def get(self):
newsHtmlList = Contents.all().filter("status =", "2").fetch(1)
if newsHtmlList:
try:
r = newsHtmlList[0].rss
except:
newsHtmlList[0].status = "1"
# db.delete(newsHtmlList)
logging.error("delete one news ,has no rss")
return
# '''
# 接下来就是要处理原始材料了。这是第一个版本的剥皮程序。
# 1.找寻所有的<p></p> 之间的内容。
# （根据我的观察，能发布新闻RSS的网站都是大型网站，有优化html代码的习惯。使得新闻html很简化。因此我觉得这个方法有一定的可行性。）
# '''
newsHtmlList = Contents.all().filter("rss =", newsHtmlList[0].rss).filter("status =", "2").fetch(20)
oldHtmlList = memcache.get("oldhtmllist" + str(newsHtmlList[0].rss.key().id()))
if not oldHtmlList:
oldHtmlList = Contents.all().filter("rss =", newsHtmlList[0].rss).filter("status >", "2").fetch(10)
try:
memcache.set("oldhtmllist" + str(newsHtmlList[0].rss.key().id()), oldHtmlList, 3600 * 24 * 3)
except Exception, e:
pass
# content=newsHtmlList[0]
# news=skinSubOne(content.content)
skinSubTwo(oldHtmlList, newsHtmlList)
def get(self):
cid = self.request.get("content")
if cid:
content = Contents.get_by_id(int(cid))
self.render("templates/look.html", {"content": content, "view": True})
return
rssid = self.request.get("rss")
if rssid:
c = Contents.all().filter("realContentResult =", 0).filter("rss =", RSS.get_by_id(int(rssid))).fetch(1)
if not rssid or not c:
c = Contents.all().filter("realContentResult =", 0).fetch(1)
if c:
content = c[0]
self.render("templates/look.html", {"content": content})
else:
self.redirect("/")
def parse(self):
contents = Contents(file=str(self.xcloc_path))
self.__parse_contents_json(contents)
self.__parse_xliff(contents)
self.__parse_screenshots(contents)
return contents
def write_file_to_database(self, m_group_id, m_group_id2, m_title, m_path,
m_url, m_level):
print 'write_to_database'
'''doc = Documents.objects.filter(url = m_url)
if (len(doc) == 0):
doc = Documents(url=m_url, uid=self.uid, title=m_title, level = m_level)
doc.save()
print 'create\n'
else:
doc[0].uid = self.uid
doc[0].title = m_title
# doc.update()
doc[0].save()
doc = doc[0]
print 'update\n'''
# doc = Documents(title='title', url='url')
# doc.save()
# print 'docid is: %s' % str(doc)
# Delete old records
res = ResAddr()
id = res.saveResaddr(m_url, m_level, '', m_title)
doc = res.getById(id)
oldContents = Contents.objects.filter(doc=doc)
oldContents.delete()
try:
print '\n\n\nstart write url:', m_url
reader = ReadBigFile(m_path, blockSize=1024 * 16)
block = reader.getNextBlock()
while (block != None):
# print 'm_content' + para
con = Contents(group_id=doc.id,
group_id2=m_group_id2,
doc=doc,
paragraph=unicode(block),
tag='p')
con.save()
block = reader.getNextBlock()
os.remove(m_path)
return doc.id
except Exception as e:
print e
print str(e)
exit()
return None
def get(self):
rssid = self.request.get("rss")
c = (
Contents.all()
.filter("rss =", RSS.get_by_id(int(rssid)))
.filter("realContentResult >", 0)
.filter("realContentResult !=", None)
)
self.render("templates/detailLook.html", {"content": c})
def parse(self):
contents = Contents(file=str(self.file_path))
wb = openpyxl.load_workbook(self.file_path)
self.__parse_metadata_sheet(contents, wb)
self.__parse_translation_sheets(contents, wb)
return contents
def get(self):
# nocode=Contents.all().filter('status =','1').filter('code =',None).fetch(10)
# db.delete(nocode)
nocontent = Contents.all().filter("status =", "1").filter("hasContent =", False).fetch(10)
db.delete(nocontent)
deletecontent = Contents.all().filter("status =", "1").filter("hasDelete =", True).fetch(10, 30)
db.delete(deletecontent)
# oldpic=Picture.all().filter('datetime <',datetime.now()+timedelta(hours=-72)).fetch(300)
# db.delete(oldpic)
# norss=Contents().all().filter('status =','2').fetch(100)
rss = 0
# for c in norss:
# try:
# r=c.rss.code
# except :
# logging.info('delete 1')
# c.status='1'
# c.put()
# rss+=1
logging.info("nocontent:" + str(len(nocontent)) + "-" + "deletecontent:" + str(len(deletecontent)))
def post(self):
link = self.request.get("link")
c = Contents.all().filter("link =", link).fetch(1)
if c:
content = c[0]
content.realContentResult = int(self.request.get("realContentResult"))
content.realContentBz = self.request.get("realContentBz")
content.put()
self.redirect("/look?rss=%s" % self.request.get("rss"))
return
self.redirect("/")
def write_file_to_database(self,m_group_id, m_group_id2, m_title, m_path, m_url, m_level): print 'write_to_database' '''doc = Documents.objects.filter(url = m_url) if (len(doc) == 0): doc = Documents(url=m_url, uid=self.uid, title=m_title, level = m_level) doc.save() print 'create\n' else: doc[0].uid = self.uid doc[0].title = m_title # doc.update() doc[0].save() doc = doc[0] print 'update\n''' # doc = Documents(title='title', url='url') # doc.save() # print 'docid is: %s' % str(doc) # Delete old records res = ResAddr() id = res.saveResaddr(m_url, m_level, '', m_title) doc = res.getById(id) oldContents = Contents.objects.filter(doc = doc) oldContents.delete() try: print '\n\n\nstart write url:', m_url reader = ReadBigFile(m_path, blockSize=1024*16) block = reader.getNextBlock() while(block!=None): # print 'm_content' + para con = Contents(group_id=doc.id, group_id2=m_group_id2, doc=doc, paragraph=unicode(block), tag='p') con.save() block = reader.getNextBlock() os.remove(m_path) return doc.id except Exception as e: print e print str(e) exit() return None
def write_to_database(self,m_group_id, m_group_id2, m_title, m_content, m_url, m_level): print 'write_to_database' '''doc = Documents.objects.filter(url = m_url) if (len(doc) == 0): doc = Documents(url=m_url, uid=self.uid, title=m_title, level = m_level) doc.save() print 'create\n' else: doc[0].uid = self.uid doc[0].title = m_title # doc.update() doc[0].save() doc = doc[0] print 'update\n''' # doc = Documents(title='title', url='url') # doc.save() # print 'docid is: %s' % str(doc) # Delete old records res = ResAddr() id = res.saveResaddr(m_url, m_level, '', m_title) doc = res.getById(id) oldContents = Contents.objects.filter(doc = doc) oldContents.delete() import types if type(m_content) is types.ListType: for para in m_content: # print 'm_content' + para con = Contents(group_id=doc.id, group_id2=m_group_id2, doc=doc, paragraph=para, tag='p') con.save() else: con = Contents(group_id=doc.id, group_id2=m_group_id2, doc=doc, paragraph=m_content, tag='p') con.save() return doc.id
def get(self):
rsslist = []
for r in RSS.all():
r.r0 = Contents.all().filter("rss =", r).filter("realContentResult =", 0).count()
r.r1 = Contents.all().filter("rss =", r).filter("realContentResult =", 1).count()
r.r2 = Contents.all().filter("rss =", r).filter("realContentResult =", 2).count()
r.r3 = Contents.all().filter("rss =", r).filter("realContentResult =", 3).count()
r.r4 = Contents.all().filter("rss =", r).filter("realContentResult =", 4).count()
r.r5 = Contents.all().filter("rss =", r).filter("realContentResult =", 5).count()
r.r6 = Contents.all().filter("rss =", r).filter("realContentResult =", None).count()
rsslist.append(r)
self.render("templates/analysis.html", {"RSSs": rsslist})
def write_to_database(self, m_group_id, m_group_id2, m_title, m_content,
m_url, m_level):
print 'write_to_database'
'''doc = Documents.objects.filter(url = m_url)
if (len(doc) == 0):
doc = Documents(url=m_url, uid=self.uid, title=m_title, level = m_level)
doc.save()
print 'create\n'
else:
doc[0].uid = self.uid
doc[0].title = m_title
# doc.update()
doc[0].save()
doc = doc[0]
print 'update\n'''
# doc = Documents(title='title', url='url')
# doc.save()
# print 'docid is: %s' % str(doc)
# Delete old records
res = ResAddr()
id = res.saveResaddr(m_url, m_level, '', m_title)
doc = res.getById(id)
oldContents = Contents.objects.filter(doc=doc)
oldContents.delete()
import types
if type(m_content) is types.ListType:
for para in m_content:
# print 'm_content' + para
con = Contents(group_id=doc.id,
group_id2=m_group_id2,
doc=doc,
paragraph=para,
tag='p')
con.save()
else:
con = Contents(group_id=doc.id,
group_id2=m_group_id2,
doc=doc,
paragraph=m_content,
tag='p')
con.save()
return doc.id
def get(self, limit):
self.urls = []
for content in Contents.all().filter("status =", "1").fetch(int(limit)):
self.urls.append((content, content.link))
self.searchRSS()
