def scrape_detail(self, target, detail_page_bundle, content_ruler, encode):
try:
order = self.web_order
ulweb = UlWebRuler()
result = ulweb.scan_detail(target, detail_page_bundle, order,
content_ruler, encode)
code, detail_page_result = result
if code == 1:
if detail_page_result is not None:
return (1, detail_page_result)
elif code == -3:
self.temp_list.append(
(target, detail_page_bundle, content_ruler, encode))
except WebTargetOutOfDateException as e:
return (-1, e.args[0])
except Exception as e:
import traceback
LogGo.warning(repr(e))
return (-1, e.args[0])
return (0, None)
def gensto(self, dao, list):
status = False
count = len(list)
element = 0
if count > 0:
for item in list:
try:
id = genUUID()
dao.save_or_update(item, id)
element += 1
except Exception as e:
import traceback
msg = traceback.format_exc()
# print(msg)
LogGo.warning(repr(e))
LogGo.info('Total :' + str(count) + ' / ' + str(element) +
' elements Saved!')
if element == 0:
status = False
else:
status = True
else:
LogGo.info("0 Element!")
stauts = False
return status
def scan_list(self, target, exists):
self.limited_forward_count = target.limited_forward_count
self.limited_attitude_count = target.limited_attitude_count
list = []
result_list = []
"""模拟登陆"""
status = 'you got it'
"""如果登陆成功"""
if status != '':
self.loops(target,exists,list)
if len(list) < 1:
return (0, (target, None, None, None))
else:
LogGo.warning("Weibo: Loop scan faild!")
return (-1, (target, None, None, None))
if len(list) > 0:
list = self.purify(list)
list.reverse()
for item in list:
if exists.count(item['id']) < 1:
result_list.append(item)
LogGo.debug('newrank list length:' + str(len(result_list)))
if len(result_list) > 0:
return (1, (target, list, None, None))
return(-1, (target, None, None, None))
def store_program_type(self, pair):
status = False
count = len(pair)
element = 0
if count > 0:
for item in pair:
try:
program, type = item
self.program_type.save_by_program_type(program, type)
element += 1
except Exception as e:
import traceback
msg = traceback.format_exc()
LogGo.warning(msg)
LogGo.info('Total :' + str(count) + ' / ' + str(element) +
' elements Saved!')
if element == 0:
status = False
else:
status = True
else:
LogGo.info("0 Element!")
return status
def newrank_detail(self, target, detail_page_bundle, content_ruler,
encode):
LogGo.info("On newrank detail: " + str(target.data_key))
try:
order = self.wechat_order
newrank = NewrankRuler()
result = newrank.scan_detail(target, detail_page_bundle, order,
content_ruler, encode)
code, detail_page_result = result
if code == 1:
if detail_page_result is not None:
return (1, detail_page_result)
elif code == -3:
self.temp_list.append(
(target, detail_page_bundle, content_ruler, encode))
except Exception:
LogGo.warning('error in newrank detail')
return (-1, None)
return (0, None)
def genup(self, dao, list):
status = False
count = len(list)
element = 0
if count > 0:
for (update, where) in list:
try:
dao.update(update, where)
element += 1
except Exception as e:
import traceback
msg = traceback.format_exc()
# print(msg)
LogGo.warning(repr(e))
LogGo.info('Total :' + str(count) + ' / ' + str(element) +
' elements Updated!')
if element == 0:
status = False
else:
status = True
else:
LogGo.info("0 Element!")
stauts = False
return status
def store_count(self, list):
status = False
count = len(list)
element = 0
update = 0
if count > 0:
for program in list:
try:
if self.check_for_exists(program) == 1:
update += 1
else:
id = genUUID()
self.pc.save(program, id)
element += 1
except Exception as e:
import traceback
msg = traceback.format_exc()
LogGo.warning(msg)
LogGo.info('Total :' + str(count) + ' (' + str(element) +
' Saved, ' + str(update) + ' Updated)')
if element == 0 and update == 0:
status = False
else:
status = True
else:
LogGo.info("0 Element!")
# return False
return status
def store_soap_target(self, targets: [], banned: bool = False):
status = False
element = 0
for target in targets:
try:
if banned:
self.banned_program.save(target)
else:
self.soap_target.save(target)
element += 1
except Exception as e:
import traceback
msg = traceback.format_exc()
LogGo.warning(msg)
LogGo.info('Total :' + str(element) + ' / ' + str(len(targets)) +
' elements Saved!')
if element == 0:
status = False
else:
status = True
return status
def store_program(self, ids, programs):
status = False
if len(ids) != len(programs):
LogGo.error("ids count unmatch programs count")
return False
count = len(ids)
element = 0
if count > 0:
for id, program in zip(ids, programs):
try:
self.program.save(program, id)
element += 1
except Exception as e:
import traceback
msg = traceback.format_exc()
LogGo.warning(msg)
LogGo.info('Total :' + str(count) + ' / ' + str(element) +
' elements Saved!')
if element == 0:
status = False
else:
status = True
else:
LogGo.info("0 Element!")
return status
def gs_detail(self, target, detail_page_bundle, content_ruler, encode):
LogGo.info("On gs detail: " + str(target.data_key))
try:
order = self.wechat_order
gs = GsdataRuler()
result = gs.scan_detail(target, detail_page_bundle, order,
content_ruler, encode)
code, detail_page_result = result
if code == 1:
if detail_page_result is not None:
return (1, detail_page_result)
elif code == 3:
self.temp_list.append(
(target, detail_page_bundle, content_ruler, encode))
except Exception as e:
import traceback
LogGo.warning(repr(e))
return (-1, e.args[0])
return (0, None)
def purify(self,list):
if len(list) < 1:
return []
result = []
for i in list:
try:
flag = True
id = i['id']
text = i['text']
limited_attitude_count = i['attitudes_count']
limited_forward_count = i['reposts_count']
program_count = 0
# 基础过滤重复id
for seq in result[::-1]:
sid = seq['id']
if id == sid:
flag = False
break
# 第一次节目名过滤（有可能会包含到非节目）
if flag and text.count('《') < 1:
flag = False
# 条二次参数过滤
if flag and self.limited_attitude_count is not None and limited_attitude_count is not None:
if limited_attitude_count < self.limited_attitude_count:
flag = False
if flag and self.limited_forward_count is not None and limited_forward_count is not None:
if limited_forward_count < self.limited_forward_count:
flag = False
# 第三次依据节目名过滤
if flag:
for program in self.exist_program:
if text.count(program) >= 1:
program_count = program_count + 1
if program_count > 3:
flag = False
break
if flag:
result.append(i)
except Exception as e:
import traceback
msg = traceback.format_exc()
LogGo.warning(msg)
return result
def start(self):
try:
if self.config.check_table:
self.check_data_base()
# RequestHelperClassVer.init(self.config)
# ProxyHelper.init(self.config)
# MysqlHelper.init(self.config)
self.start_mormal_mission()
except Exception as e:
import traceback
msg = traceback.format_exc()
LogGo.warning(msg)
def gs_list(self, target):
LogGo.info("On gs list: " + str(target.data_key))
try:
exists = self.exists_signature
gs = GsdataRuler()
code, value = gs.scan_list(target, exists)
return (code, value)
except Exception as e:
import traceback
LogGo.warning(repr(e))
return (0, None)
def newrank_list(self, target):
LogGo.info("On newrank list: " + str(target.data_key))
try:
exists = self.exists_title
newrank = NewrankRuler()
code, value = newrank.scan_list(target, exists)
return (code, value)
except Exception as e:
import traceback
LogGo.warning(repr(e))
return (0, None)
def weibo_list(self, target):
LogGo.info("On weibo list: " + str(target.data_key))
try:
exists = self.exists_identifier
weibo = WeiboRuler()
code, value = weibo.scan_list(target, exists)
return (code, value)
except Exception as e:
import traceback
LogGo.warning(repr(e))
return (0, None)
def store(self, news_list: [], article_list: [], heavy_list: [] = None):
status = False
if len(article_list) != len(news_list):
LogGo.error("news count unmatch article count")
return False
count = len(news_list)
element = 0
if count > 0:
if heavy_list is not None:
for news, article, heavy in zip(news_list, article_list,
heavy_list):
try:
id = genUUID()
self.news.save(news, id)
self.article.save(article, id)
self.heavy.save_with_news_id(heavy, id)
element += 1
except Exception as e:
LogGo.warning(repr(e))
else:
for news, article in zip(news_list, article_list):
try:
id = genUUID()
self.news.save(news, id)
self.article.save(article, id)
element += 1
except Exception as e:
LogGo.warning(repr(e))
LogGo.info('Total :' + str(count) + ' / ' + str(element) +
' elements Saved!')
if element == 0:
status = False
else:
status = True
# return True
else:
LogGo.info("0 Element!")
# return False
return status
def scrape_list(self, target):
LogGo.info("On scrape list: " + str(target.data_key))
try:
exists = self.exists_url
ulweb = UlWebRuler()
code, value = ulweb.scan_list(target, exists)
return (code, value)
except WebTargetOutOfDateException as e:
LogGo.warning(e.args[0])
except Exception as e:
import traceback
LogGo.warning(repr(e))
return (0, None)
def start(self):
result = 0
try:
LogGo.info('搜狗爬虫')
# Updatemp.loot()
return result
except Exception as e:
import traceback
msg = traceback.format_exc()
print(msg)
LogGo.warning(e)
result = -1
return result
def store_soap(self, soap):
status = False
if len(soap) < 1:
LogGo.info("no data to save!")
return False
try:
id = genUUID()
self.soap.save(soap, id)
status = True
except Exception as e:
import traceback
msg = traceback.format_exc()
LogGo.warning(msg)
LogGo.info('Soap Saved')
return status
def weibo_detail(self, target, detail_page_bundle, content_ruler, encode):
LogGo.info("On weibo detail: " + str(target.data_key))
try:
order = self.weibo_order
weibo = WeiboRuler()
detail_page_result_dic = weibo.scan_detail(target,
detail_page_bundle,
order, content_ruler,
encode)
if detail_page_result_dic is not None:
return (1, detail_page_result_dic)
except Exception as e:
import traceback
LogGo.warning(repr(e))
return (-1, e.args[0])
return (0, None)
def scan_list(self, target, exists):
"""请求参数"""
par = (['flag', 'true'], ['uuid', target.extra0])
"""抓取关键字"""
keys = [
'title', 'author', 'publicTime', 'url', 'clicksCount', 'likeCount',
'publicTime', 'summary'
]
list = []
result_list = []
try:
raw = RequestHelper.post(NewrankRuler.url,
par,
file_cookie=Configs.newrank_cookie_file)
except Exception as e:
import traceback
msg = traceback.format_exc()
# print(msg)
LogGo.warning(msg)
return (-1, (target, None, None, None))
try:
list = ExtraJSON.extra_newrank_wechat_list(raw, keys)
except:
return (-1, (target, None, None, None))
if len(list) > 0:
list.reverse()
for item in list:
if exists.count(item['title']) < 1:
result_list.append(item)
LogGo.debug('newrank list length:' + str(len(result_list)))
if len(result_list) > 0:
return (1, (target, list, None, None))
return (-1, (target, None, None, None))
def anyList(rawData, keys, start):
par_list = keys
# print(">>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>")
con = []
offect = start
dic = dict()
for key in par_list:
try:
content = ExtraJSON.getContent(rawData, key, offect)
con.append(content)
offect += content[1]
# print(key + " : " + content[0])
dic[key] = content[0]
except Exception as e:
LogGo.warning(e)
continue
# print("<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<")
# print(" ")
minLen = 0
for i in con:
minLen += i[1]
try:
nextIndex = rawData.index(keys[0], start + minLen)
except ValueError as e:
#LogGo.warning(e)
return (con, 0)
return (con, nextIndex, dic)
def loops(self,target,exists,result):
try:
base_url = target.extra0
for i in range(0, Configs().length_weibo): # [::-1]:
print("page: " + str(i))
list = self.build_and_request(WeiboRuler.keys, base_url, WeiboRuler.request_getindex, i)
if len(list) == 0:
break
for item in list:
"""日常抓取时的重复验证"""
if exists.count(item['id']) < 1:
result.append(item)
else:
return
except Exception as e:
import traceback
msg = traceback.format_exc()
print(msg)
LogGo.warning(repr(e))
LogGo.warning("Scan Failed!")
return
def scan_list(self, target, exists) -> ():
# order = ScrappdeDataDao.get_max_order('web') # 数据库中排序代码
detail_page_bundle_list = []
error_code = None
first = target.extra0#'http://ent.people.com.cn/GB/81374/index1.html'
second = target.extra1#'http://ent.people.com.cn/GB/81374/index2.html'
third = target.extra2#'http://ent.people.com.cn/GB/81374/index3.html'
str_parent_container = target.extra3#'(div,[class:ej_list_box clear])'
str_list_container = target.extra4#'(li,[])'
list_ruler = target.extra5#'link:a href()=;title:a;data:em'
content_ruler = target.extra6
list_json_path = target.extra9
url = ''
one = False
if second == "" or second is None:
one = True
url = first
analyser = None
if one == False:
analyser = Analyser(first, second, third)
try:
encode = self.extractor.get_page_encode(first)
except HttpConnectionFailedException as e:
return (-2, (target, None, None, None))
for i in range(1, Configs.length_web):
LogGo.info('scaning index: ' + str(i))
if one:
pass
else:
url = analyser.get_url(i)
try:
raw = self.req.get(url,encode=encode)
if target.type == 'ulweb':
self.looper_html(detail_page_bundle_list, raw, exists, list_ruler, str_parent_container, str_list_container)
elif target.type == 'jsweb':
raw = self.extra4_process(target.extra4, raw)
self.looper_js(detail_page_bundle_list, raw, exists, list_ruler, str_parent_container, list_json_path=list_json_path)
if one:
break
except AttributeError as e:
pass
except TypeError as e:
import traceback
LogGo.warning(repr(e))
except HttpConnectionFailedException as e:
import traceback
LogGo.warning(repr(e))
except Exception as e:
import traceback
LogGo.warning(repr(e))
if len(detail_page_bundle_list) > 0:
detail_page_bundle_list.reverse()
detail_page_bundle_list = self.purify(detail_page_bundle_list,'link')
return (1, (target, detail_page_bundle_list, content_ruler, encode))
else:
return (-1, (target, None, None, None))
def build_base_dic(self,target,list,existsUrls,order):
news = TBNews()
article = TBArticle()
picture_dao = PictureDao()
result = []
article_result = []
"""抓取正文"""
for i in list:
try:
i['content_url'] = UrlHelper.unify(i['content_url']) #StringHelper.unescape(i['content_url'])
if existsUrls.count(i['content_url']) < 1: # getattr(i, 'url')
LogGo.info(">>> file id: " + str(i['fileid']))
LogGo.info(">>> url: " + str(i['content_url']))
try:
tup = ExtraJSON.wechat_extra_content(i['content_url']) # getattr(i, 'url')
except Exception as e:
print(e)
print(">>> ")
print(">>> extra content error.")
print(">>> ")
LogGo.info("extra content error.")
LogGo.info("possible a deleted msg")
# LogGo.info("url: " + i['content_url'])
continue
raw_content = tup[1]
content = tup[2]
"""字典的 键 对应数据库中的字段名 值 对应要存储的值"""
dic = dict()
article_dic = dict()
order = order + 5
dic[news.order_code.key] = order # """排序代码"""
dic[news.create_date.key] = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S') # """此条记录创建时间"""
dic[news.valid.key] = 1
dic[news.text_not_format.key] = content #"""去除标签的正文内容"""
# dic[news.text_blob.key] = raw_content #"""原始带标签字段"""
dic[news.subscribe_time.key] = i['datetime'] # getattr(i, 'publicTime') """文章发表日期"""
dic[news.author.key] = i['author'] # getattr(i, 'author')"""文章所属机构"""
dic[news.title.key] = i['title'] # getattr(i, 'title')"""文章标题"""
dic[news.subject.key] = i['digest'] # """摘要"""
dic[news.status.key] = 2
picture_id = picture_dao.save_data(i['cover'])
dic[news.main_pic_id.key] = picture_id #"""列表图片 id"""
article_dic[article.fingerprint.key] = md5(i['content_url'])#"""由地址生成的指纹"""
article_dic[article.target_id.key] = target.id
article_dic[article.company.key] = target.data_key # getattr(i, 'author') """文章所属机构"""
article_dic[article.content_url.key] = i['content_url'] # getattr(i, 'url')"""正文链接"""
article_dic[article.scrabble_type.key] = 'wechat' # """文章类型 微信固定值为 wechat """
article_dic[article.is_scrabbled.key] = 1 # """在数据库中作为 这是一条抓取到的数据 的标记"""
result.append(dic)
article_result.append(article_dic)
except Exception as e:
import traceback
msg = traceback.format_exc()
print(msg)
LogGo.warning(repr(e))
continue
return result, article_result
def scan_detail(self, target, detail_page_bundle, order, content_ruler,
encode):
news = TBNews()
article = TBArticle()
# picture_dao = PictureDao()
result_dic = dict()
try:
info = self.ready_info(detail_page_bundle['title'],
detail_page_bundle['url'])
LogGo.info(info)
try:
# tup = ExtraJSON.wechat_extra_content(detail_page_bundle['url'])
tup = self.jsons.wechat_extra_content(
detail_page_bundle['url'])
except HttpConnectionFailedException as e:
LogGo.warning(repr(e))
return (-3, None)
except AttributeError:
LogGo.warning(
"Maybe a deleted msg, complete the code to detect this error"
)
return (-2, None)
except Exception:
LogGo.warning("Error when get detail message!")
return (-2, None)
raw_content = tup[1]
content = tup[2]
picture = tup[3]
"""字典的 键 对应数据库中的字段名 值 对应要存储的值"""
news_dic = dict()
article_dic = dict()
############################## NEWS ###############################
"""列表图片 id"""
# if picture is not None:
# picture_id = picture_dao.save_data(picture)
# news_dic[news.main_pic_id.key] = picture_id
news_dic[news.text_not_format.key] = content # """去除标签的正文内容"""
# dic[news.text_blob.key] = raw_content#"""原始带标签字段"""
news_dic[news.subscribe_time.key] = detail_page_bundle[
'publicTime'] # """文章发表日期"""
news_dic[news.create_date.key] = datetime.datetime.now().strftime(
'%Y-%m-%d %H:%M:%S') # """此条记录创建时间"""
news_dic[news.subject.key] = detail_page_bundle[
'summary'] # """摘要"""
news_dic[news.valid.key] = 1
news_dic[news.author.key] = detail_page_bundle['author']
news_dic[news.title.key] = detail_page_bundle[
'title'] # """文章标题"""
news_dic[news.status.key] = 2
order += 5
news_dic[news.order_code.key] = order # """排序代码"""
############################## ARTICLE ###############################
article_dic[article.content_url.key] = detail_page_bundle[
'url'] # getattr(i, 'url')"""正文链接"""
article_dic[article.fingerprint.key] = md5(
detail_page_bundle['url']) # """由地址生成的指纹"""
article_dic[article.company.key] = target.data_key # """文章所属机构"""
article_dic[article.target_id.key] = target.id
article_dic[article.raw_click_count.key] = detail_page_bundle[
'clicksCount'] # getattr(i, 'clicksCount')#"""阅读量"""
article_dic[article.vote_up_count.key] = detail_page_bundle[
'likeCount'] # getattr(i, 'likeCount')"""点赞数"""
article_dic[article.scrabble_type.
key] = 'wechat' # """文章类型 微信固定值为 wechat """
article_dic[
article.is_scrabbled.key] = 1 # """在数据库中作为 这是一条抓取到的数据 的标记"""
article_dic[article.publishStatus.key] = 1
# article_dic[article.messageType.key] = random.randint(0, 1)
############################## DIC ###############################
result_dic.update(news_dic)
result_dic.update(article_dic)
except Exception:
import traceback
msg = traceback.format_exc()
LogGo.warning(msg)
return (-1, None)
return (1, result_dic)
def scan(self, target, order):
result = []
type = self.td(target)
url = target.extra0 #'http://ent.people.com.cn/GB/81374/index1.html'
cap = None
ruler = None
if self.td(target) == 'i':
cap = ['var tvInfoJs=', '']
url = self.iqiyi_base.format(url)
ruler = 'keywords:contentKeyword;latestOrder:latestOrder;name:name;playCount:playCount;score:score;videoCount:videoCount'
elif type == 'l':
ruler = 'score:plist_score;comments:pcommon_count;bullets:pdm_count;like:up;hate:down;playCount:plist_play_count'
url = self.letv_base.format(url, target.extra1)
elif type == 't':
cap = ["tlux.dispatch('$cover',", ");"]
ruler = 'score:score->score;playCount:view_all_count;videoCount:episode_all;latestOrder:episode_updatedd'
url = self.qq_base.format(url)
elif type == 'm':
url = self.mgtv_base.format(url)
cap = ['"data":', ',"msg"']
ruler = 'playCount:all;like:like;hate:unlike'
elif type == 'y':
ruler = 'playCount:li [总播放数];comments:li [评论];like:li [顶];score:span class=star-num'
if not s.is_url(url):
if not url.startswith('id'):
url = self.youku_prefix.format(url)
url = self.youku_base.format(url)
elif type == 's':
url = self.sohu_base.format(url)
elif type == 'c':
url = self.cntv_base.format(url)
ruler = 'playCount:^label [播放次数]'
try:
encode = ExtraHtml.get_page_encode(url)
if type == 'y' or type == 'c':
result = self.looper_html(url, ruler, encode, target)
else:
raw = RequestHelper.get(url, encode=encode)
if type == 's':
result = self.finder_sohu(raw)
else:
result = self.looper_js(raw, ruler, cap)
except AttributeError as e:
pass
except Exception as e:
import traceback
msg = traceback.format_exc()
print(msg)
LogGo.warning(repr(e))
if len(result) > 0:
result = self.build_base_dic(target, result, order)
return result[0]
def build_count_dic(self, pro_list):
# pc = TBProgramPlayCount
result = []
try:
LogGo.info(">>> count: " + str(len(pro_list)))
for programs in pro_list:
"""字典的 键 对应数据库中的字段名 值 对应要存储的值"""
dic = dict()
total = 0
for program in programs:
try:
dic[TBProgramPlayCount.program.key] = program[
TBSoap.program.key]
plantform = program[TBSoap.plantform.key]
count = program[TBSoap.play_count.key]
total += count
if self.td(plantform) == 'i':
dic[TBProgramPlayCount.count1.key] = count
elif self.td(plantform) == 'l':
dic[TBProgramPlayCount.count2.key] = count
elif self.td(plantform) == 't':
dic[TBProgramPlayCount.count3.key] = count
elif self.td(plantform) == 'm':
dic[TBProgramPlayCount.count4.key] = count
elif self.td(plantform) == 'y':
dic[TBProgramPlayCount.count5.key] = count
elif self.td(plantform) == 's':
dic[TBProgramPlayCount.count6.key] = count
except Exception as e:
import traceback
msg = traceback.format_exc()
LogGo.info(msg)
dic[TBProgramPlayCount.total_count.key] = total
dic[TBProgramPlayCount.
create_time.key] = datetime.datetime.now().strftime(
'%Y-%m-%d') # """此条记录创建时间"""
result.append(dic)
except BaseDateLackException as e:
msg = "Lake improtant data(" + str(e) + ')'
LogGo.warning(msg)
except DataFormatException as e:
pass
# msg = "Date format error: " + i['link'] + '\r\n' + str(e)
# LogGo.warning(msg)
except KeyError as e:
import traceback
msg = traceback.format_exc()
LogGo.warning(msg)
except Exception as e:
import traceback
msg = traceback.format_exc()
LogGo.warning(msg)
return result
def build_base_dic(self, target, result, order):
soap = TBSoap()
program_dao = ProgramDao()
soap_result = []
try:
name = ''
if Configs.show_utf:
try:
name = target.data_key
except:
name = '<<error>>'
LogGo.info(">>> name: " + str(name) + "(" +
str(result['playCount']) + ")")
"""字典的 键 对应数据库中的字段名 值 对应要存储的值"""
dic = dict()
try:
dic[soap.play_count.key] = result['playCount'] #瞬时播放量
except KeyError as e:
raise BaseDateLackException(str(e))
try:
dic[soap.keywords.key] = result['keywords'] # 关键字
except:
pass
try:
dic[soap.bullet_count.key] = result['bullets'] # 弹幕量
except:
pass
try:
dic[soap.hate_count.key] = result['hate'] # 怒踩量
except:
pass
try:
dic[soap.like_count.key] = result['like'] # 点赞量
except:
pass
try:
dic[soap.latest_order.key] = result['latestOrder'] # 最新剧集
except:
pass
try:
dic[soap.name.key] = result['name'] # 剧名
except:
pass
try:
dic[soap.name.key] = program_dao.get_title_by_id(
target.program_id)
except:
pass
try:
dic[soap.score.key] = result['score'] # 分数
except:
pass
try:
dic[soap.video_count.key] = result['videoCount'] # 视频数量
except:
pass
try:
# pass
dic[soap.program.key] = target.program_id # program
dic[soap.target.key] = target.id # program
except:
pass
dic[soap.plantform.key] = target.soap_type
order += 1
dic[soap.order_code.key] = order # """排序代码"""
dic[soap.create_date.key] = datetime.datetime.now().strftime(
'%Y-%m-%d %H:%M:%S') # """此条记录创建时间"""
dic[soap.valid.key] = 1
soap_result.append(dic)
except BaseDateLackException as e:
msg = "Lake improtant data(" + str(e) + ')'
LogGo.warning(msg)
except DataFormatException as e:
pass
# msg = "Date format error: " + i['link'] + '\r\n' + str(e)
# LogGo.warning(msg)
except KeyError as e:
import traceback
msg = traceback.format_exc()
LogGo.warning(msg)
except Exception as e:
import traceback
msg = traceback.format_exc()
LogGo.warning(msg)
return soap_result
def build_single_page_dic(self, target, detail_page_bundle, order, content_ruler, encode):
news = TBNews()
article = TBArticle()
result_dic = dict()
try:
LogGo.info(WeiboRuler.url_status + detail_page_bundle['id'])
# blob = i['text'].encode("UTF-8")
"""字典的 键 对应数据库中的字段名 值 对应要存储的值"""
news_dic = dict()
article_dic = dict()
"""排序代码"""
order += 2
news_dic[news.order_code.key] = order
# dic[news.text_not_format.key] = i['text']#"""去除标签的正文内容"""
# dic[news.text_blob.key] = blob #"""原始带标签字段"""
sub_tim = detail_page_bundle['created_at']
if sub_tim is not None:
news_dic[news.subscribe_time.key] = sub_tim # getattr(i, 'publicTime') """文章发表日期"""
else:
LogGo.warning("no subscribe time!")
news_dic[news.create_date.key] = DateGo.get_current_date() # """此条记录创建时间"""
news_dic[news.status.key] = 1 # """状态"""
news_dic[news.valid.key] = 1
news_dic[news.title.key] = detail_page_bundle['text']
news_dic[news.text_not_format.key] = detail_page_bundle['text']
news_dic[news.text_blob.key] = detail_page_bundle['text']
# title = None
# try:
# title = i['page_info']
# title = title['content1']
# except Exception as e:
# pass
# if title is None:
# dic[news.title.key] = i['text'] # getattr(i, 'title') """文章标题"""
# else:
# dic[news.title.key] = title # """文章标题"""
"""文章所属机构"""
try:
user = detail_page_bundle['user']
screen_name = user['screen_name']
article_dic[article.company.key] = screen_name # getattr
except Exception as e:
pass
article_dic[article.vote_up_count.key] = detail_page_bundle['attitudes_count'] # getattr(i, 'likeCount') """点赞数"""
article_dic[article.scrabble_type.key] = 'weibo' #"""文章类型"""
article_dic[article.is_scrabbled.key] = 1 #"""在数据库中作为 这是一条抓取到的数据 的标记"""
article_dic[article.identifier.key] = detail_page_bundle['id'] #"""数据在母体中的 id"""
article_dic[article.target_id.key] = target.id
article_dic[article.content_url.key] = WeiboRuler.url_status + detail_page_bundle['id'] # getattr(i, 'url') """正文链接"""
article_dic[article.publishStatus.key] = 1
# article_dic[article.messageType.key] = random.randint(0, 1)
"""如果是回复 或者 引用 会有被引用的微博，记录那个微博的 id"""
try:
retweeted_status = detail_page_bundle['retweeted_status']
ret_id = retweeted_status['id']
article_dic[article.identifier_re.key] = ret_id
except Exception as e:
pass
"""阅读量"""
# dic['click_count'] = i['clicksCount'] #getattr(i, 'clicksCount')
"""转发数"""
"""评论量"""
# """图片组"""
# try:
# pics = i['pics']
# if len(pics) > 0:
# group_id = PictureDao.save_group_data(pics)
# if group_id is not None:
# dic['group_picture_id'] = group_id
# except Exception as e:
# print(e)
# LogGo.warning(dic['content_url'])
# LogGo.warning(e)
result_dic.update(article_dic)
result_dic.update(news_dic)
except Exception as e:
import traceback
msg = traceback.format_exc()
LogGo.warning(msg)
return None
return result_dic
