def get_cities(self, gid, country_id, offset):
PROXY = get_proxy(source="Platform")
x = time.time()
proxies = {'http': 'socks5://' + PROXY, 'https': 'socks5://' + PROXY}
headers = {'User-agent': GetUserAgent()}
try:
target_url = 'http://www.tripadvisor.cn/TourismChildrenAjax?geo={0}&offset={1}&desktop=true'.format(
gid, offset)
page = requests.get(target_url, headers=headers, proxies=proxies)
page.encoding = 'utf8'
content = page.text
res = re.findall(
'ta.store\(\'tourism.popularCitiesMaxPage\', \'(\d+)\'\);',
content)
has_next = False
if res is not None and res != []:
if offset < int(res[0]):
has_next = True
result = []
for line in _parse_city(content=content, target_url=target_url):
per_city = list(line)
per_city.append(country_id)
result.append(per_city)
print insert_db(result)
if has_next:
get_cities.delay(gid, country_id, offset + 1)
except Exception as exc:
update_proxy('Platform', PROXY, x, '23')
self.retry(exc=traceback.format_exc(exc))
def hotel_base_data(self, source, url, other_info, **kwargs):
x = time.time()
PROXY = get_proxy(source="Platform")
proxies = {'http': 'socks5://' + PROXY, 'https': 'socks5://' + PROXY}
headers = {'User-agent': GetUserAgent()}
try:
page = requests.get(url, proxies=proxies, headers=headers, timeout=240)
page.encoding = 'utf8'
content = page.text
# agoda 特殊情况 start
url_about = 'https://www.agoda.com/NewSite/zh-cn/Hotel/AboutHotel?hotelId={0}&languageId=8&hasBcomChildPolicy=False'.format(
other_info['source_id'])
page_about = requests.get(url=url_about, headers=headers)
page_about.encoding = 'utf8'
about_content = page_about.text
other_info['about_content'] = about_content
# agoda end
result = parse_hotel(content=content,
url=url,
other_info=other_info,
source=source)
if not result:
update_proxy('Platform', PROXY, x, '23')
self.retry()
else:
update_task(kwargs['task_id'])
print "Success with " + PROXY + ' CODE 0'
update_proxy('Platform', PROXY, x, '0')
return result
except Exception as exc:
update_proxy('Platform', PROXY, x, '23')
self.retry(exc=traceback.format_exc(exc))
def tripadvisor_city_query_task(self, city_name, **kwargs):
x = time.time()
PROXY = get_proxy(source="Platform")
proxies = {'http': 'socks5://' + PROXY, 'https': 'socks5://' + PROXY}
headers = {'User-agent': GetUserAgent()}
try:
conn = pymysql.connect(host='10.10.180.145',
user='******',
passwd='hourong',
db='SuggestName',
charset="utf8")
with conn as cursor:
print(city_name)
quote_string = quote(city_name.encode('utf8'))
page = requests.get(
'http://www.tripadvisor.cn/TypeAheadJson?interleaved=true&types=geo%2Ctheme_park%2Cair&neighborhood_geos=true&link_type=geo&details=true&max=6&hglt=true&query={0}&action=API&uiOrigin=GEOSCOPE&source=GEOSCOPE'
.format(quote_string),
proxies=proxies,
headers=headers)
page.encoding = 'utf8'
content = page.text.replace('while(1);', '')
for line in get_query_data(content=content,
query_string=city_name):
cursor.execute(
'insert into TripAdvisorSuggestCity (`QueryName`,`Name`,`coords`,`Url`) VALUES (%s,%s,%s,%s)',
line)
conn.close()
update_task(kwargs['task_id'])
print "Success with " + PROXY + ' CODE 0'
update_proxy('Platform', PROXY, x, '0')
except Exception as exc:
update_proxy('Platform', PROXY, x, '23')
self.retry(exc=traceback.format_exc(exc))
def yelp_price_level(self, target_url, mid):
PROXY = get_proxy(source="Platform")
x = time.time()
proxies = {
'http': 'socks5://' + PROXY,
'https': 'socks5://' + PROXY
}
headers = {
'User-agent': GetUserAgent()
}
try:
page = requests.get(target_url, proxies=proxies, headers=headers, timeout=120)
price_level = get_yelp_price_level(page)
if not page.text:
update_proxy('Platform', PROXY, x, '23')
self.retry()
else:
print "Success with " + PROXY + ' CODE 0'
update_proxy('Platform', PROXY, x, '0')
print yelp_price_level_update_db((price_level, mid))
return price_level
except Exception as exc:
update_proxy('Platform', PROXY, x, '23')
self.retry(exc=traceback.format_exc(exc))
def tp_rest_list_page_num(self, index_url, city_id, part):
PROXY = get_proxy(source="Platform")
x = time.time()
proxies = {
'http': 'socks5://' + PROXY,
'https': 'socks5://' + PROXY
}
print "Now Proxy is " + PROXY
headers = {
'User-agent': GetUserAgent()
}
page = requests.get(index_url, proxies=proxies, headers=headers)
page.encoding = 'utf8'
if len(page.text) < 100:
update_proxy('Platform', PROXY, x, '23')
self.retry()
page.encoding = 'utf8'
doc = PyQuery(page.text)
doc.make_links_absolute(index_url)
num_list = []
for item in doc('.pageNumbers a').items():
num = int(rest_oa_pattern.findall(item.attr.href)[0])
num_list.append(num)
tp_rest_detail_page_url.delay(index_url, city_id, part)
try:
for page_num in range(30, max(num_list) + 30, 30):
g_num = rest_g_pattern.findall(index_url)[0]
tp_rest_detail_page_url.delay(index_url.replace('-g' + g_num, '-g{0}-oa{1}'.format(g_num, page_num)),
city_id, part)
except:
pass
def tp_rest_detail_page_url(self, page_num_url, city_id, part):
PROXY = get_proxy(source="Platform")
x = time.time()
proxies = {
'http': 'socks5://' + PROXY,
'https': 'socks5://' + PROXY
}
print "Now Proxy is " + PROXY
headers = {
'User-agent': GetUserAgent()
}
page = requests.get(page_num_url, proxies=proxies, headers=headers)
page.encoding = 'utf8'
if len(page.text) < 100:
update_proxy('Platform', PROXY, x, '23')
self.retry()
doc = PyQuery(page.text)
doc.make_links_absolute(page_num_url)
data = []
worker = u'daodao_poi_base_data'
for item in doc('.property_title').items():
href = item.attr.href
if 'Restaurant_Review' in href:
args = json.dumps(
{u'target_url': unicode(href), u'city_id': unicode(city_id), u'type': u'rest'})
task_id = get_task_id(worker, args=args)
data.append((task_id, worker, args, unicode(part).replace(u'list', u'detail')))
print insert_task(data=data)
def get_images_without_md5(self, source, target_url):
# PROXY = get_proxy(source="Platform")
# proxies = {
# 'http': 'socks5://' + PROXY,
# 'https': 'socks5://' + PROXY
# }
headers = {
'User-agent': GetUserAgent()
}
try:
page = requests.get(target_url, headers=headers, timeout=480)
f = StringIO(page.content)
flag, h, w = is_complete_scale_ok(f)
if flag in [1, 2]:
# x = time.time()
# update_proxy('Platform', PROXY, x, '22')
# print "Image Error with Proxy " + PROXY
self.retry(countdown=2)
else:
# x = time.time()
# print "Success with " + PROXY + ' CODE 0'
file_name = target_url.split('/')[-1].split('.')[0]
save_image(source, file_name, page.content)
# update_proxy('Platform', PROXY, x, '0')
return flag, h, w
except Exception as exc:
# x = time.time()
# update_proxy('Platform', PROXY, x, '22')
self.retry(exc=traceback.format_exc(exc), countdown=2)
def venere_comment(self, target_url, **kwargs):
PROXY = get_proxy(source="Platform")
x = time.time()
proxies = {
'http': 'socks5://' + PROXY,
'https': 'socks5://' + PROXY
}
headers = {
'User-agent': GetUserAgent()
}
try:
page = requests.get(target_url, proxies=proxies, headers=headers, timeout=120)
page.encoding = 'utf8'
result = venere_comment_parser(page.text, target_url)
if not result:
update_proxy('Platform', PROXY, x, '23')
self.retry()
else:
update_task(kwargs['mongo_task_id'])
print "Success with " + PROXY + ' CODE 0'
update_proxy('Platform', PROXY, x, '0')
return result
except Exception as exc:
update_proxy('Platform', PROXY, x, '23')
self.retry(exc=traceback.format_exc(exc))
def booking_list_crawl(task):
# 将任务进行拆分，拆分成该源上的城市中文名和城市id
# eg :黄石国家公园西门&6406®ion , 大雾山国家公园&255516&landmark
# eg: 福森&-1773182
# 任务类型, city, region, landmark
city_name_zh, source_city_id, search_type = task.content.encode(
'utf8').split('&')
# 对城市中文名进行编码
city_name_zh = urllib.quote(city_name_zh)
check_in_year = task.check_in[0:7]
check_in_day = task.check_in[8:]
check_out_year = task.check_out[0:7]
check_out_day = task.check_out[8:]
# 对首页url进行拼接
# url = get_search_url(check_in, check_out, source_city_id, city_name_zh, 1)
# 注意！！！！！！大部分抓的dest_type都是city，黄石国家公园西门是region, 大雾山国家公园大峡谷国家公园都是landmark
Id = source_city_id
dest_type = search_type
destination = city_name_zh
if is_alp(Id[0]):
url = 'http://www.booking.com/searchresults.zh-cn.html?aid=397647;label=bai408jc-index-XX-XX-XX-unspec-cn-com-L%3Azh-O%3Aabn-B%3Achrome-N%3Ayes-S%3Abo-U%3Asalo;sid=4cb8e58619e9a15fe212e5b9fbec271b;dcid=12;checkin_monthday=' + check_in_day + ';checkin_year_month=' + check_in_year + ';checkout_monthday=' + check_out_day + ';checkout_year_month=' + check_out_year + ';class_interval=1;dest_id=' + Id + ';dest_type=' + dest_type + ';dtdisc=0;group_adults=2;group_children=0;hlrd=0;hyb_red=0;inac=0;label_click=undef;nha_red=0;no_rooms=1;offset=0;postcard=0;qrhpp=9f9582988e3752a8d34a7f85874afc39-city-0;redirected_from_city=0;redirected_from_landmark=0;redirected_from_region=0;review_score_group=empty;room1=A%2CA;sb_price_type=total;score_min=0;src=index;src_elem=sb;ss=' + destination + ';ss_all=0;ss_raw=' + destination + ';ssb=empty;sshis=0;origin=search;srpos=1&place_id=' + Id
else:
url = 'http://www.booking.com/searchresults.zh-cn.html?aid=397647;label=bai408jc-index-XX-XX-XX-unspec-cn-com-L%3Azh-O%3Aabn-B%3Achrome-N%3Ayes-S%3Abo-U%3Asalo;sid=4cb8e58619e9a15fe212e5b9fbec271b;dcid=12;checkin_monthday=' + check_in_day + ';checkin_year_month=' + check_in_year + ';checkout_monthday=' + check_out_day + ';checkout_year_month=' + check_out_year + ';class_interval=1;dest_id=' + Id + ';dest_type=' + dest_type + ';dtdisc=0;group_adults=2;group_children=0;hlrd=0;hyb_red=0;inac=0;label_click=undef;nha_red=0;no_rooms=1;offset=0;postcard=0;qrhpp=9f9582988e3752a8d34a7f85874afc39-city-0;redirected_from_city=0;redirected_from_landmark=0;redirected_from_region=0;review_score_group=empty;room1=A%2CA;sb_price_type=total;score_min=0;src=index;src_elem=sb;ss=' + destination + ';ss_all=0;ss_raw=' + destination + ';ssb=empty;sshis=0;origin=search;srpos=1'
print url, '================='
PROXY = get_proxy(source="Platform")
headers = {'User-agent': GetUserAgent()}
proxies = {'http': 'socks5://' + PROXY, 'https': 'socks5://' + PROXY}
page = requests.get(url, proxies=proxies, headers=headers)
page.encoding = 'utf8'
content = page.text
root = HTML.fromstring(content)
hotel = root.xpath('//*[@class="sr_header "]/h1/text()')[0].encode(
'utf-8').replace(',', '').strip()
# print hotel
# 获取酒店数，获取的当前时间内有空房的酒店数
# 有两个数时取后面的数
temp_count = hotelcount_pat.findall(hotel)
hotel_count = temp_count[-1]
crawl_page = int(hotel_count) / 15 + 1
# todo data crawl
# 对首页进行数据爬取
# parse_each_page(page, city_id, continent)
result = list()
result.append(url)
# 开始进行翻页
for page_index in range(1, crawl_page):
offset = 14 + (page_index - 1) * 15
each_page_url = get_search_url(task.check_in, task.check_out,
source_city_id, city_name_zh, offset,
search_type)
result.append(each_page_url)
return result
def booking_comment_without_proxy(self, target_url):
headers = {
'User-agent': GetUserAgent()
}
try:
page = requests.get(target_url, headers=headers, timeout=120)
page.encoding = 'utf8'
result = booking_comment_parser(page.text, target_url)
if not result:
self.retry()
return result
except Exception as exc:
self.retry(exc=traceback.format_exc(exc))
def expedia_comment(self, target_url, **kwargs):
headers = {
'User-agent': GetUserAgent()
}
try:
page = requests.get(target_url, headers=headers, timeout=180)
page.encoding = 'utf8'
result = expedia_comment_parser(page.text, target_url)
if not result:
self.retry()
else:
update_task(kwargs['mongo_task_id'])
return result
except Exception as exc:
self.retry(exc=traceback.format_exc(exc))
def get_lost_poi_image(self, file_path, file_name, target_url):
headers = {
'User-agent': GetUserAgent()
}
try:
page = requests.get(target_url, headers=headers, timeout=480)
f = StringIO(page.content)
flag, h, w = is_complete_scale_ok(f)
if flag in [1, 2]:
self.retry(countdown=2)
else:
save_image(file_path, file_name, page.content)
return flag, h, w
except Exception as exc:
self.retry(exc=traceback.format_exc(exc), countdown=2)
def qyer_img_task(self, target_url, mid):
headers = {
'User-agent': GetUserAgent()
}
try:
page = requests.get(target_url, headers=headers, timeout=120)
raw_img_result = '|'.join(qyer_img_parser(page.text))
if not raw_img_result:
self.retry()
print "Fail", target_url
else:
qyer_img_insert_db((mid, target_url, raw_img_result))
print "Succeed", target_url
return raw_img_result
except:
print "Fail", target_url
self.retry()
def _get_site_url(target_url):
PROXY = get_proxy(source="Platform")
proxies = {
'http': 'socks5://' + PROXY,
'https': 'socks5://' + PROXY
}
headers = {
'User-agent': GetUserAgent()
}
page = requests.get(target_url, proxies=proxies, headers=headers, allow_redirects=False)
source_site_url = page.headers['location']
print source_site_url
# source_site_url = page.url
if source_site_url != '' and source_site_url is not None:
return source_site_url.replace('#_=_', '')
else:
return "Error"
def detail_page(self, pid, page_num, city_id, part):
x = time.time()
PROXY = get_proxy(source="Platform")
proxies = {
'http': 'socks5://' + PROXY,
'https': 'socks5://' + PROXY
}
headers = {
'User-agent': GetUserAgent(),
}
try:
data = {
u'page': unicode(page_num),
u'type': u'city',
u'pid': unicode(pid),
u'sort': u'32',
u'subsort': u'all',
u'isnominate': u'-1',
u'haslastm': u'false',
u'rank': u'6'
}
json_page = requests.post(u'http://place.qyer.com/poi.php?action=list_json', data=data, proxies=proxies,
headers=headers)
json_page.encoding = u'utf8'
content = json_page.text
j_data = json.loads(content)
task_data = []
url_result = []
for attr in j_data[u'data'][u'list']:
worker = u'qyer_poi_task'
args = json.dumps(
{u'target_url': unicode(u'http:' + attr[u'url']), u'city_id': unicode(city_id)})
task_id = get_task_id(worker=worker, args=args)
task_data.append((task_id, worker, args, unicode(part.replace('list', 'detail'))))
url_result.append(u'http' + attr[u'url'])
result = insert_task(data=task_data)
print result
print url_result
return result
except Exception as exc:
update_proxy('Platform', PROXY, x, '23')
self.retry(exc=traceback.format_exc(exc))
def vote(self):
import httplib
httplib.HTTPConnection.debuglevel = 1
httplib.HTTPSConnection.debuglevel = 1
PROXY = get_proxy(source="Platform")
proxies = {
'http': 'socks5://' + PROXY,
'https': 'socks5://' + PROXY
}
print "Now Proxy is " + PROXY
headers = {
'User-agent': GetUserAgent(),
'Referer': 'http://www.travelmeetingsawards-china.com/Events/Awards2015Business/Readers-Voting/?cat=5',
'Host': 'www.travelmeetingsawards-china.com',
'Origin': 'http://www.travelmeetingsawards-china.com',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate',
# 'Cookie': 'EktGUID=91ea164d-e2c6-4748-8e31-33c05e6e5439; EkAnalytics=0; ASP.NET_SessionId=piy2livrdw4nb4vulygiet4y; awardvotes=[{"AwardEventID":7,"AwardCategoryID":5,"AwardSubCategoryID":98,"Datetime":"\/Date(1492764048212)\/"}]; s_cc=true; s_nr=1492766246608-New; _ga=GA1.2.1289463038.1492764050; _gat=1; ecm=user_id=0&isMembershipUser=0&site_id=&username=&new_site=/&unique_id=0&site_preview=0&langvalue=0&DefaultLanguage=2052&NavLanguage=2052&LastValidLanguageID=2052&DefaultCurrency=840&SiteCurrency=840&ContType=&UserCulture=1033&dm=www.travelmeetingsawards-china.com&SiteLanguage=2052; s_sq=ntmntmmcchina%3D%2526pid%253D(5105)%252520%2525E8%2525AF%2525BB%2525E8%252580%252585%2525E6%25258A%252595%2525E7%2525A5%2525A8%252520-%2525202017%2525E4%2525B8%2525AD%2525E5%25259B%2525BD%2525E6%252597%252585%2525E6%2525B8%2525B8%2525E4%2525B8%25259A%2525E7%252595%25258C%2525E5%2525A5%252596%2525EF%2525BC%252588%2525E5%252595%252586%2525E5%25258A%2525A1%2525E7%2525B1%2525BB%2525EF%2525BC%252589%2525E8%2525AF%252584%2525E9%252580%252589%252520%25257C%2526pidt%253D1%2526oid%253DVote%252520%2525E6%25258A%252595%2525E7%2525A5%2525A8%2526oidt%253D3%2526ot%253DSUBMIT'
}
# data = {
# '__VIEWSTATE': '/wEPDwUKLTQ0MDg4MzI3MWRkhc6az5DCGMMce+MYab5BPdm3oOCc0QhMXjgPO+KlHJc=',
# '__VIEWSTATEGENERATOR': 'C57773B4',
# '__EVENTVALIDATION': '/wEdAApdhN7azgIf7udjNG5rBO36uJWyBmoVrn+KGuzxsc+IdAhrj7iGCUNTOfLFH3a+X2zXZyb9ZhM4Agf2PTEzU0NRt9vByiAtAO532pQGgxLMkPxQ4KIC5CcITHzHErIOKsL+X/4YFsqB/WKj97Ohz20ZIOo7mLBzjoLYCKAW/gNPwcKu4LFvmYccMsvGxcqsoFFypiSNmMf2UIdcHp3gKJUE1+/bEdftTH+meRV6Ro2Ps7Lou2EFvxJCcav33eyACAc=',
# 'ctl00$cphMain$ucVoting$rptVotingList$ctl02$rptTopThreeList$ctl02$btnVote': 'Vote 投票'
# }
data = {
'__VIEWSTATE': '/wEPDwUKLTQ0MDg4MzI3MWRkhc6az5DCGMMce+MYab5BPdm3oOCc0QhMXjgPO+KlHJc=',
'__VIEWSTATEGENERATOR': 'C57773B4',
'__EVENTVALIDATION': '/wEdAApdhN7azgIf7udjNG5rBO36uJWyBmoVrn+KGuzxsc+IdAhrj7iGCUNTOfLFH3a+X2zXZyb9ZhM4Agf2PTEzU0NRt9vByiAtAO532pQGgxLMkPxQ4KIC5CcITHzHErIOKsL+X/4YFsqB/WKj97Ohz20ZIOo7mLBzjoLYCKAW/gNPwcKu4LFvmYccMsvGxcqsoFFypiSNmMf2UIdcHp3gKJUE1+/bEdftTH+meRV6Ro2Ps7Lou2EFvxJCcav33eyACAc=',
'ctl00$cphMain$ucVoting$rptVotingList$ctl02$rptTopThreeList$ctl00$btnVote': 'Vote 投票'
}
session = requests.session()
session.proxies = proxies
session.headers.update(headers)
ip_page = requests.get('https://api.ipify.org?format=json', proxies=proxies)
out_ip = json.loads(ip_page.text)['ip']
page = session.get('http://www.travelmeetingsawards-china.com/Events/Awards2015Business/Readers-Voting/?cat=5')
page = session.post('http://www.travelmeetingsawards-china.com/Events/Awards2015Business/Readers-Voting/?cat=5',
data=data)
save_ip(out_ip, PROXY)
return out_ip
def tp_rest_city_page(self, city_url, city_id, part):
PROXY = get_proxy(source="Platform")
x = time.time()
proxies = {
'http': 'socks5://' + PROXY,
'https': 'socks5://' + PROXY
}
print "Now Proxy is " + PROXY
headers = {
'User-agent': GetUserAgent()
}
page = requests.get(city_url, proxies=proxies, headers=headers)
page.encoding = 'utf8'
if len(page.text) < 100:
update_proxy('Platform', PROXY, x, '23')
self.retry()
doc = PyQuery(page.text)
doc.make_links_absolute(city_url)
for item in doc('.restaurants.twoLines a').items():
tp_rest_list_page_num.delay(item.attr.href, city_id, part)
def get_long_comment(self, target_url, language, miaoji_id, special_str):
PROXY = get_proxy(source="Platform")
x = time.time()
proxies = {
'http': 'socks5://' + PROXY,
'https': 'socks5://' + PROXY
}
headers = {
'User-agent': GetUserAgent()
}
try:
page = requests.get(target_url, headers=headers, proxies=proxies, timeout=120)
page.encoding = 'utf8'
data = long_comment_parse(page.content, target_url, language, miaoji_id)
update_proxy('Platform', PROXY, x, '0')
print "Success with " + PROXY + ' CODE 0'
return insert_db((data,), 'tp_comment_' + special_str)
except Exception as exc:
update_proxy('Platform', PROXY, x, '23')
self.retry(exc=traceback.format_exc(exc))
def get_images_without_proxy(self, source, target_url, **kwargs):
headers = {
'User-agent': GetUserAgent()
}
try:
print 'Get Img Url', target_url
page = requests.get(target_url, headers=headers, timeout=240)
f = StringIO(page.content)
flag, h, w = is_complete_scale_ok(f)
if flag in [1, 2]:
print 'Img', target_url, 'Error in 1,2'
self.retry(countdown=2)
else:
update_task(kwargs['mongo_task_id'])
file_name = hashlib.md5(target_url).hexdigest()
save_image(source, file_name, page.content)
print source, file_name, 'success'
return flag, h, w
except Exception as exc:
print 'Exception', str(exc)
self.retry(exc=traceback.format_exc(exc), countdown=2)
def get_lost_rest_new(self, target_url, city_id, **kwargs):
PROXY = get_proxy(source="Platform")
x = time.time()
proxies = {
'http': 'socks5://' + PROXY,
'https': 'socks5://' + PROXY
}
headers = {
'User-agent': GetUserAgent()
}
try:
page = requests.get(target_url, headers=headers, proxies=proxies, timeout=15)
page.encoding = 'utf8'
result = rest_parser(page.content, target_url, city_id)
if result == 'Error':
self.retry()
else:
update_task(task_id=kwargs['mongo_task_id'])
update_proxy('Platform', PROXY, x, '23')
return result
except Exception as exc:
self.retry(exc=traceback.format_exc(exc))
def get_comment(self, target_url, language, miaoji_id, special_str, **kwargs):
if language == 'en':
data = {
'mode': 'filterReviews',
'filterLang': 'en'
}
elif language == 'zhCN':
data = {
'mode': 'filterReviews',
'filterLang': 'zh_CN'
}
else:
return "Error, no such language"
PROXY = get_proxy(source="Platform")
x = time.time()
proxies = {
'http': 'socks5://' + PROXY,
'https': 'socks5://' + PROXY
}
headers = {
'User-agent': GetUserAgent()
}
if data != '':
try:
page = requests.post(target_url, data, headers=headers, proxies=proxies, timeout=120)
page.encoding = 'utf8'
res = parse(page.text, target_url, language, miaoji_id, special_str)
if res == 0:
update_proxy('Platform', PROXY, x, '23')
self.retry(countdown=120)
else:
# update_task(kwargs['mongo_task_id'])
update_proxy('Platform', PROXY, x, '0')
print "Success with " + PROXY + ' CODE 0'
except Exception as exc:
update_proxy('Platform', PROXY, x, '23')
self.retry(exc=traceback.format_exc(exc), countdown=120)
def get_pid_total_page(self, target_url, city_id, part):
x = time.time()
PROXY = get_proxy(source="Platform")
proxies = {
'http': 'socks5://' + PROXY,
'https': 'socks5://' + PROXY
}
headers = {
'User-agent': GetUserAgent()
}
try:
html_page = requests.get(target_url, proxies=proxies, headers=headers)
html_page.encoding = u'utf8'
content = html_page.text
pid = re.findall(u'PID :\'(\d+)\'', content)[0]
total_attr = re.findall(u'景点\((\d+)\)', content)[0]
# return pid, (int(total_attr) // 15) + 1
print pid, total_attr
for page_num in range(1, (int(total_attr) // 15) + 2):
detail_page.delay(pid, page_num, city_id, part)
except Exception as exc:
update_proxy('Platform', PROXY, x, '23')
self.retry(exc=traceback.format_exc(exc))
def qyer_city_query_task(self, city_name, **kwargs):
x = time.time()
PROXY = get_proxy(source="Platform")
proxies = {'http': 'socks5://' + PROXY, 'https': 'socks5://' + PROXY}
headers = {
'User-agent': GetUserAgent(),
'Referer': "http://www.qyer.com/",
}
try:
conn = pymysql.connect(host='10.10.180.145',
user='******',
passwd='hourong',
db='SuggestName',
charset="utf8")
with conn as cursor:
print(city_name)
quote_string = quote(city_name.encode('utf8'))
page = requests.get(
'http://www.qyer.com/qcross/home/ajax?action=search&keyword={0}'
.format(quote_string),
proxies=proxies,
headers=headers)
page.encoding = 'utf8'
content = page.text.replace('while(1);', '')
for line in get_query_data(content=content,
query_string=city_name):
cursor.execute(
'insert into QyerSuggestCity (`QueryName`,`Name`,`BelongName`,`Url`) VALUES (%s,%s,%s,%s)',
line)
conn.close()
update_task(kwargs['task_id'])
print "Success with " + PROXY + ' CODE 0'
update_proxy('Platform', PROXY, x, '0')
except Exception as exc:
update_proxy('Platform', PROXY, x, '23')
self.retry(exc=traceback.format_exc(exc))
def get_daodao_image_url(self, source_url, mid, **kwargs):
PROXY = get_proxy(source="Platform")
x = time.time()
proxies = {
'http': 'socks5://' + PROXY,
'https': 'socks5://' + PROXY
}
print "Now Proxy is " + PROXY
headers = {
'User-agent': GetUserAgent()
}
try:
detail_id = re.findall('-d(\d+)', source_url)[0]
target_url = 'http://www.tripadvisor.cn/LocationPhotoAlbum?detail=' + detail_id
page = requests.get(target_url, proxies=proxies, headers=headers, timeout=240)
page.encoding = 'utf8'
if not page.text:
update_proxy('Platform', PROXY, x, '23')
self.retry()
else:
print "Success with " + PROXY + ' CODE 0'
root = PyQuery(page.text)
images_list = []
for div in root('.photos.inHeroList div').items():
images_list.append(div.attr['data-bigurl'])
img_list = '|'.join(images_list)
if img_list == '':
self.retry()
data = (mid, source_url, img_list)
print insert_daodao_image_list(data)
update_proxy('Platform', PROXY, x, '0')
update_task(kwargs['mongo_task_id'])
return data
except Exception as exc:
update_proxy('Platform', PROXY, x, '23')
self.retry(exc=traceback.format_exc(exc))
def booking_detail_crawl(url, task):
PROXY = get_proxy(source="Platform")
headers = {'User-agent': GetUserAgent()}
proxies = {'http': 'socks5://' + PROXY, 'https': 'socks5://' + PROXY}
page = requests.get(url, proxies=proxies, headers=headers)
page.encoding = 'utf8'
content = page.text
root = HTML.fromstring(content)
session = DBSession()
hotel_element_list = root.get_element_by_id('hotellist_inner').xpath('div')
for hotel in hotel_element_list:
try:
hotel_crawl = HotelCrawl()
hotel_crawl.source_id = hotel.xpath('@data-hotelid')[0]
hotel_crawl.source = 'booking'
hotel_url = hotel.find_class('hotel_name_link')[0].xpath(
'@href')[0]
hotel_crawl.hotel_url = 'http://www.booking.com' + hotel_url.split(
'?sid')[0]
hotel_crawl.city_id = task.city_id
hotel_crawl.flag = task.flag
session.merge(hotel_crawl)
except Exception, e:
print str(e)
else:
hotel.source_id = other_info['source_id']
hotel.city_id = other_info['city_id']
# others_info_dict = hotel.__dict__
# hotel.others_info = json.dumps(others_info_dict)
# #print hotel
return hotel
if __name__ == '__main__':
from util.UserAgent import GetUserAgent
from common.common import get_proxy
headers = {'User-agent': GetUserAgent(), "authority": "www.agoda.com"}
other_info = {'source_id': '1006311', 'city_id': '11164', 'hid': 100}
# url = 'http://10.10.180.145:8888/hotel_page_viewer?task_name=hotel_base_data_agoda&id=329cf4fa7c9196ce026aa1053c652c2f'
# url = 'http://10.10.180.145:8888/hotel_page_viewer?task_name=hotel_base_data_agoda&id=49536fe85753dfd12ea88d0700bda26d'
# url = 'https://www.agoda.com/zh-cn/wingate-by-wyndham-arlington_2/hotel/all/arlington-tx-us.html?checkin=2017-08-03&los=1&adults=1&rooms=1&cid=-1&searchrequestid=09d590d3-cc17-4046-89a1-112b6ed35266'
# url = 'https://www.agoda.com/zh-cn/hotel-las-bovedas/hotel/badajoz-es.html?checkin=2017-12-25&los=1&adults=2&rooms=1&cid=-1&searchrequestid=65bc1980-4fcf-4ed1-bdf0-438a11704f7a'
# url = 'https://www.agoda.com/zh-cn/estudio-casco-antiguo/hotel/all/badajoz-es.html?checkin=2017-12-25&los=1&adults=2&rooms=1&cid=-1&searchrequestid=65bc1980-4fcf-4ed1-bdf0-438a11704f7'
# url = 'https://www.agoda.com/zh-cn/ilunion-golf-badajoz-hotel/hotel/badajoz-es.html?checkin=2017-12-25&los=1&adults=2&rooms=1&cid=-1&searchrequestid=65bc1980-4fcf-4ed1-bdf0-438a11704f7a'
# url = 'https://www.agoda.com/zh-cn/hotel-lisboa/hotel/all/badajoz-es.html?checkin=2017-12-25&los=1&adults=2&rooms=1&cid=-1&searchrequestid=65bc1980-4fcf-4ed1-bdf0-438a11704f7a'
url = 'https://www.agoda.com/zh-cn/oarsman-s-bay-lodge/hotel/yasawa-islands-fj.html?checkin=2017-11-25&los=1&adults=2&rooms=1&cid=-1&searchrequestid=b5bd9776-41c6-4fdd-b361-4abcaf8c8703'
# url = 'https://www.agoda.com/zh-cn/hotel-huatian-chinagora/hotel/alfortville-fr.html?checkin=2017-12-20&los=1&adults=2&rooms=1&cid=-1&searchrequestid=f53c35ca-007e-4974-af8f-ebfa20c4dfee'
# url = 'https://www.agoda.com/zh-cn/puesta-del-sol-apartment/hotel/all/asilah-ma.html?checkin=2017-12-25&los=1&adults=2&rooms=1&cid=-1&searchrequestid=a00c61b5-db95-40f9-b5c3-a385219f7e7a'
# url = 'https://www.agoda.com/zh-cn/ana-o-tai/hotel/all/hanga-roa-cl.html?checkin=2017-12-15&los=1&adults=2&rooms=1&cid=-1&searchrequestid=1b174d8d-2aef-4fea-836d-fb7a5e70e234'
# url = 'https://www.agoda.com/zh-cn/cabanas-teo/hotel/all/isla-de-pascua-cl.html?checkin=2017-12-25&los=1&adults=2&rooms=1&cid=-1&searchrequestid=5460efbf-de01-4b89-99c8-11e1adc2f066'
url = 's23'
