def merge_fields(self, info):
L = Contents()
L.title = info.get("name")
L.summary = info.get("description")
L.iqiyi_tvId = info.get("tvId")
L.iqiyi_vid = info.get("vid")
L.iqiyi_plays_num = info.get("playCount")
L.iqiyi_albumId = info.get("albumId")
L.iqiyi_play_url = info.get("url")
if info.get("duration") and info.get("duration") != "":
L.duration = info.get("duration")/60
L.poster = []
if info.get("albumImageUrl"):
L.img_url = info.get("albumImageUrl")
L.poster.append({"url": info.get("albumImageUrl")})
if info.get("imageUrl"):
L.poster.append({"url": info.get("imageUrl")})
if info.get("videoImageUrl"):
L.poster.append({"url": info.get("videoImageUrl")})
if info.get("posterUrl"):
L.poster.append({"url": info.get("posterUrl")})
if info.get("tvImageUrl"):
L.poster.append({"url": info.get("tvImageUrl")})
if info.get("qualityImageUrl"):
L.poster.append({"url": info.get("qualityImageUrl")})
if info["issueTime"]:
L.release_date = mictime_to_ymd(info["issueTime"])
if info.get("crumbList"):
level2 = True
for x in info.get("crumbList"):
if int(x["level"])==2 and x["title"]!=u'VIP会员':
L.category = x["title"]
level2 = False
if level2:
for x in info.get("crumbList"):
if int(x["level"])==3:
L.category = x["title"]
level2 = False
_temp = []
for x in info.get("categories"):
if u"地区" in x.get("subName"):
L.area = area_process(x.get("name"))
elif u"类型" in x.get("subName") or u'风格' in x.get("subName") or u'分类' in x.get("subName") or u'小学' in x.get("subName") or u'高中' in x.get("subName") or u'短片' in x.get("subName"):
_temp.append(x.get("name"))
elif u"语种" in x.get("subName"):
L.language = language_process(x.get("name"))
elif x.get("subName") == u"年龄段":
L.age = x.get("name")
L.tags = ",".join(_temp)
L.all_episode = info.get("videoCount")
L.sub_title = info.get("subtitle")
L.iqiyi_rating_num = info.get("commentCount")
L.iqiyi_qitanId = info.get("qitanId")
if info.get("cast") and info.get("cast").get("directors"):
L.directors = []
L.directors_list = []
for x in info.get("cast").get("directors"):
L.directors.append(x.get("name"))
L.directors_list.append({"name": x.get("name"), "iqiyi_id": x.get("id"), "avatar": x.get(
"imageUrl"), "iqiyi_userId": x.get("userId"), "iqiyi_circleId": x.get("circleId")})
L.directors = ",".join(L.directors)
if info.get("cast") and info.get("cast").get("speakers"):
L.speakers = []
L.speakers_list = []
for x in info.get("cast").get("speakers"):
L.speakers.append(x.get("name"))
L.speakers_list.append({"name": x.get("name"), "iqiyi_id": x.get("id"), "avatar": x.get(
"imageUrl"), "iqiyi_userId": x.get("userId"), "iqiyi_circleId": x.get("circleId")})
L.speakers = ",".join(L.speakers)
if info.get("cast") and info.get("cast").get("publishers"):
L.publishers = []
L.publishers_list = []
for x in info.get("cast").get("publishers"):
L.publishers.append(x.get("name"))
L.publishers_list.append({"name": x.get("name"), "iqiyi_id": x.get("id"), "avatar": x.get(
"imageUrl"), "iqiyi_userId": x.get("userId"), "iqiyi_circleId": x.get("circleId")})
L.publishers = ",".join(L.publishers)
if info.get("cast") and info.get("cast").get("singers"):
L.singers = []
L.singers_list = []
for x in info.get("cast").get("singers"):
L.singers.append(x.get("name"))
L.singers_list.append({"name": x.get("name"), "iqiyi_id": x.get("id"), "avatar": x.get(
"imageUrl"), "iqiyi_userId": x.get("userId"), "iqiyi_circleId": x.get("circleId")})
L.singers = ",".join(L.singers)
if info.get("cast") and info.get("cast").get("mainActors"):
L.starring = []
L.starring_list = []
for x in info.get("cast").get("mainActors"):
L.starring.append(x.get("name"))
L.starring_list.append({"name": x.get("name"), "iqiyi_id": x.get("id"), "avatar": x.get(
"imageUrl"), "iqiyi_userId": x.get("userId"), "iqiyi_circleId": x.get("circleId")})
L.starring = ",".join(L.starring)
"""编剧"""
if info.get("cast") and info.get("cast").get("writers"):
L.screenwriters = []
L.screenwriter_list = []
for x in info.get("cast").get("writers"):
L.screenwriters.append(x.get("name"))
L.screenwriter_list.append({"name": x.get("name"), "iqiyi_id": x.get("id"), "avatar": x.get(
"imageUrl"), "iqiyi_userId": x.get("userId"), "iqiyi_circleId": x.get("circleId")})
L.screenwriters = ",".join(L.screenwriters)
if info.get("cast") and info.get("cast").get("actors"):
L.actors = []
L.actors_list = []
for x in info.get("cast").get("actors"):
L.actors.append(x.get("name"))
L.actors_list.append({"name": x.get("name"), "iqiyi_id": x.get("id"), "avatar": x.get(
"imageUrl"), "iqiyi_userId": x.get("userId"), "iqiyi_circleId": x.get("circleId")})
L.actors = ",".join(L.actors)
"""嘉宾"""
if info.get("cast") and info.get("cast").get("guests"):
L.guests = []
L.guests_list = []
for x in info.get("cast").get("guests"):
L.guests.append(x.get("name"))
L.guests_list.append({"name": x.get("name"), "iqiyi_id": x.get("id"), "avatar": x.get(
"imageUrl"), "iqiyi_userId": x.get("userId"), "iqiyi_circleId": x.get("circleId")})
L.guests = ",".join(L.guests)
if info.get("cast") and info.get("cast").get("hosts"):
L.hosts = []
L.hosts_list = []
for x in info.get("cast").get("hosts"):
L.hosts.append(x.get("name"))
L.hosts_list.append({"name": x.get("name"), "iqiyi_id": x.get("id"), "avatar": x.get(
"imageUrl"), "iqiyi_userId": x.get("userId"), "iqiyi_circleId": x.get("circleId")})
L.hosts = ",".join(L.hosts)
if L.release_date and L.year==None:
m = re.search(u'(\d{4})',L.release_date)
if m:
L.year = m.group(1)
if not L.directors_list and not L.directors_list and L.hosts:
L.directors = L.hosts
L.directors_list = L.hosts_list
L.focuses = info.get("focuses")
L.iqiyi_rating = info.get("score")
L.created_at = time.time()
return L.__dict__
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__