def create_product_to_sell(self, product_params):
"""
create a product and save into db
"""
try:
# change the size of the image
big_img, small_img = change_img_size(product_params["image"])
product_to_sell = ProductToSell(
owner=product_params["owner"],
product_name=product_params["productname"],
broad_type=product_params["broadtype"],
sub_type=product_params["subtype"],
belong_campus=product_params["belongcampus"],
trade_type=product_params["tradetype"],
purity=product_params["purity"],
big_img=big_img,
small_img=small_img,
price=product_params["price"],
trade_title=product_params["tradetitle"],
trade_detail=product_params["tradedetail"],
release_time=product_params["releasetime"],
)
product_to_sell.save()
nid = create_nid(product_to_sell.id)
product_to_sell.nid = nid
product_to_sell.save()
return product_to_sell
except Exception, e:
print e
return None
def test_crawler(fiction_url):
fiction_infor = get_book_infor(
'http://qidian.com',
'qidian',
fiction_url,
)
if not fiction_infor:
return
print fiction_infor
#save tag
#save all the fiction into database
fiction_title = '武炼巅峰'
author_name = '莫默'
ids = ['2494758']
types = '1'
try:
web_site = FictionWebSite.objects.get(title='qidian')
except:
web_site = FictionWebSite(
title='qidian',
url='http://qidian.com',
)
web_site.save()
try:
#如果同样的标题的小说已经被收录,唯一性由标题和作者确定
fic = Fiction.objects.get(fiction_title=fiction_title,
author=author_name)
#如果所在网站相同，则不继续处理
DG.trace("get it")
print fic.source_site.title
print web_site.title
if fic.source_site.title == web_site.title:
return
except Exception, e:
print e
fic = Fiction(
fiction_title=fiction_title,
fiction_avatar_url=fiction_infor['avatar'],
fiction_intro=fiction_infor['intro'],
fiction_id=ids[0],
fiction_style=types,
total_word=fiction_infor['total_word'],
stock_time=10,
com_word="",
source_site=web_site,
click_time=fiction_infor['click_time'],
rec_time=fiction_infor['rec_time'],
author=author_name,
author_url="",
)
fic.save()
fic.fiction_nid = create_nid(fic.id)
fic.save()
if isinstance(fiction_title, unicode):
fiction_title = fiction_title.encode('utf-8')
#如果是新加入的小说，则为其建立索引
t1 = threading.Thread(target=build_index_database,
args=(fiction_title, fic, '1'))
t1.start()
t1.join()
def register(request):
if request.user.is_authenticated():
return HttpResponseRedirect('/')
if request.method == 'GET':
return RTR('register.html', {'error_msg': False},
context_instance=RequestContext(request))
#get validationg code
validate_code = request.POST.get('validate', '')
if not_legal(validate_code) or validate_code.lower(
) != request.session['validate'].lower():
return RTR('register.html', {'error_msg': True},
context_instance=RequestContext(request))
email = request.POST.get('email', '')
password = request.POST.get('password', '')
name = request.POST.get('name', '')
remember = request.POST.get('remember', '')
try:
try:
user = Account.objects.get(name=name)
return HttpResponse("you ren le")
except:
pass
#build shelf
shelf = Shelf(fiction_number=0)
shelf.save()
user = Account(name=name,
password=hashlib.md5(password).hexdigest(),
is_active='0',
email=email,
shelf=shelf)
user.save()
user.nid = create_nid(user.id)
user.save()
user = authenticate(name=user.name, password=password)
if user:
login(request, user)
response = HttpResponseRedirect('/' + user.nid)
if remember == 'on':
response.set_cookie('login', 'True', max_age=7 * 24 * 60 * 60)
return response
else:
return HttpResponse('ok')
except:
HttpResponse("服务器故障,请稍候再试<a href = '%s'>返回<a/>" %
request.META['HTTP_REFERER'])
def create_user(self, user_params):
"""
create a user and save into db
"""
try:
user = Account(nick_name = user_params['nickname'],
real_name = user_params['realname'],
password = hashlib.md5(user_params['password']).hexdigest(),
email = user_params['email'],
qq = user_params['qq'],
person_intro = user_params['intro'],
phone = user_params['phone'])
user.save()
nid = create_nid(user.id)
user.nid = nid
user.save()
return user
except Exception,e:
print e
return None
def create_product_to_buy(self, product_params):
"""
create a product and save into db
"""
try:
product_to_buy = ProductToBuy(
owner=product_params["owner"],
product_name=product_params["productname"],
broad_type=product_params["broadtype"],
trade_type=product_params["tradetype"],
sub_type=product_params["subtype"],
release_time=product_params["releasetime"],
)
product_to_buy.save()
nid = create_nid(product_to_buy.id)
product_to_buy.nid = nid
product_to_buy.save()
return product_to_buy
except Exception, e:
print e
return None
def crawler_types(types,
web_site,
url,
):
#index stands for the pageIndex
pattern = ALL_PATTERN[web_site.title]
for index in range(1, 100):
new_url = build_url_page(url, web_site.title, index, types)
html_page = urllib2.urlopen(new_url)
html_content = html_page.read()
html_content = gzip_content(html_content)
#get content
content = BeautifulSoup(html_content)
out = content.findAll(pattern['all_content_tag'], pattern['all_content_dict'])
contents = ''.join([str(item) for item in out])
chapter = BeautifulSoup(contents)
fictions = chapter.findAll(pattern['all_fiction_tag'], pattern['all_fiction_dict'])
for item in fictions:
#get fiction title
contents = str(item)
try:
fiction_title = re.findall(pattern['all_fiction_title'], contents)
fiction_title = ''.join([str(_item) for _item in fiction_title])
#get fiction url
fiction_url = re.findall(pattern['all_fiction_url'], contents)
fiction_url = ''.join([str(_item) for _item in fiction_url[0]])
#get fiction type
fiction_type = re.findall(pattern['all_fiction_type'], contents)
fiction_type = ''.join([str(_item) for _item in fiction_type])
#get fiction id in thissite
author_name = re.findall(pattern['all_author_name'], contents)
author_name = ''.join([str(_item) for _item in author_name])
ids = re.findall(pattern['ids_pattern'], fiction_url)
if not fiction_title or not fiction_url or not fiction_type or not author_name:
continue
#get write information
except:
continue
print '小说%s抓取开始' % fiction_title
try:
#if the fiction has been select into the database
#which is indetified by author and title
hash_url = HashUrl.objects.get(urls = fiction_url)
continue
except:
hash_url = HashUrl(urls = fiction_url)
hash_url.save()
fiction_infor = get_book_infor(web_site.url,
web_site.title,
fiction_url,
)
if not fiction_infor:
continue
#save tag
#save all the fiction into database
fic = Fiction(fiction_title = fiction_title,
fiction_avatar_url = fiction_infor['avatar'],
fiction_intro = fiction_infor['intro'],
fiction_id = ids[0],
fiction_style = types,
total_word= fiction_infor['total_word'],
stock_time = 10,
com_word = "",
source_site = web_site,
click_time = fiction_infor['click_time'],
rec_time = fiction_infor['rec_time'],
author = author_name,
author_url = "",
)
fic.save()
fic.fiction_nid = create_nid(fic.id)
fic.save()
print '小说 %s 基本信息存入数据库' % fiction_title
#save tags
for tags in fiction_infor['tags']:
try:
tag = Tag.objects.get(tag = tags)
except:
tag = Tag(tag = tags)
tag.save()
fic.tag.add(tag)
fic.save()
ms = MemberShip(fiction = fic, website = web_site)
ms.save()
threads = []
print '获取小说 %s 章节' % fiction_title
chapter_url = build_url_fiction(ids[0], web_site.title)
#chapter_infor = chapter_func[web_site.title](chapter_url)
fiction_intro = fiction_infor['intro']
if isinstance(fiction_title, unicode):
fiction_title = fiction_title.encode('utf-8')
t1 = threading.Thread(target = build_index_database, args = (fiction_title, fic, '1'))
t2 = threading.Thread(target = chapter_func[web_site.title], args = (chapter_url, fic, web_site))
t1.start()
t2.start()
t1.join()
t2.join()
def crawler_types(
types,
web_site,
url,
):
#index stands for the pageIndex
pattern = ALL_PATTERN[web_site.title]
for index in range(1, 100):
new_url = build_url_page(url, web_site.title, index, types)
html_page = urllib2.urlopen(new_url)
html_content = html_page.read()
html_content = gzip_content(html_content)
#get content
content = BeautifulSoup(html_content)
out = content.findAll(pattern['all_content_tag'],
pattern['all_content_dict'])
contents = ''.join([str(item) for item in out])
chapter = BeautifulSoup(contents)
fictions = chapter.findAll(pattern['all_fiction_tag'],
pattern['all_fiction_dict'])
for item in fictions:
#get fiction title
contents = str(item)
try:
fiction_title = re.findall(pattern['all_fiction_title'],
contents)
fiction_title = ''.join(
[str(_item) for _item in fiction_title])
#get fiction url
fiction_url = re.findall(pattern['all_fiction_url'], contents)
fiction_url = ''.join([str(_item) for _item in fiction_url[0]])
#get fiction type
fiction_type = re.findall(pattern['all_fiction_type'],
contents)
fiction_type = ''.join([str(_item) for _item in fiction_type])
#get fiction id in thissite
author_name = re.findall(pattern['all_author_name'], contents)
author_name = ''.join([str(_item) for _item in author_name])
ids = re.findall(pattern['ids_pattern'], fiction_url)
if not fiction_title or not fiction_url or not fiction_type or not author_name:
continue
#get write information
except:
continue
print '小说%s抓取开始' % fiction_title
try:
#if the fiction has been select into the database
#which is indetified by author and title
hash_url = HashUrl.objects.get(urls=fiction_url)
continue
except:
hash_url = HashUrl(urls=fiction_url)
hash_url.save()
fiction_infor = get_book_infor(
web_site.url,
web_site.title,
fiction_url,
)
if not fiction_infor:
continue
#save tag
#save all the fiction into database
fic = Fiction(
fiction_title=fiction_title,
fiction_avatar_url=fiction_infor['avatar'],
fiction_intro=fiction_infor['intro'],
fiction_id=ids[0],
fiction_style=types,
total_word=fiction_infor['total_word'],
stock_time=10,
com_word="",
source_site=web_site,
click_time=fiction_infor['click_time'],
rec_time=fiction_infor['rec_time'],
author=author_name,
author_url="",
)
fic.save()
fic.fiction_nid = create_nid(fic.id)
fic.save()
print '小说 %s 基本信息存入数据库' % fiction_title
#save tags
for tags in fiction_infor['tags']:
try:
tag = Tag.objects.get(tag=tags)
except:
tag = Tag(tag=tags)
tag.save()
fic.tag.add(tag)
fic.save()
ms = MemberShip(fiction=fic, website=web_site)
ms.save()
threads = []
print '获取小说 %s 章节' % fiction_title
chapter_url = build_url_fiction(ids[0], web_site.title)
#chapter_infor = chapter_func[web_site.title](chapter_url)
fiction_intro = fiction_infor['intro']
if isinstance(fiction_title, unicode):
fiction_title = fiction_title.encode('utf-8')
t1 = threading.Thread(target=build_index_database,
args=(fiction_title, fic, '1'))
t2 = threading.Thread(target=chapter_func[web_site.title],
args=(chapter_url, fic, web_site))
t1.start()
t2.start()
t1.join()
t2.join()
def run(self):
"""thread method"""
#get all the fresh information
_headers = {
"User-Agent":
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.1) Gecko/20090624 Firefox/3.5",
"Accept": "text/plain"
}
print self.newest_url
request = urllib2.Request(self.newest_url, headers=_headers)
html_page = urllib2.urlopen(request).read()
try:
import gzip, StringIO
data = html_page
data = StringIO.StringIO(data)
gzipper = gzip.GzipFile(fileobj=data)
html = gzipper.read()
html_page = html
except:
pass
html_page = BeautifulSoup(str(html_page))
content = html_page.findAll(self.content_tag, self.content_dict)
contents = ''.join([str(item) for item in content])
chapter_infor = BeautifulSoup(contents)
content = chapter_infor.findAll(self.chapter_tag, self.chapter_dict)
indexs = 1
print content
for item in content:
indexs += 1
contents = str(item)
types = ''.join(re.findall(self.types_pattern, contents))
title = ''.join(re.findall(self.title_pattern, contents))
chapter = ''.join(re.findall(self.chapter_pattern, contents))
author = ''.join(re.findall(self.author_pattern, contents))
fiction_url = ''.join(
re.findall(self.fiction_url_pattern, contents))
chapter_url = ''.join(
re.findall(self.chapter_url_pattern, contents))
if not types or not title or \
not chapter or not author or not fiction_url or not chapter_url:
continue
newest_chapter_url = chapter_url
host = self.host
print author
if self.host[len(self.host) - 1] == '/':
host = self.host[:len(self.host) - 1]
if chapter_url[0] == '/':
chapter_url = host + chapter_url
if fiction_url[0] == '/':
fiction_url = host + fiction_url
try:
web_site = FictionWebSite.objects.get(url=self.host)
except:
web_site = FictionWebSite(title=self.thread_name,
url=self.host)
web_site.save()
try:
hash_url = HashUrl.objects.get(urls=fiction_url)
is_exit = True
fic = Fiction.objects.get(fiction_title=title, author=author)
except:
is_exit = False
print 'here'
if not is_exit:
try:
hash_url = HashUrl(urls=fiction_url)
hash_url.save()
except:
continue
#if the fiction got by crawler is the newest one
#get the book infor
book_infor = get_book_infor(self.host, self.thread_name,
fiction_url, True)
ids = re.findall(ALL_PATTERN[web_site.title]['ids_pattern'],
fiction_url)
types = '4' if not STYLE[self.thread_name].has_key(book_infor['types']) else \
STYLE[self.thread_name][(book_infor['types'])]
try:
fic = Fiction(
fiction_title=title,
fiction_avatar_url=book_infor['avatar'],
fiction_intro=book_infor['intro'],
fiction_id=ids[0],
fiction_style=types,
total_word=book_infor['total_word'],
com_word="",
source_site=web_site,
click_time=book_infor['click_time'],
rec_time=book_infor['rec_time'],
author=author,
stock_time=0,
author_url="",
)
fic.save()
fic.fiction_nid = create_nid(fic.id)
fic.save()
member = MemberShip(fiction=fic,
website=web_site,
fiction_url=fiction_url)
member.save()
del member
except Exception, e:
print 'Ever'
continue
#search only by fiction title
for item in mmseg.Algorithm(title):
try:
index = Index.objects.get(key=item.text)
except:
index = Index(key=item.text)
index.save()
IndexFictionRelationship.objects.create(
key=index,
fiction=fic,
position=','.join([str(item.start),
str(item.end)]),
bit='2', #chapter
)
#get all chapters
if book_infor.has_key('read_url'):
chapter_url = book_infor['read_url']
else:
chapter_url = build_url_fiction(ids[0], web_site.title)
get_chapters_thread = threading.Thread(
target=chapter_func[web_site.title],
args=(chapter_url, fic, web_site, '1'))
get_chapters_thread.start()
get_chapters_thread.join()
#if the fiction has been inserted into the database before
else:
print "yes it is!"
#get the max index of chapters
try:
chapter_index = ChapterIndex.objects.get(
fiction=fic.id, web_site=web_site.title)
except Exception, e1:
try:
chapter_index = ChapterIndex.objects.filter(
fiction=fic.id, web_site=web_site.title)[0]
except Exception, e:
print e
print e1
continue
def run(self):
"""thread method"""
#get all the fresh information
_headers = {"User-Agent": "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.1) Gecko/20090624 Firefox/3.5",
"Accept": "text/plain"}
print self.newest_url
request = urllib2.Request(self.newest_url, headers = _headers)
html_page = urllib2.urlopen(request).read()
try:
import gzip, StringIO
data = html_page
data = StringIO.StringIO(data)
gzipper = gzip.GzipFile(fileobj=data)
html = gzipper.read()
html_page = html
except:
pass
html_page = BeautifulSoup(str(html_page))
content = html_page.findAll(self.content_tag, self.content_dict)
contents = ''.join([str(item) for item in content])
chapter_infor = BeautifulSoup(contents)
content = chapter_infor.findAll(self.chapter_tag, self.chapter_dict)
indexs = 1
print content
for item in content:
indexs += 1
contents = str(item)
types = ''.join(re.findall(self.types_pattern, contents))
title = ''.join(re.findall(self.title_pattern, contents))
chapter = ''.join(re.findall(self.chapter_pattern, contents))
author = ''.join(re.findall(self.author_pattern, contents))
fiction_url = ''.join(re.findall(self.fiction_url_pattern, contents))
chapter_url = ''.join(re.findall(self.chapter_url_pattern, contents))
if not types or not title or \
not chapter or not author or not fiction_url or not chapter_url:
continue
newest_chapter_url = chapter_url
host = self.host
print author
if self.host[len(self.host) - 1] == '/':
host = self.host[:len(self.host) - 1]
if chapter_url[0] == '/':
chapter_url = host + chapter_url
if fiction_url[0] == '/':
fiction_url = host + fiction_url
try:
web_site = FictionWebSite.objects.get(url = self.host)
except:
web_site = FictionWebSite(title = self.thread_name, url = self.host)
web_site.save()
try:
hash_url = HashUrl.objects.get(urls = fiction_url)
is_exit = True
fic = Fiction.objects.get(fiction_title = title, author = author)
except:
is_exit = False
print 'here'
if not is_exit:
try:
hash_url = HashUrl(urls = fiction_url)
hash_url.save()
except:
continue
#if the fiction got by crawler is the newest one
#get the book infor
book_infor = get_book_infor(self.host, self.thread_name, fiction_url, True)
ids = re.findall(ALL_PATTERN[web_site.title]['ids_pattern'], fiction_url)
types = '4' if not STYLE[self.thread_name].has_key(book_infor['types']) else \
STYLE[self.thread_name][(book_infor['types'])]
try:
fic = Fiction(fiction_title = title,
fiction_avatar_url = book_infor['avatar'],
fiction_intro = book_infor['intro'],
fiction_id = ids[0],
fiction_style = types,
total_word = book_infor['total_word'],
com_word = "",
source_site = web_site,
click_time = book_infor['click_time'],
rec_time = book_infor['rec_time'],
author = author,
stock_time = 0,
author_url = "",
)
fic.save()
fic.fiction_nid = create_nid(fic.id)
fic.save()
member = MemberShip(fiction = fic, website = web_site, fiction_url = fiction_url)
member.save()
del member
except Exception,e:
print 'Ever'
continue
#search only by fiction title
for item in mmseg.Algorithm(title):
try:
index = Index.objects.get(key = item.text)
except:
index = Index(key = item.text)
index.save()
IndexFictionRelationship.objects.create(key = index,
fiction = fic,
position = ','.join([str(item.start), str(item.end)]),
bit = '2',#chapter
)
#get all chapters
if book_infor.has_key('read_url'):
chapter_url = book_infor['read_url']
else:
chapter_url = build_url_fiction(ids[0], web_site.title)
get_chapters_thread = threading.Thread(target = chapter_func[web_site.title],
args = (chapter_url, fic, web_site, '1'))
get_chapters_thread.start()
get_chapters_thread.join()
#if the fiction has been inserted into the database before
else:
print "yes it is!"
#get the max index of chapters
try:
chapter_index = ChapterIndex.objects.get(fiction = fic.id, web_site = web_site.title)
except Exception, e1:
try:
chapter_index = ChapterIndex.objects.filter(fiction = fic.id, web_site = web_site.title)[0]
except Exception, e:
print e
print e1
continue
def crawler_types(
types,
web_site,
url,
):
#index stands for the pageIndex
pattern = ALL_PATTERN[web_site.title]
for index in range(1, 100):
new_url = build_url_page(url, web_site.title, index, types)
html_page = urllib2.urlopen(new_url)
html_content = html_page.read()
html_content = gzip_content(html_content)
#get content
content = BeautifulSoup(html_content)
out = content.findAll(pattern['all_content_tag'],
pattern['all_content_dict'])
if not out:
break
contents = ''.join([str(item) for item in out])
chapter = BeautifulSoup(contents)
fictions = chapter.findAll(pattern['all_fiction_tag'],
pattern['all_fiction_dict'])
for item in fictions:
#get fiction title
contents = str(item)
try:
fiction_title = re.findall(pattern['all_fiction_title'],
contents)
fiction_title = ''.join(
[str(_item) for _item in fiction_title])
#get fiction url
fiction_url = re.findall(pattern['all_fiction_url'], contents)
fiction_url = ''.join([str(_item) for _item in fiction_url[0]])
#get fiction type
fiction_type = re.findall(pattern['all_fiction_type'],
contents)
fiction_type = ''.join([str(_item) for _item in fiction_type])
#get fiction id in thissite
author_name = re.findall(pattern['all_author_name'], contents)
author_name = ''.join([str(_item) for _item in author_name])
ids = re.findall(pattern['ids_pattern'], fiction_url)
if not fiction_title or not fiction_url or not author_name:
continue
#get write information
except Exception, e:
continue
try:
hash_url = HashUrl.objects.get(urls=fiction_url)
continue
except:
hash_url = HashUrl(urls=fiction_url)
hash_url.save()
fiction_infor = get_book_infor(
web_site.url,
web_site.title,
fiction_url,
)
if not fiction_infor:
continue
#save tag
#save all the fiction into database
try:
#如果同样的标题的小说已经被收录,唯一性由标题和作者确定
fic = Fiction.objects.get(fiction_title=fiction_title,
author=author_name)
#如果所在网站相同，则不继续处理
DG.trace("get it")
if fic.source_site.title == web_site.title:
continue
except:
fic = Fiction(
fiction_title=fiction_title,
fiction_avatar_url=fiction_infor['avatar'],
fiction_intro=fiction_infor['intro'],
fiction_id=ids[0],
fiction_style=types,
total_word=fiction_infor['total_word'],
stock_time=10,
com_word="",
source_site=web_site,
click_time=fiction_infor['click_time'],
rec_time=fiction_infor['rec_time'],
author=author_name,
author_url="",
)
fic.save()
fic.fiction_nid = create_nid(fic.id)
fic.save()
if isinstance(fiction_title, unicode):
fiction_title = fiction_title.encode('utf-8')
#如果是新加入的小说，则为其建立索引
#t1 = threading.Thread(target = build_index_database, args = (fiction_title, fic, '1'))
#t1.start()
#t1.join()
#save tags
for tags in fiction_infor['tags']:
try:
tag = Tag.objects.get(tag=tags)
except:
tag = Tag(tag=tags)
tag.save()
fic.tag.add(tag)
fic.save()
#新添小说和网站的联系表
ms = MemberShip(fiction=fic,
website=web_site,
fiction_url=fiction_url)
ms.save()
#获取该小说的所有章节
chapter_url = build_url_fiction(ids[0], web_site.title)
t2 = threading.Thread(target=chapter_func[web_site.title],
args=(chapter_url, fic, web_site))
t2.start()
t2.join()
