def fetchWWWFoodList(self, url, additions={}, timeout=TIMEOUT, implementor=None):
headers = {
"User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36",
}
result = request.get(url, headers=headers, timeout=timeout, format='HTML')
foods = result.findall('.//div[@id="shop-all-list"]//ul//li')
print len(foods)
if len(foods) < 15:
nextpage = None
else:
index = url.split('/')
index[-1] = str(int(index[-1]) + 1)
nextpage = '/'.join(index)
yield nextpage
for one in foods:
groupbuy = request.getHtmlNodeContent(one.find('.//div[@class="svr-info"]//a'), {'ATTR':'href'})
detail = request.get(groupbuy, headers=headers, timeout=timeout, format='HTML')
pic = []
try:
for pic_one in detail.findall('.//div[@class="detail"]'):
if request.getHtmlNodeContent(pic_one.find('.//span[@class="name"]'), 'TEXT') == '商户介绍':
pic.extend([request.getHtmlNodeContent(img, {'ATTR':'lazy-src-load'}) for img in pic_one.findall('.//img')])
break
except:
pass
additions['pic'] = pic
gid = groupbuy.split('/')[-1]
url = 'http://t.dianping.com/ajax/dealGroupShopDetail?dealGroupId=%s&action=shops' % gid
yield {'url': url, 'additions':additions}
def fetchTuanFoodList(self, url, additions={}, timeout=TIMEOUT, implementor=None):
headers = {
"User-Agent":"iPhone; CPU iPhone OS 9_1 like Mac OS X AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1",
}
result = request.get(url, headers=headers, timeout=timeout, format='HTML')
foods = result.findall('.//ul[@class="tg-floor-list Fix tg-floor-list-freak"]//a[@class="tg-floor-img"]')
if len(foods) < 40:
nextpage = None
else:
index = url.split('=')
index[-1] = str(int(index[-1]) + 1)
nextpage = '-'.join(index)
yield nextpage
for one in foods:
detail = request.get('http://t.dianping.com%s' % request.getHtmlNodeContent(one, {'ATTR':'href'}), headers=headers, timeout=timeout, format='HTML')
pic = []
try:
for pic_one in detail.findall('.//div[@class="detail"]'):
if request.getHtmlNodeContent(pic_one.find('.//span[@class="name"]'), 'TEXT') == '商户介绍':
pic.extend([request.getHtmlNodeContent(img, {'ATTR':'lazy-src-load'}) for img in pic_one.findall('.//img')])
break
except:
pass
additions['pic'] = pic
gid = request.getHtmlNodeContent(one, {'ATTR':'href'}).split('/')[-1]
url = 'http://t.dianping.com/ajax/dealGroupShopDetail?dealGroupId=%s&action=shops' % gid
yield {'url': url, 'additions':additions}
def fetchList(self, url, additions={}, timeout=TIMEOUT, implementor=None):
result = request.get(url, timeout=timeout, format='HTML')
news = result.findall('.//div[@class="news_nr"]//li')
news = zip(*[iter(news)]*5)
for one in news:
category, name, detail_link, _, icon = one
name = request.getHtmlNodeContent(name.find('.//div'), 'TEXT')
icon = request.getHtmlNodeContent(icon.find('.//div'), 'TEXT').replace('"', '')
detail_link = request.getHtmlNodeContent(detail_link.find('.//div'), 'TEXT').replace('"', '')
detail = request.get(detail_link, timeout=timeout, format='HTML')
desc = ''
src = '东方网'
category = request.getHtmlNodeContent(category, 'TEXT')
atime = request.getHtmlNodeContent(detail.find('.//div[@id="title"]//span[@class="src"]'), 'TEXT').split(u'\u2003')[-1]
atime = atime.split(u'\xa0\xa0\xa0\xa0')[0]
atime = datetime.strptime(atime, '%Y-%m-%d %H:%M')
create_time = datetime.now()
update_time = datetime.now()
data = {"name":name,
"icon":icon,
"detail_link":detail_link,
"desc":desc,
"src":src,
"category":category,
'group':'text',
'content':'',
"atime":atime,
"create_time":create_time,
"update_time":update_time,
'tid':self.tid}
yield Data(**data)
def fetchTuanFoodList(self,
url,
additions={},
timeout=TIMEOUT,
implementor=None):
headers = {
"User-Agent":
"iPhone; CPU iPhone OS 9_1 like Mac OS X AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1",
}
result = request.get(url,
headers=headers,
timeout=timeout,
format='HTML')
foods = result.findall(
'.//ul[@class="tg-floor-list Fix tg-floor-list-freak"]//a[@class="tg-floor-img"]'
)
if len(foods) < 40:
nextpage = None
else:
index = url.split('=')
index[-1] = str(int(index[-1]) + 1)
nextpage = '-'.join(index)
yield nextpage
for one in foods:
detail = request.get(
'http://t.dianping.com%s' %
request.getHtmlNodeContent(one, {'ATTR': 'href'}),
headers=headers,
timeout=timeout,
format='HTML')
pic = []
try:
for pic_one in detail.findall('.//div[@class="detail"]'):
if request.getHtmlNodeContent(
pic_one.find('.//span[@class="name"]'),
'TEXT') == '商户介绍':
pic.extend([
request.getHtmlNodeContent(
img, {'ATTR': 'lazy-src-load'})
for img in pic_one.findall('.//img')
])
break
except:
pass
additions['pic'] = pic
gid = request.getHtmlNodeContent(one, {
'ATTR': 'href'
}).split('/')[-1]
url = 'http://t.dianping.com/ajax/dealGroupShopDetail?dealGroupId=%s&action=shops' % gid
yield {'url': url, 'additions': additions}
def fetchList(self, url, additions={}, timeout=TIMEOUT, implementor=None):
result = request.get(url, timeout=timeout, format='JSON')
news = result['data']['data']
if result['data']['is_more']:
index = url.split('=')
index[-1] = str(int(index[-1]) + 1)
nextpage = '='.join(index)
else:
nextpage = None
nextpage = None
yield nextpage
for one in news:
name = one['title']
icon = one['img_url']
detail_link = one['link'].strip()
desc = one['description']
src = '虎扑新闻'
category = '足球'
group = 'text'
detail = request.get(detail_link, timeout=timeout, format='HTML')
atime = request.getHtmlNodeContent(
detail.find('.//span[@class="stime"]'), 'TEXT').strip()
if not atime:
atime = request.getHtmlNodeContent(
detail.find('.//span[@id="pubtime_baidu"]'),
'TEXT').strip()
else:
atime = '%s:00' % atime
if not atime:
continue
else:
atime = datetime.strptime(atime, '%Y-%m-%d %H:%M:%S')
create_time = datetime.now()
update_time = datetime.now()
data = {
"name": name,
"icon": icon,
"detail_link": detail_link,
"desc": desc,
"src": src,
"category": category,
'group': group,
'content': '',
"atime": atime,
"create_time": create_time,
"update_time": update_time,
'tid': self.tid
}
yield Data(**data)
def fetchShopList(self,
url,
additions={},
timeout=TIMEOUT,
implementor=None):
headers = {
"User-Agent":
"iPhone; CPU iPhone OS 9_1 like Mac OS X AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1",
}
result = request.get(url,
headers=headers,
timeout=timeout,
format='JSON')
shops = result['msg']['shops']
for one in shops:
additions = dict(additions, **{})
additions['name'] = one['shopName'] + one['branchName']
additions['address'] = one['address']
additions['tel'] = one['contactPhone']
additions['longitude'] = one['glng']
additions['latitude'] = one['glat']
additions['desc'] = one['businessHours'] + ',' + one['crossRoad']
additions['average'] = one['avgPrice']
yield {
'url': 'http://www.dianping.com/shop/%s' % str(one['shopId']),
'additions': additions
}
def fetchWWWFoodList(self,
url,
additions={},
timeout=TIMEOUT,
implementor=None):
headers = {
"User-Agent":
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36",
}
result = request.get(url,
headers=headers,
timeout=timeout,
format='HTML')
foods = result.findall('.//div[@id="shop-all-list"]//ul//li')
print len(foods)
if len(foods) < 15:
nextpage = None
else:
index = url.split('/')
index[-1] = str(int(index[-1]) + 1)
nextpage = '/'.join(index)
yield nextpage
for one in foods:
groupbuy = request.getHtmlNodeContent(
one.find('.//div[@class="svr-info"]//a'), {'ATTR': 'href'})
detail = request.get(groupbuy,
headers=headers,
timeout=timeout,
format='HTML')
pic = []
try:
for pic_one in detail.findall('.//div[@class="detail"]'):
if request.getHtmlNodeContent(
pic_one.find('.//span[@class="name"]'),
'TEXT') == '商户介绍':
pic.extend([
request.getHtmlNodeContent(
img, {'ATTR': 'lazy-src-load'})
for img in pic_one.findall('.//img')
])
break
except:
pass
additions['pic'] = pic
gid = groupbuy.split('/')[-1]
url = 'http://t.dianping.com/ajax/dealGroupShopDetail?dealGroupId=%s&action=shops' % gid
yield {'url': url, 'additions': additions}
def fetchList(self, url, additions={}, timeout=TIMEOUT, implementor=None):
result = request.get(url, timeout=timeout, format='JSON')
news = result['data']['data']
if result['data']['is_more']:
index = url.split('=')
index[-1] = str(int(index[-1]) + 1)
nextpage = '='.join(index)
else:
nextpage = None
nextpage = None
yield nextpage
for one in news:
name = one['title']
icon = one['img_url']
detail_link = one['link'].strip()
desc = one['description']
src = '虎扑新闻'
category = '足球'
group = 'text'
detail = request.get(detail_link, timeout=timeout, format='HTML')
atime = request.getHtmlNodeContent(detail.find('.//span[@class="stime"]'), 'TEXT').strip()
if not atime:
atime = request.getHtmlNodeContent(detail.find('.//span[@id="pubtime_baidu"]'), 'TEXT').strip()
else:
atime = '%s:00' % atime
if not atime:
continue
else:
atime = datetime.strptime(atime, '%Y-%m-%d %H:%M:%S')
create_time = datetime.now()
update_time = datetime.now()
data = {"name":name,
"icon":icon,
"detail_link":detail_link,
"desc":desc,
"src":src,
"category":category,
'group':group,
'content':'',
"atime":atime,
"create_time":create_time,
"update_time":update_time,
'tid':self.tid}
yield Data(**data)
def getArticle(aid):
projection = {'uid':1, 'name':1, 'clsname':1, 'filepath':1, 'digest':1}
article = request.post('%sgdc/api/article/%s' % (HOST, str(aid)), {'projection':json.dumps(projection), 'limit':'one'}, format='JSON', s=session)
article = article['article']
filepath = article['filepath']
if filepath in Store and article['digest'] == Store[filepath]:
return article
result = request.get('%sstatic/exe/%s' % (HOST, filepath), format='TEXT')
persist(filepath, result)
Store[filepath] = article['digest']
return article
def getDatamodel(dmid):
projection = {'filepath':1, 'digest':1, 'name':1}
datamodel = request.post('%sgdc/api/datamodel/%s' % (HOST, str(dmid)), {'projection':json.dumps(projection), 'limit':'one'}, format='JSON', s=session)
datamodel = datamodel['datamodel']
filepath = datamodel['filepath']
if filepath in Store and datamodel['digest'] == Store[filepath]:
return datamodel
result = request.get('%sstatic/exe/%s' % (HOST, filepath), format='TEXT')
persist(filepath, result)
Store[filepath] = datamodel['digest']
return datamodel
def getUnit(uid):
projection = {'name':1, 'filepath':1, 'digest':1, 'dmid':1}
unit = request.post('%sgdc/api/unit/%s' % (HOST, str(uid)), {'projection':json.dumps(projection), 'limit':'one'}, format='JSON', s=session)
unit = unit['unit']
filepath = unit['filepath']
if filepath in Store and unit['digest'] == Store[filepath]:
return unit
result = request.get('%sstatic/exe/%s' % (HOST, filepath), format='TEXT')
persist(filepath, result)
Store[filepath] = unit['digest']
filepath = os.path.join(os.path.dirname(os.path.join(CURRPATH, filepath)), '__init__.py')
persist(filepath, '#!/usr/bin/env python\n# coding=utf8')
return unit
def fetchList(self, url, additions={}, timeout=TIMEOUT, implementor=None):
result = request.get(url, timeout=timeout, format='HTML')
news = result.findall('.//div[@class="news_nr"]//li')
news = zip(*[iter(news)] * 5)
for one in news:
category, name, detail_link, _, icon = one
name = request.getHtmlNodeContent(name.find('.//div'), 'TEXT')
icon = request.getHtmlNodeContent(icon.find('.//div'),
'TEXT').replace('"', '')
detail_link = request.getHtmlNodeContent(
detail_link.find('.//div'), 'TEXT').replace('"', '')
detail = request.get(detail_link, timeout=timeout, format='HTML')
desc = ''
src = '东方网'
category = request.getHtmlNodeContent(category, 'TEXT')
atime = request.getHtmlNodeContent(
detail.find('.//div[@id="title"]//span[@class="src"]'),
'TEXT').split(u'\u2003')[-1]
atime = atime.split(u'\xa0\xa0\xa0\xa0')[0]
atime = datetime.strptime(atime, '%Y-%m-%d %H:%M')
create_time = datetime.now()
update_time = datetime.now()
data = {
"name": name,
"icon": icon,
"detail_link": detail_link,
"desc": desc,
"src": src,
"category": category,
'group': 'text',
'content': '',
"atime": atime,
"create_time": create_time,
"update_time": update_time,
'tid': self.tid
}
yield Data(**data)
def getDatamodel(dmid):
projection = {'filepath': 1, 'digest': 1, 'name': 1}
datamodel = request.post('%sgdc/api/datamodel/%s' % (HOST, str(dmid)), {
'projection': json.dumps(projection),
'limit': 'one'
},
format='JSON',
s=session)
datamodel = datamodel['datamodel']
filepath = datamodel['filepath']
if filepath in Store and datamodel['digest'] == Store[filepath]:
return datamodel
result = request.get('%sstatic/exe/%s' % (HOST, filepath), format='TEXT')
persist(filepath, result)
Store[filepath] = datamodel['digest']
return datamodel
def fetchShopList(self, url, additions={}, timeout=TIMEOUT, implementor=None):
headers = {
"User-Agent":"iPhone; CPU iPhone OS 9_1 like Mac OS X AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1",
}
result = request.get(url, headers=headers, timeout=timeout, format='JSON')
shops = result['msg']['shops']
for one in shops:
additions = dict(additions, **{})
additions['name'] = one['shopName'] + one['branchName']
additions['address'] = one['address']
additions['tel'] = one['contactPhone']
additions['longitude'] = one['glng']
additions['latitude'] = one['glat']
additions['desc'] = one['businessHours'] + ',' + one['crossRoad']
additions['average'] = one['avgPrice']
yield {'url':'http://www.dianping.com/shop/%s' % str(one['shopId']), 'additions':additions}
def fetchList(self, url, additions={}, timeout=TIMEOUT, implementor=None):
result = request.get(url, timeout=timeout, format='JSON')
news = result['result']
if len(news) == 0:
nextpage = None
else:
urlobj, params = URLParse.decode(url)
span = int(params['cend']) - int(params['cstart'])
params['cstart'] = params['cend']
params['cend'] = str(int(params['cstart']) + span)
nextpage = URLParse.encode(urlobj, params)
nextpage = None
yield nextpage
for one in news:
if not one['ctype'] == "news":
continue
name = one['title']
if 'icon' in one:
icon = one['icon']
elif 'image_urls' in one and one['image_urls']:
icon = 'http://i1.go2yd.com/image.php?url=%s&type=thumbnail_200x140' % one['image_urls'][0]
else:
icon = ''
detail_link = one['url']
desc = one['summary']
src = '一点资讯'
category = one['category']
atime = datetime.strptime(one['date'], '%Y-%m-%d %H:%M:%S')
create_time = datetime.now()
update_time = datetime.now()
data = {"name":name,
"icon":icon,
"detail_link":detail_link,
"desc":desc,
"src":src,
"category":category,
'group':'text',
'content':'',
"atime":atime,
"create_time":create_time,
"update_time":update_time,
'tid':self.tid}
yield Data(**data)
def fetchList(self, url, additions={}, timeout=TIMEOUT, implementor=None):
result = request.get(url, timeout=timeout, format='JSON')
news = result['data']
if not 'next' in result:
nextpage = None
else:
urlobj, params = URLParse.decode(url)
if str(params['max_behot_time']) == str(
result['next']['max_behot_time']):
nextpage = None
else:
params['max_behot_time'] = result['next']['max_behot_time']
nextpage = URLParse.encode(urlobj, params)
nextpage = None
yield nextpage
for one in news:
name = one['title']
if 'image_url' in one:
icon = one['image_url']
elif 'image_list' in one and one['image_list']:
icon = one['image_list'][0]['url']
else:
icon = ''
detail_link = one['display_url']
desc = one['source'] + '，' + one['abstract']
src = '今日头条'
category = additions.get('category', '') # '财经'
atime = datetime.strptime(one['datetime'], '%Y-%m-%d %H:%M')
create_time = datetime.now()
update_time = datetime.now()
data = {
"name": name,
"icon": icon,
"detail_link": detail_link,
"desc": desc,
"src": src,
"category": category,
'group': 'text',
'content': '',
"atime": atime,
"create_time": create_time,
"update_time": update_time,
'tid': self.tid
}
yield Data(**data)
def fetchList(self, url, additions={}, timeout=TIMEOUT, implementor=None):
result = request.get(url, timeout=timeout, format='JSON')
news = result['data']
if not 'next' in result:
nextpage = None
else:
urlobj, params = URLParse.decode(url)
if str(params['max_behot_time']) == str(result['next']['max_behot_time']):
nextpage = None
else:
params['max_behot_time'] = result['next']['max_behot_time']
nextpage = URLParse.encode(urlobj, params)
nextpage = None
yield nextpage
for one in news:
name = one['title']
if 'image_url' in one:
icon = one['image_url']
elif 'image_list' in one and one['image_list']:
icon = one['image_list'][0]['url']
else:
icon = ''
detail_link = one['display_url']
desc = one['source'] + '，' + one['abstract']
src = '今日头条'
category = additions.get('category', '') # '财经'
atime = datetime.strptime(one['datetime'], '%Y-%m-%d %H:%M')
create_time = datetime.now()
update_time = datetime.now()
data = {"name":name,
"icon":icon,
"detail_link":detail_link,
"desc":desc,
"src":src,
"category":category,
'group':'text',
'content':'',
"atime":atime,
"create_time":create_time,
"update_time":update_time,
'tid':self.tid}
yield Data(**data)
def getUnit(uid):
projection = {'name': 1, 'filepath': 1, 'digest': 1, 'dmid': 1}
unit = request.post('%sgdc/api/unit/%s' % (HOST, str(uid)), {
'projection': json.dumps(projection),
'limit': 'one'
},
format='JSON',
s=session)
unit = unit['unit']
filepath = unit['filepath']
if filepath in Store and unit['digest'] == Store[filepath]:
return unit
result = request.get('%sstatic/exe/%s' % (HOST, filepath), format='TEXT')
persist(filepath, result)
Store[filepath] = unit['digest']
filepath = os.path.join(os.path.dirname(os.path.join(CURRPATH, filepath)),
'__init__.py')
persist(filepath, '#!/usr/bin/env python\n# coding=utf8')
return unit
def fetchList(self, url, additions={}, timeout=TIMEOUT, implementor=None):
result = request.get(url, timeout=timeout, format='JSON')
news = result['result']['data']
if len(news) < 30:
nextpage = None
else:
index = url.split('=')
index[-1] = str(int(index[-1]) + 1)
nextpage = '='.join(index)
nextpage = None
yield nextpage
for one in news:
name = one['stitle']
icon = one['img']['u']
detail_link = one.get('wapurl') or one.get('url', '')
desc = one['intro']
src = '新浪新闻'
category = '足球'
group = 'text'
if 'http://video.sina.com.cn' in detail_link:
group = 'video'
atime = time.strftime('%Y-%m-%d %H:%M:%S',
time.localtime(float(one['ctime'])))
atime = datetime.strptime(atime, '%Y-%m-%d %H:%M:%S')
create_time = datetime.now()
update_time = datetime.now()
data = {
"name": name,
"icon": icon,
"detail_link": detail_link,
"desc": desc,
"src": src,
"category": category,
'group': group,
'content': '',
"atime": atime,
"create_time": create_time,
"update_time": update_time,
'tid': self.tid
}
yield Data(**data)
def fetchList(self, url, additions={}, timeout=TIMEOUT, implementor=None):
result = request.get(url, timeout=timeout, dirtys=[('artiList({', '{'), ('})', '}')], format='JSON')
news = result['BA8E6OEOwangning']
start, end = url[url.rindex('/')+1:url.rindex('.')].split('-')
span = int(end) - int(start)
if len(news) < span:
nextpage = None
else:
start = end
end = str(int(start) + span)
nextpage = '%s/%s-%s.html' % (url[:url.rindex('/')], start, end)
nextpage = None
yield nextpage
for one in news:
if '|' in url:
continue
name = one['title']
icon = one['imgsrc']
detail_link = 'http://3g.163.com/touch/article.html?channel=sports&docid=%s' % one['docid']
desc = one['digest']
src = '网易新闻'
category = additions.get('category')
atime = datetime.strptime(one['ptime'], '%Y-%m-%d %H:%M:%S')
create_time = datetime.now()
update_time = datetime.now()
data = {"name":name,
"icon":icon,
"detail_link":detail_link,
"desc":desc,
"src":src,
"category":category,
'group':'text',
'content':'',
"atime":atime,
"create_time":create_time,
"update_time":update_time,
'tid':self.tid}
yield Data(**data)
def getArticle(aid):
projection = {
'uid': 1,
'name': 1,
'clsname': 1,
'filepath': 1,
'digest': 1
}
article = request.post('%sgdc/api/article/%s' % (HOST, str(aid)), {
'projection': json.dumps(projection),
'limit': 'one'
},
format='JSON',
s=session)
article = article['article']
filepath = article['filepath']
if filepath in Store and article['digest'] == Store[filepath]:
return article
result = request.get('%sstatic/exe/%s' % (HOST, filepath), format='TEXT')
persist(filepath, result)
Store[filepath] = article['digest']
return article
def fetchList(self, url, additions={}, timeout=TIMEOUT, implementor=None):
result = request.get(url, timeout=timeout, format='JSON')
news = result['result']['data']
if len(news) < 30:
nextpage = None
else:
index = url.split('=')
index[-1] = str(int(index[-1]) + 1)
nextpage = '='.join(index)
nextpage = None
yield nextpage
for one in news:
name = one['stitle']
icon = one['img']['u']
detail_link = one.get('wapurl') or one.get('url', '')
desc = one['intro']
src = '新浪新闻'
category = '足球'
group = 'text'
if 'http://video.sina.com.cn' in detail_link:
group = 'video'
atime = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(float(one['ctime'])))
atime = datetime.strptime(atime, '%Y-%m-%d %H:%M:%S')
create_time = datetime.now()
update_time = datetime.now()
data = {"name":name,
"icon":icon,
"detail_link":detail_link,
"desc":desc,
"src":src,
"category":category,
'group':group,
'content':'',
"atime":atime,
"create_time":create_time,
"update_time":update_time,
'tid':self.tid}
yield Data(**data)
def fetchShopDetail(self, url, additions={}, timeout=TIMEOUT, implementor=None):
headers = {
"User-Agent":"iPhone; CPU iPhone OS 9_1 like Mac OS X AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1",
}
result = request.get(url, headers=headers, timeout=timeout, format='HTML')
food_id = [additions['food_id'], ]
name = additions['name']
desc = additions['desc']
tel = additions['tel']
pic = additions['pic']
province_id = additions['province_id']
city_id = additions['city_id']
tag = []
try:
for one in result.findall('.//p[@class="info info-indent"]'):
prompt = request.getHtmlNodeContent(one.find('.//span'), 'TEXT')
if '标签' in prompt:
tag.extend([request.getHtmlNodeContent(a, 'TEXT') for a in one.findall('.//a')])
except:
pass
area_id = additions['area_id']
town_id = additions['town_id']
country_id = additions['country_id']
address = additions['address']
longitude = additions['longitude']
latitude = additions['latitude']
dianping = {
'url': url,
'star': 0,
'average': additions['average'],
'taste': 0,
'env': 0,
'service': 0,
}
dianping_info = result.findall('.//div[@class="brief-info"]//span')
try:
dianping['star'] = request.getHtmlNodeContent(dianping_info[0], {'ATTR':'class'})
dianping['star'] = dianping['star'].replace('mid-rank-stars mid-str', '')
dianping['star'] = float('%s.%s' % (dianping['star'][0], dianping['star'][1:]))
dianping['taste'] = float(request.getHtmlNodeContent(dianping_info[3], 'TEXT').replace('口味：', ''))
dianping['env'] = float(request.getHtmlNodeContent(dianping_info[4], 'TEXT').replace('环境：', ''))
dianping['service'] = float(request.getHtmlNodeContent(dianping_info[5], 'TEXT').replace('服务：', ''))
except:
pass
src = '大众点评'
link_url = url
atime = datetime.now()
uptime = atime
time = atime
print link_url, name
time_result = request.get(url+'/editmember', headers=headers, timeout=timeout, format='HTML')
time_info = time_result.findall('.//ul[@class="block-inner desc-list contribute-list Fix"]//li')
try:
for one in time_info:
prompt = request.getHtmlNodeContent(one.find('.//strong'), 'TEXT')
if '商户' in prompt:
atime = datetime.strptime('20%s' % request.getHtmlNodeContent(one.find('.//span'), 'TEXT').split('\xc2\xa0')[-1], '%Y-%m-%d')
elif '更新' in prompt:
uptime = datetime.strptime('20%s' % request.getHtmlNodeContent(one.find('.//span'), 'TEXT').split('\xc2\xa0')[-1], '%Y-%m-%d')
except:
pass
data = Data(food_id=food_id, name=name, desc=desc, tel=tel, pic=pic, province_id=province_id,
city_id=city_id, tag=tag, area_id=area_id, town_id=town_id, country_id=country_id, address=address,
longitude=longitude, latitude=latitude, dianping=dianping, src=src, link_url=link_url,
atime=atime, time=time, uptime=uptime, tid=self.tid)
yield data
def fetchList(self, url, additions={}, timeout=TIMEOUT, implementor=None):
result = request.get(url, timeout=timeout, format='HTML')
news = result.findall('.//dl[@id="idcur"]//dd')
news.append(result.find('.//dl[@id="idcur"]//dt'))
for one in news:
name = request.getHtmlNodeContent(one.find('.//p'), 'TEXT')
icon = request.getHtmlNodeContent(one.find('.//img'), {'ATTR':'src'})
detail_link = request.getHtmlNodeContent(one.find('.//a'), {'ATTR':'href'})
detail = request.get(detail_link, timeout=timeout, format='HTML')
desc = ''
src = 'cctv'
category = '足球'
atime = request.getHtmlNodeContent(detail.find('.//div[@class="font_xx"]'), 'TEXT').strip()
atime = ('20%s' % atime.replace('日 ', 'T').split(' 20')[-1]).replace('年', '-').replace('月', '-')
atime = datetime.strptime(atime, '%Y-%m-%dT%H:%M')
create_time = datetime.now()
update_time = datetime.now()
data = {"name":name,
"icon":icon,
"detail_link":detail_link,
"desc":desc,
"src":src,
"category":category,
'group':'pic',
'content':'',
"atime":atime,
"create_time":create_time,
"update_time":update_time,
'tid':self.tid}
yield Data(**data)
news = result.findall('.//ul[@class="il_w120_b1"]//li')
for one in news:
name = request.getHtmlNodeContent(one.find('.//div[@class="text"]//a'), 'TEXT').replace('[高清组图]', '')
icon = request.getHtmlNodeContent(one.find('.//div[@class="image"]//img'), {'ATTR':'src'})
detail_link = request.getHtmlNodeContent(one.find('.//div[@class="image"]//a'), {'ATTR':'href'})
detail = request.get(detail_link, timeout=timeout, format='HTML')
desc = ''
src = 'cctv'
category = '足球'
atime = request.getHtmlNodeContent(detail.find('.//div[@class="font_xx"]'), 'TEXT').strip()
atime = ('20%s' % atime.replace('日 ', 'T').split(' 20')[-1]).replace('年', '-').replace('月', '-')
atime = datetime.strptime(atime, '%Y-%m-%dT%H:%M')
create_time = datetime.now()
update_time = datetime.now()
data = {"name":name,
"icon":icon,
"detail_link":detail_link,
"desc":desc,
"src":src,
"category":category,
'group':'pic',
'content':'',
"atime":atime,
"create_time":create_time,
"update_time":update_time,
'tid':self.tid}
yield Data(**data)
news = result.findall('.//div[@class="text_list"]//ul//li')
for one in news:
name = request.getHtmlNodeContent(one.find('.//a'), 'TEXT')
detail_link = request.getHtmlNodeContent(one.find('.//a'), {'ATTR':'href'})
detail = request.get(detail_link, timeout=timeout, format='HTML')
icon = request.getHtmlNodeContent(detail.find('.//p[@align="center"]//img'), {'ATTR':'src'})
desc = ''
src = 'cctv'
category = '足球'
atime = request.getHtmlNodeContent(detail.find('.//div[@class="function"]//span[@class="info"]//i'), 'TEXT').strip()
atime = ('20%s' % atime.replace('日 ', 'T').split(' 20')[-1]).replace('年', '-').replace('月', '-')
atime = datetime.strptime(atime, '%Y-%m-%dT%H:%M')
create_time = datetime.now()
update_time = datetime.now()
data = {"name":name,
"icon":icon,
"detail_link":detail_link,
"desc":desc,
"src":src,
"category":category,
'group':'text',
'content':'',
"atime":atime,
"create_time":create_time,
"update_time":update_time,
'tid':self.tid}
yield Data(**data)
def fetchShopDetail(self,
url,
additions={},
timeout=TIMEOUT,
implementor=None):
headers = {
"User-Agent":
"iPhone; CPU iPhone OS 9_1 like Mac OS X AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1",
}
result = request.get(url,
headers=headers,
timeout=timeout,
format='HTML')
food_id = [
additions['food_id'],
]
name = additions['name']
desc = additions['desc']
tel = additions['tel']
pic = additions['pic']
province_id = additions['province_id']
city_id = additions['city_id']
tag = []
try:
for one in result.findall('.//p[@class="info info-indent"]'):
prompt = request.getHtmlNodeContent(one.find('.//span'),
'TEXT')
if '标签' in prompt:
tag.extend([
request.getHtmlNodeContent(a, 'TEXT')
for a in one.findall('.//a')
])
except:
pass
area_id = additions['area_id']
town_id = additions['town_id']
country_id = additions['country_id']
address = additions['address']
longitude = additions['longitude']
latitude = additions['latitude']
dianping = {
'url': url,
'star': 0,
'average': additions['average'],
'taste': 0,
'env': 0,
'service': 0,
}
dianping_info = result.findall('.//div[@class="brief-info"]//span')
try:
dianping['star'] = request.getHtmlNodeContent(
dianping_info[0], {'ATTR': 'class'})
dianping['star'] = dianping['star'].replace(
'mid-rank-stars mid-str', '')
dianping['star'] = float(
'%s.%s' % (dianping['star'][0], dianping['star'][1:]))
dianping['taste'] = float(
request.getHtmlNodeContent(dianping_info[3],
'TEXT').replace('口味：', ''))
dianping['env'] = float(
request.getHtmlNodeContent(dianping_info[4],
'TEXT').replace('环境：', ''))
dianping['service'] = float(
request.getHtmlNodeContent(dianping_info[5],
'TEXT').replace('服务：', ''))
except:
pass
src = '大众点评'
link_url = url
atime = datetime.now()
uptime = atime
time = atime
print link_url, name
time_result = request.get(url + '/editmember',
headers=headers,
timeout=timeout,
format='HTML')
time_info = time_result.findall(
'.//ul[@class="block-inner desc-list contribute-list Fix"]//li')
try:
for one in time_info:
prompt = request.getHtmlNodeContent(one.find('.//strong'),
'TEXT')
if '商户' in prompt:
atime = datetime.strptime(
'20%s' % request.getHtmlNodeContent(
one.find('.//span'), 'TEXT').split('\xc2\xa0')[-1],
'%Y-%m-%d')
elif '更新' in prompt:
uptime = datetime.strptime(
'20%s' % request.getHtmlNodeContent(
one.find('.//span'), 'TEXT').split('\xc2\xa0')[-1],
'%Y-%m-%d')
except:
pass
data = Data(food_id=food_id,
name=name,
desc=desc,
tel=tel,
pic=pic,
province_id=province_id,
city_id=city_id,
tag=tag,
area_id=area_id,
town_id=town_id,
country_id=country_id,
address=address,
longitude=longitude,
latitude=latitude,
dianping=dianping,
src=src,
link_url=link_url,
atime=atime,
time=time,
uptime=uptime,
tid=self.tid)
yield data