpath(u'//dt[contains(text(),"星座")]')
if len(constellation) > 0:
S.constellation = parse_simple(constellation[0].getnext().text)
current_residence = page.xpath(u'//dt[contains(text(),"现居地")]')
if len(current_residence) > 0:
S.current_residence = parse_simple(
current_residence[0].getnext().text)
agency = page.xpath(u'//dt[contains(text(),"经纪公司")]')
if len(agency) > 0:
S.agency = parse_simple(agency[0].getnext().text)
hobbies = page.xpath(u'//dt[contains(text(),"爱好")]')
if len(hobbies) > 0:
S.hobbies = parse_simple(hobbies[0].getnext().text)
intro = page.xpath(u'//p[@class="introduce-info"]')
if len(intro):
S.intro = "".join(page.xpath(u'//p[@class="introduce-info"]/text()'))
S.intro = parse_simple(S.intro)
if not S.name:
return False
S.created_at = time.time()
return S.__dict__
def baike_parser(r,url=None):
try:
r = re.sub(u' ','',r)
page = etree.HTML(r)
except Exception as e:
return False
L = Contents()
summary = page.xpath(u'//div[@class="lemmaWgt-lemmaSummary lemmaWgt-lemmaSummary-light"]')
if len(summary) > 0:
L.summary = summary[0].text
title = page.xpath(u'//dt[contains(text(),"中文名")]')
if len(title) > 0:
L.title = parse_simple(title[0].getnext().text)
foreign_title = page.xpath(u'//dt[contains(text(),"外文名")]')
if len(foreign_title) > 0:
L.foreign_title = parse_simple(foreign_title[0].getnext().text)
production_company = page.xpath(u'//dt[contains(text(),"出品公司")]')
if len(production_company) > 0:
L.production_company = parse_simple(production_company[0].getnext().text)
producer_country = page.xpath(u'//dt[contains(text(),"制片地区")]')
if len(producer_country) > 0:
L.producer_country = area_process(parse_simple(producer_country[0].getnext().text))
directors_list = page.xpath(u'//dt[contains(text(),"导演")]')
if len(directors_list) > 0:
a_tag = directors_list[0].getnext().findall('a')
if len(a_tag) > 0:
L.directors_list = []
directors = []
for x in a_tag:
L.directors_list.append({"name":parse_simple(x.text),"baike_id":x.get("data-lemmaid"),"baike_url":u'https://baike.baidu.com'+x.get("href")})
directors.append(parse_simple(x.text))
L.directors = ",".join(set(directors))
else:
L.directors = area_process(parse_simple(directors_list[0].getnext().text))
screenwriter_list = page.xpath(u'//dt[contains(text(),"编剧")]')
if len(screenwriter_list) > 0:
a_tag = screenwriter_list[0].getnext().findall('a')
if len(a_tag) > 0:
L.screenwriter_list = []
screenwriters = []
for x in a_tag:
L.screenwriter_list.append({"name":parse_simple(x.text),"baike_id":x.get("data-lemmaid"),"baike_url":u'https://baike.baidu.com'+x.get("href")})
screenwriters.append(parse_simple(x.text))
L.screenwriters = ",".join(set(screenwriters))
else:
L.screenwriters = area_process(parse_simple(screenwriter_list[0].getnext().text))
starring_list = page.xpath(u'//dt[contains(text(),"主演")]')
if len(starring_list) > 0:
a_tag = starring_list[0].getnext().findall('a')
if len(a_tag) > 0:
L.starring_list = []
starring = []
for x in a_tag:
L.starring_list.append({"name":parse_simple(x.text),"baike_id":x.get("data-lemmaid"),"baike_url":u'https://baike.baidu.com'+x.get("href")})
starring.append(parse_simple(x.text))
L.starring = ",".join(set(starring))
else:
L.starring = area_process(parse_simple(starring_list[0].getnext().text))
alias = page.xpath(u'//dt[contains(text(),"其它译名")]')
if len(alias) > 0:
a_tag = alias[0].getnext().findall("a")
if len(a_tag) > 0:
L.alias = ",".join([parse_simple(x.text) for x in a_tag if parse_simple(x.text)])
else:
L.alias = parse_simple(alias[0].getnext().text)
types = page.xpath(u'//dt[contains(text(),"类型")]')
if len(types) > 0:
L.type = area_process(parse_simple(types[0].getnext().text))
duration = page.xpath(u'//dt[contains(text(),"片长")]')
if len(duration) > 0:
L.duration = area_process(parse_simple(duration[0].getnext().text))
release_date = page.xpath(u'//dt[contains(text(),"上映时间")]')
if len(release_date) > 0:
L.release_date = area_process(parse_simple(release_date[0].getnext().text))
release_date = page.xpath(u'//dt[contains(text(),"语言")]')
if len(release_date) > 0:
L.language = language_process(parse_simple(release_date[0].getnext().text))
douban_rating = page.xpath(u'//span[contains(@class,"star-text")]')
if len(douban_rating) > 0:
L.douban_rating = douban_rating[0].text
poster = page.xpath(u'//img[@alt="词条图片"]')
if len(poster) > 0:
L.poster = [{"url":poster[0].get("src"),"name":poster[0].get("alt")}]
L.img_url = poster[0].get("src")
actor_list = page.xpath(u'//ul[@class="actorList"]/li')
if len(actor_list) > 0:
starring = L.starring.split(',')
L.actor_list = []
starring_list = []
for x in actor_list:
_temp = {"avatar":x.find('img').get("src"),"name":x.xpath(u'//dl[@class="info"]/a')[0].text,"baike_id":x.xpath(u'//dl[@class="info"]/a')[0].get("data-lemmaid"),"baidu_url":"https://baike.baidu.com"+x.xpath(u'//dl[@class="info"]/a')[0].get("href")}
if _temp['name'] in starring:
starring_list.append(_temp)
else:
L.actor_list.append(_temp)
if starring_list:
L.starring_list = starring_list
L.created_at = time.time()
return L.__dict__
def vdetail_parser(self, r):
data = Contents()
try:
page = etree.HTML(r)
except Exception as e:
return False
year = re.search(u'<span class="year">\((\d{4})\)</span>', r)
if year:
data.year = year.group(1)
title = re.search(u'<span property="v\:itemreviewed">(.*)</span>', r)
if title:
data.title = title.group(1)
bianju = page.xpath(u'//span[contains(text(),"编剧")]')
if len(bianju) > 0:
bianju_a = bianju[0].getnext()
if bianju_a is not None:
bianju_a = bianju_a.findall('a')
data.screenwriter_list = []
screenwriters = ''
for x in bianju_a:
screenwriters = screenwriters + parse_simple(x.text) + ","
_temp = {}
if re.search(u'/celebrity/(\d*)/', x.get("href")):
_temp["doubanid"] = re.search(u'/celebrity/(\d*)/',
x.get("href")).group(1)
else:
# doubanid = x.get("href")
pass
if x.get("href"):
_temp[
"douban_url"] = "https://movie.douban.com" + x.get(
"href")
_temp["name"] = parse_simple(x.text)
data.screenwriter_list.append(_temp)
data.screenwriters = screenwriters.strip(',')
directors_el = page.xpath(u'//span[contains(text(),"导演")]')
if len(directors_el) > 0:
directors_a = directors_el[0].getnext()
if directors_a is not None:
directors_a = directors_a.findall('a')
data.directors_list = []
directors = ""
for x in directors_a:
directors = directors + parse_simple(x.text) + ","
_temp = {}
if re.search(u'/celebrity/(\d*)/', x.get("href")):
_temp["doubanid"] = re.search(u'/celebrity/(\d*)/',
x.get("href")).group(1)
else:
# doubanid = x.get("href")
pass
if x.get("href"):
_temp[
"douban_url"] = "https://movie.douban.com" + x.get(
"href")
_temp["name"] = parse_simple(x.text)
data.directors_list.append(_temp)
data.directors = directors.strip(',')
starring_el = page.xpath(u'//span[contains(text(),"主演")]')
if len(starring_el) > 0:
starring_a = starring_el[0].getnext()
if starring_a is not None:
starring_a = starring_a.findall('a')
data.starring_list = []
starring = ""
for x in starring_a:
starring = starring + parse_simple(x.text) + ","
_temp = {}
if re.search(u'/celebrity/(\d*)/', x.get("href")):
_temp["doubanid"] = re.search(u'/celebrity/(\d*)/',
x.get("href")).group(1)
else:
# doubanid = x.get("href")
pass
if x.get("href"):
_temp[
"douban_url"] = "https://movie.douban.com" + x.get(
"href")
_temp["name"] = parse_simple(x.text)
data.starring_list.append(_temp)
starring = starring.strip(',')
data.starring = starring
type_el = page.xpath(u'//span[@property="v:genre"]') # 类型
mvtype = []
if len(type_el) > 0:
for x in type_el:
mvtype.append(parse_simple(x.text))
tags = page.xpath(u'//div[@class="tags-body"]/a')
_temp = []
for x in tags:
_temp.append(parse_simple(x.text))
_temp = _temp + mvtype
data.tags = ",".join(set(_temp))
producer_country_el = page.xpath(
u'//span[contains(text(),"制片国家/地区:")]')
if len(producer_country_el) > 0:
producer_country = page.xpath(
u'//span[contains(text(),"制片国家/地区:")]/following::text()[1]')[0]
data.producer_country = area_process(
split_space(producer_country.replace('/', ',')))
language_el = page.xpath(u'//span[contains(text(),"语言:")]')
if len(language_el) > 0:
language = page.xpath(
u'//span[contains(text(),"语言:")]/following::text()[1]')[0]
data.language = language_process(
split_space(language.replace('/', ',')))
all_episode = page.xpath(u'//span[contains(text(),"集数:")]')
if len(all_episode) > 0:
all_episode = page.xpath(
u'//span[contains(text(),"集数:")]/following::text()[1]')[0]
m = re.search(u'(\d{1,})', all_episode.replace(" ", ""))
if m:
data.all_episode = m.group(1)
episode_time = page.xpath(u'//span[contains(text(),"单集片长:")]')
if len(episode_time) > 0:
episode = page.xpath(
u'//span[contains(text(),"单集片长:")]/following::text()[1]')[0]
m = re.search(u'(\d{1,})', episode.replace(" ", ""))
if m:
data.duration = m.group(1)
season = page.xpath(
u'//select[@id="season"]/option[@selected="selected"]') #season季数
if len(season) > 0:
data.season = season[0].text
release_date_el = page.xpath(
u'//span[@property="v:initialReleaseDate"]') #首播
if len(release_date_el) > 0:
release_date = ""
for x in release_date_el:
release_date = release_date + parse_simple(x.text) + "|"
release_date = release_date.strip('|')
m = re.search(u'(\d{4}-\d{2}-\d{2})',
release_date.replace(" ", ""))
if m:
data.release_date = m.group(1)
else:
data.release_date = release_date
duration_el = page.xpath(u'//span[@property="v:runtime"]')
if len(duration_el) > 0:
m = re.search(u'(\d{1,})', duration_el[0].text.replace(" ", ''))
if m:
data.duration = m.group(1) # 片长
alias_al = page.xpath(u'//span[contains(text(),"又名:")]')
if len(alias_al) > 0:
alias = page.xpath(
u'//span[contains(text(),"又名:")]/following::text()[1]')[0]
data.alias = split_space(alias.replace('/', ','))
IMDb_el = page.xpath(u'//span[contains(text(),"IMDb链接")]')
if len(IMDb_el) > 0:
data.IMDb = IMDb_el[0].getnext().get("href")
rating = re.search(u'property="v\:average">(\d*\.\d*)</strong>', r)
if rating:
data.douban_rating = rating.group(1)
rating_sum = page.xpath(u'//span[@property="v:votes"]')
if len(rating_sum) > 0:
data.douban_rating_sum = rating_sum[0].text
summary_all = page.xpath(u'//span[@class="all hidden"]')
summary = page.xpath(u'//span[@property="v:summary"]')
if len(summary_all) > 0:
data.summary = ''.join(
page.xpath(u'//span[@class="all hidden"]/text()'))
data.summary = parse_simple(data.summary)
elif len(summary) > 0:
data.summary = ''.join(
page.xpath(u'//span[@property="v:summary"]/text()'))
data.summary = parse_simple(data.summary)
img_url = page.xpath(u'//img[@title="点击看更多海报"]')
nbgnbg = page.xpath(u'//a[@title="点击看大图" and @class="nbgnbg"]')
if len(img_url) > 0:
data.img_url = page.xpath(u'//img[@title="点击看更多海报"]')[0].get("src")
elif len(nbgnbg) > 0:
data.img_url = nbgnbg[0].get("href")
if data.all_episode > 1 and (u"动漫" in data.tags or u"动画" in data.tags):
data.category = u"动漫"
elif data.all_episode > 1 and (u"综艺" in data.tags
or u'真人秀' in data.tags):
data.category = u'综艺'
elif data.all_episode > 1:
data.category = u"电视剧"
elif u"动漫" in data.tags or u"动画" in data.tags:
data.category = u'动漫'
elif u"短片" in data.tags:
data.category = u'短片'
else:
data.category = u'电影'
m = re.search(u"SUBJECT_ID: *'(\d*)'", r)
if m:
data.doubanid = m.group(1)
print(
"oooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooo"
)
print(data.__dict__)
print(
"oooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooo"
)
return data.__dict__
def parse_star(self, r, url):
try:
page = etree.HTML(r)
except Exception as e:
return False
data = Star()
name = page.xpath(u'//div[@id="content"]/h1')
if len(name) > 0:
data.name = parse_simple(name[0].text)
else:
return False
m = re.search(u'celebrity/(\d*)/', url)
if m:
data.doubanid = m.group(1)
imgUrl = page.xpath(u'//div[@class="pic"]/a[@class="nbg"]')
if len(imgUrl) > 0:
data.avatar = imgUrl[0].get("href")
gender = page.xpath(
u'//span[contains(text(),"性别")]/following::text()[1]')
if len(gender):
gender = re.sub('\n', '', gender[0])
gender = gender.strip(':')
data.gender = parse_simple(gender.strip(' '))
constellation = page.xpath(
u'//span[contains(text(),"星座")]/following::text()[1]')
if len(constellation) > 0:
constellation = re.sub('\n', '', constellation[0])
constellation = constellation.strip(':')
data.constellation = parse_simple(constellation.strip(' '))
date_birth = page.xpath(
u'//span[contains(text(),"出生日期")]/following::text()[1]')
if len(date_birth) > 0:
date_birth = re.sub('\n', '', date_birth[0])
date_birth = date_birth.strip(':')
date_birth = date_birth.strip(' ')
data.date_birth = parse_simple(date_birth.strip(' '))
birthplace = page.xpath(
u'//span[contains(text(),"出生地")]/following::text()[1]')
if len(birthplace) > 0:
birthplace = re.sub(u'\n', "", birthplace[0])
birthplace = birthplace.strip(':')
data.birthplace = parse_simple(birthplace.strip(' '))
occupation = page.xpath(
u'//span[contains(text(),"职业")]/following::text()[1]')
if len(occupation) > 0:
occupation = re.sub('\n', '', occupation[0])
occupation = occupation.strip(':')
data.occupation = split_space(occupation.replace('/', ","))
foreign_names = page.xpath(
u'//span[contains(text(),"更多外文名")]/following::text()[1]')
if len(foreign_names) > 0:
foreign_names = re.sub('\n', '', foreign_names[0])
foreign_names = foreign_names.strip(':')
data.foreign_names = split_space(foreign_names.replace("/", ","))
zh_names = page.xpath(
u'//span[contains(text(),"更多中文名")]/following::text()[1]')
if len(zh_names) > 0:
zh_names = re.sub('\n', '', zh_names[0])
zh_names = zh_names.strip('\n').strip(':')
data.zh_names = split_space(zh_names.replace('/', ','))
family_member = page.xpath(
u'//span[contains(text(),"家庭成员")]/following::text()[1]')
if len(family_member) > 0:
family_member = re.sub('\n', '', family_member[0])
family_member = family_member.strip(u':')
data.family_member = split_space(family_member.replace('/', ','))
imdb = page.xpath(u'//span[contains(text(),"imdb编号")]')
if len(imdb) > 0:
if imdb[0].getnext() is not None:
data.IMDb = parse_simple(imdb[0].getnext().text)
intro = page.xpath(u'//span[@class="all hidden"]/text()')
_intro = page.xpath(u'//div[@id="intro"]/div[@class="bd"]/text()')
if len(intro):
data.intro = parse_simple("".join(intro))
else:
data.intro = parse_simple("".join(_intro))
if not data.name:
return False
return data.__dict__
def parse_detail(self, r, url=None):
try:
page = etree.HTML(r)
except Exception as e:
return None
data = Contents()
sss = re.sub(u'\\n', '', r)
v_show = page.xpath(
u'//div[@class="p-post"]/div[@class="yk-pack p-list"]/div[@class="p-thumb"]/a'
)
if len(v_show) > 0:
data.youku_play = "http:" + v_show[0].get("href")
# 海报:
thumb = page.xpath(
u'//div[@class="p-post"]/div[@class="yk-pack p-list"]/div[@class="p-thumb"]/img'
)
if len(thumb) > 0:
data.poster = [{
"url": "http:" + thumb[0].get("src"),
"title": thumb[0].get("alt"),
"width": 200,
"height": 300
}]
data.title = thumb[0].get("alt")
data.img_url = "http:" + thumb[0].get("src")
# category:
category = page.xpath(
'//div[@class="p-base"]/ul/li[@class="p-row p-title"]/a')
if len(category) > 0:
data.category = parse_simple(category[0].text)
# 年份:可能没有
year = page.xpath(
'//div[@class="p-base"]/ul/li[@class="p-row p-title"]/span[@class="sub-title"]'
)
if len(year) > 0 and year[0].text:
m = re.search(u'(\d{4})', year[0].text)
if m:
data.year = m.group(1)
# 别名:可能没有
alias = page.xpath('//div[@class="p-base"]/ul/li[@class="p-alias"]')
if len(alias) > 0:
data.alias = split_space(alias[0].get("title").replace('/', ','))
# 上映:可能没有
published_at = re.search(u'>上映：</label>(\w+-\d+-\d+)*</span>', sss)
if published_at != None:
data.release_date = published_at.group(1)
# 优酷评分：可能没有
youku_score = page.xpath(
'//div[@class="p-base"]/ul/li[@class="p-score"]/span[@class="star-num"]'
)
if len(youku_score) > 0:
data.youku_rating = parse_simple(youku_score[0].text)
# 豆瓣评分:可能没有
douban_score = re.search(u'<span class="db-bignum">(\d+\.\d*)</span>',
sss)
if douban_score != None:
data.douban_rating = douban_score.group(1)
# 豆瓣评价数量，可能没有
douban_cm_num = re.search(u'<span class="db-cm-num">(\d*)评价</span>',
sss)
if douban_cm_num != None:
data.douban_comment_sum = douban_cm_num.group(1)
# 主演:可能没有
actors = page.xpath(
'//div[@class="p-base"]/ul/li[@class="p-performer"]')
if len(actors) > 0:
data.starring = split_space(actors[0].get('title').replace(
"/", ","))
data.starring_list = []
for x in page.xpath(
'//div[@class="p-base"]/ul/li[@class="p-performer"]/a'):
_temp = {}
_temp["name"] = parse_simple(x.text)
_temp["youkuid"] = re.search(
u"//list\.youku\.com/star/show/(.*)\.html",
etree.tostring(x)).group(1)
if x.get("href"):
_temp["youku_url"] = "http:" + x.get("href")
data.starring_list.append(_temp)
# 集数
renew = page.xpath(
'//div[@class="p-base"]/ul/li[@class="p-row p-renew"]')
if len(renew) > 0 and renew[0].text:
m = re.search(u'(\d*)', renew[0].text)
if m:
data.all_episode = m.group(1)
# 导演:循环出来
directed = page.xpath(
u'//div[@class="p-base"]/ul/li[contains(text(),"导演：")]/a')
data['director_list'] = []
if len(directed) > 0:
data.directors = []
for x in directed:
data.directors.append(parse_simple(x.text))
_temp = {}
_temp["name"] = parse_simple(x.text)
_temp["youkuid"] = re.search(
u"//list\.youku\.com/star/show/(.*)\.html",
etree.tostring(x)).group(1)
if x.get("href"):
_temp["youku_url"] = x.get("href")
data.directors_list.append(_temp)
data.directors = ",".join(data.directors)
data.directors = ",".join(data.directors)
# 地区，可能没有
area = re.search(
u'>地区：<a href="//list\.youku\.com/category/show/([^\.html]+?)\.html" target="_blank">([^</a></li>]+?)</a>',
sss)
if area != None:
data.producer_country = parse_simple(area.group(2))
# 类型:循环出来
types = page.xpath(
u'//div[@class="p-base"]/ul/li[contains(text(),"类型")]/a')
if len(types) > 0:
data.tags = []
for x in types:
data.tags.append(parse_simple(x.text))
data.tags = ",".join(data.tags)
# 总播放数:可能为none
plays_num = re.search(u'<li>总播放数：([^</li>]+?)</li>', sss)
if plays_num != None:
data.youku_plays_num = plays_num.group(1).replace(',', "")
# 评论数量:可能为none
youku_comments_num = re.search(u'<li>评论：([^</li>]+?)</li>', sss)
if youku_comments_num:
data.youku_comments_num = youku_comments_num.group(1)
# 顶:可以空
ding = re.search(u'<li>顶：([^</li>]+?)</li>', sss)
if ding:
data.ding = ding.group(1)
# 简介:
summary = page.xpath(u'.//span[contains(@class,"intro-more")]/text()')
if summary:
data.summary = parse_simple("".join(summary)).replace(u"简介：", "")
# 适合年龄，可能为空
age = re.search(u'>适用年龄：([^</li>]+?)</li>', sss)
if age:
data.age = age.group(1)
peiyin = page.xpath(
u'//div[@class="p-base"]/ul/li[contains(text(),"声优：")]/a')
if len(peiyin) > 0:
data.peiyin = []
data.peiyin_list = []
for x in peiyin:
data.peiyin.append(parse_simple(x.text))
_temp = {}
_temp["name"] = parse_simple(x.text)
_temp["youkuid"] = re.search(
u"//list\.youku\.com/star/show/(.*)\.html",
etree.tostring(x)).group(1)
_temp['youku_url'] = "http:" + x.get("href")
data['peiyin_list'].append(_temp)
data.peiyin = ",".join(data.peiyin)
# 综艺节目有
presenters = page.xpath(
u'//div[@class="p-base"]/ul/li[contains(text(),"主持人：")]/a')
if len(presenters) > 0:
data.presenters = []
data.presenters_list = []
for x in presenters:
data.presenters.append(parse_simple(x.text))
_temp["name"] = parse_simple(x.text)
_temp["youkuid"] = re.search(
u"//list\.youku\.com/star/show/(.*)\.html",
etree.tostring(x)).group(1)
_temp['youku_url'] = "http:" + x.get("href")
data.presenters = ",".join(data.presenters)
if data.title == None:
return None
data.created_at = time.time()
return data.__dict__
def vdetail_parser(self, r):
try:
page = etree.HTML(r)
except Exception as e:
return False
L = Contents()
title = page.xpath(u'//a[@_stat="info:title"]')
m = re.search(u'\{"id":"(\w*\d*)"', r)
if m:
L.qq_id = m.group(1)
m = re.search(u'&vid=(\w*\d*)&', r)
if m:
L.qq_vid = m.group(1)
if len(title) > 0:
L.title = title[0].text
category = page.xpath(u'//span[@class="type"]')
if len(category) > 0:
L.category = category[0].text
area = page.xpath(u'.//span[contains(text(),"地 区:")]')
if len(area) > 0:
L.area = area_process(area[0].getnext().text)
foreign_title = page.xpath(u'//span[@class="title_en"]')
if len(foreign_title) > 0:
L.foreign_title = foreign_title[0].text
qq_play = page.xpath(u'.//a[@_stat="info:playbtn"]')
if len(qq_play) > 0:
L.qq_play = qq_play[0].get("href")
language = page.xpath(u'//span[contains(text(),"语 言:")]')
if len(language) > 0:
L.language = language_process(language[0].getnext().text)
year = page.xpath(u'.//span[contains(text(),"上映时间")]')
if len(year) > 0 and year[0].getnext().text:
m = re.search(u'(\d{4})', year[0].getnext().text)
if m:
L.year = m.group(1)
all_episode = page.xpath(u'//span[contains(text(),"总集数:")]')
if len(all_episode) > 0:
L.all_episode = all_episode[0].getnext().text
release_date = page.xpath(u'//span[contains(text(),"出品时间:")]')
if len(release_date) > 0:
L.release_date = release_date[0].getnext().text
if L.release_date and L.year == None:
try:
m = re.search(u'(\d{4})', L.release_date)
if m:
L.year = m.group(1)
except Exception as e:
pass
year = page.xpath(u'.//span[contains(text(),"首播时间")]')
if len(year) > 0 and L.year == None:
m = re.search(u'(\d{4})', year[0].getnext().text)
if m:
L.year = m.group(1)
alias = page.xpath(u'//span[contains(text(),"别 名")]')
if len(alias) > 0:
L.alias = alias[0].getnext().text
tags = page.xpath(u'//a[@class="tag"]')
if len(tags) > 0:
_temp = [x.text for x in tags]
L.tags = ",".join(set(_temp))
summary = page.xpath(
u'//span[@class="desc_txt"]/span[@class="txt _desc_txt_lineHight"]'
)
if len(summary) > 0:
L.summary = parse_simple(summary[0].text)
qq_rating = page.xpath(u'//div[@class="score_v"]/span[@class="score"]')
if len(qq_rating) > 0:
L.qq_rating = qq_rating[0].text
douban_rating = page.xpath(
u'//a[@class="score_db"]/span[@class="score"]')
if len(douban_rating) > 0:
L.douban_rating = douban_rating[0].text
poster = page.xpath(u'//img[@_stat="info:poster"]')
if len(poster) > 0:
L.poster = []
if poster[0].get("src"):
L.poster.append({
"url": self.parse_imgurl(poster[0].get("src")),
"name": poster[0].get("alt")
})
L.img_url = self.parse_imgurl(poster[0].get("src"))
#导演演员
actor_list = page.xpath(u'//ul[contains(@class,"actor_list")]/li')
starring_list = []
starring = []
directors_list = []
directors = []
if len(actor_list) > 0:
_temp = []
for actor in actor_list:
_dic = {}
actor_avatar = actor.find(u'a')
if actor_avatar is not None:
if actor_avatar.find('img') is not None:
_dic["avatar"] = self.parse_imgurl(
actor_avatar.find('img').get("src"))
_dic["qq_id"] = actor.get("data-id")
if actor.find("span") is not None:
_dic["name"] = actor.find("span").text
_dic["qq_home_page"] = actor_avatar.get("href")
actor_detail = actor.xpath(
u'.//div[@class="actor_detail"]')
if actor_detail:
# 职业
occupation = actor_detail[0].xpath(
u'.//span[contains(text(),"职业")]')
if occupation:
_dic['occupation'] = occupation[0].getnext().text
# 地区
area = actor_detail[0].xpath(
u'.//span[contains(text(),"地区")]')
if len(area) > 0:
_dic['area'] = area[0].getnext().text
# 简介
intro = actor.xpath(u'.//span[@itemprop="description"]')
if intro:
_dic["intro"] = intro[0].text
# 导演
if actor_avatar.xpath(u'.//span[@class="director"]'):
directors_list.append(_dic)
directors.append(_dic['name'])
else:
# 演员
starring_list.append(_dic)
starring.append(_dic['name'])
if starring_list:
L.starring = ','.join(starring)
L.starring_list = starring_list
if directors_list:
L.directors = ','.join(directors)
L.directors_list = directors_list
if L.title == None:
return False
L.created_at = time.time()
return L.__dict__
def parse_star(self, r, url):
data = Star()
try:
page = etree.HTML(r)
except Exception as e:
return False
intro = page.xpath(u'.//div[@class="wiki_content"]/text()')
if intro:
data.intro = parse_simple("".join(intro))
name = page.xpath(u'.//span[contains(text(),"中文名")]')
if len(name) > 0:
data.name = parse_simple(name[0].getnext().text)
date_birth = page.xpath(u'.//span[contains(text(),"出生日期")]')
if len(date_birth) > 0:
data.date_birth = parse_simple(date_birth[0].getnext().text)
m = re.search(u'(\d{4}).{1}(\d{2}).{1}(\d{2})', data.date_birth)
if m:
data.date_birth = "-".join(m.groups())
foreign_names = page.xpath(u'.//span[contains(text(),"外文名")]')
if len(foreign_names) > 0:
data.foreign_names = parse_simple(foreign_names[0].getnext().text)
occupation = page.xpath(u'.//span[contains(text(),"职 业")]')
if len(occupation) > 0:
data.occupation = parse_simple(occupation[0].getnext().text)
alias = page.xpath(u'.//span[contains(text(),"别 名")]')
if len(alias) > 0:
data.alias = parse_simple(alias[0].getnext().text)
hobbies = page.xpath(u'.//span[contains(text(),"爱 好")]')
if len(hobbies) > 0:
data.hobbies = parse_simple(hobbies[0].getnext().text)
area = page.xpath(u'.//span[contains(text(),"地 区")]')
if len(area) > 0:
data.area = parse_simple(area[0].getnext().text)
area = page.xpath(u'.//span[contains(text(),"地 区")]')
if len(area) > 0:
data.area = parse_simple(area[0].getnext().text)
constellation = page.xpath(u'.//span[contains(text(),"星 座")]')
if len(constellation) > 0:
data.constellation = parse_simple(constellation[0].getnext().text)
blood = page.xpath(u'.//span[contains(text(),"血 型")]')
if len(blood) > 0:
data.blood = parse_simple(blood[0].getnext().text)
body_height = page.xpath(u'.//span[contains(text(),"身 高")]')
if len(body_height) > 0:
data.body_height = parse_simple(body_height[0].getnext().text)
body_height = page.xpath(u'.//span[contains(text(),"身 高")]')
if len(body_height) > 0:
data.body_height = parse_simple(body_height[0].getnext().text)
body_weight = page.xpath(u'.//span[contains(text(),"体 重")]')
if len(body_weight) > 0:
data.body_weight = parse_simple(body_weight[0].getnext().text)
birthplace = page.xpath(u'.//span[contains(text(),"出生地")]')
if len(birthplace) > 0:
data.birthplace = parse_simple(birthplace[0].getnext().text)
avatar = page.xpath(u'.//div[@class="star_pic"]/img')
if len(avatar) > 0:
data.avatar = "http:" + avatar[0].get("src")
data.qq_home_page = url
if not data.name:
return False
data.created_at = time.time()
return data.__dict__
