def get_build_info(self, build_url_list): for i in build_url_list: try: build = Building(co_index) build_url = 'http://222.223.160.199:8088/website/buildquery/selectBuild.jsp?buildID=' + i[ 0] response = requests.get(build_url, headers=self.headers) html = response.text build.bu_id = i[0] build.co_build_structural = re.search('结构类型.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) build.bo_build_end_time = re.search('建成年份.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) build.bu_build_size = re.search('总建筑面积.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) build.bu_num = re.search('幢号.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) build.size = re.search('占地面积.*?<td>(.*?)<', html, re.S | re.M).group(1) build.bu_floor = re.search('房屋层数.*?<td>(.*?)<', html, re.S | re.M).group(1) build.bu_all_house = re.search('房屋套数.*?<td>(.*?)<', html, re.S | re.M).group(1) build.area = re.search('坐落区.*?<td>(.*?)<', html, re.S | re.M).group(1) build.insert_db() self.get_house_info(build.bu_id) except Exception as e: print('请求错误,url={}'.format(build_url), e)
def co_parse(self, url_list): for url in url_list: try: co_url = url.xpath("./@href")[0] new_url = "http://tmsf.qzfdcgl.com" + co_url co_res = requests.get(new_url, headers=self.headers) con = co_res.text co = Comm(co_index) co.co_id = re.search('property_(.*?)_info', co_url).group(1) co.co_name = re.search('楼盘名称:</span>(.*)', con).group(1) co.co_develops = re.search('项目公司:</span>(.*)', con).group(1) co.co_address = re.search('物业地址:</span>(.*?)</p', con, re.S | re.M).group(1) co.area = re.search('所属城区:</span>(.*)', con).group(1) co.insert_db() sid = re.search('property_(\d+)_', co_url).group(1) propertyid = re.search('(\d+)_info', co_url).group(1) bu_url = new_url.replace('info', 'price') res = requests.get(bu_url, headers=self.headers) bu_html = etree.HTML(res.text) bu_idlist = bu_html.xpath("//dd[@id='building_dd']/a") except: continue for bu_ in bu_idlist[1:]: id = bu_.xpath("./@id")[0] bu_id = re.search('.*?(\d+)', id).group(1) bu = Building(co_index) bu.bu_id = bu_id bu.co_id = co.co_id bu.bu_num = bu_.xpath("./text()")[0] bu.insert_db() self.house_parse(bu_id, co.co_id, sid, propertyid)
def build_info(self, co_id, temp_url_list): for temp_url in temp_url_list: try: build_url = "http://222.77.178.63:7002/" + temp_url res = requests.get(build_url, headers=self.headers) html = etree.HTML(res.content.decode('gbk')) build_info_list = html.xpath("//tr[@class='indextabletxt']") for build_info in build_info_list: bu = Building(co_index) ho_url = build_info.xpath("./td/a/@href")[0] bu.co_id = co_id bu.bu_id = re.search('Param=(.*)', ho_url).group(1) bu.bu_num = build_info.xpath("./td/a/text()")[0] bu.bu_all_house = build_info.xpath("./td[2]/text()")[0] try: bu.bu_all_size = build_info.xpath("./td[3]/text()")[0] except: bu.bu_all_size = None try: bu.bu_live_size = build_info.xpath("./td[5]/text()")[0] except: bu.bu_live_size = None bu.insert_db() except Exception as e: # log.error('楼栋信息错误{}'.format(e)) print('楼栋信息错误{}'.format(e)) continue self.house_info(ho_url, co_id, bu.bu_id)
def parse(self, res): html = etree.HTML(res.content.decode('gbk')) bu_list = html.xpath("//div[@class='listCon']") for i in bu_list: temp = i.xpath("./a[@class='listCon2']/@href")[0] name = i.xpath("./a[@class='listCon1']/@title")[0] url = "http://www.hyfc365.com" + temp try: bu_res = requests.get(url, headers=self.headers) content = bu_res.content.decode('gbk') bu = Building(co_index) bu.bu_num = name project_id = re.search('ID=(.*)', temp).group(1) bu.bu_pre_sale = re.search('预售证名称.*?NAME">(.*?)</span', content, re.S | re.M).group(1) bu.bu_pre_sale_date = re.search('申领时间.*?">(.*?)</span', content, re.S | re.M).group(1) bu.bo_develops = re.search('申领单位.*?">(.*?)</span', content, re.S | re.M).group(1) bu.bu_build_size = re.search('"SALE_HOUSE_AREA">(.*?)<', content, re.S | re.M).group(1) bu.bu_all_house = re.search('"SALE_HOUSE_COUNT">(.*?)<', content, re.S | re.M).group(1) detail_url = 'http://www.hyfc365.com/RealEstate/Project/BuildingList.aspx?ID=' + project_id detail_res = requests.get(detail_url) bu_id = re.search("BUILDING_ID=(.*?)'", detail_res.text).group(1) bu.bu_id = bu_id bu.insert_db() except Exception as e: log.error("{}楼栋页面解析失败{}".format(url, e)) continue self.house_parse(bu_id)
def get_comm_info(self, comm_url_list): for i in comm_url_list: comm_url = "http://www.kmhouse.org" + i try: co_id = re.search("PreId=(.*?)&", i).group(1) s = re.search('prename=(.*?)$', comm_url, re.S | re.M).group(1) s_decode_str = parse.quote(s, encoding='gbk') comm_url = comm_url.replace(s, s_decode_str) response = requests.get(comm_url, headers=self.headers) html = response.content.decode('gbk') comm_detail_url = re.findall('linkone" href="(.*?)"', html, re.S | re.M)[0] self.get_comm_detail(comm_detail_url) build_html = re.search('请选择幢号.*?</select>', html, re.S | re.M).group() bu_info_list = re.findall("<option.*?</option>", build_html, re.S | re.M) for info in bu_info_list: build = Building(co_index) build.bu_id = re.search("value='(.*?)'", info, re.S | re.M).group(1) build.bu_num = re.search("<option.*?>(.*?)<", info, re.S | re.M).group(1) build.co_id = co_id build.insert_db() self.get_build_info(build.bu_id, co_id) except Exception as e: print('小区错误,co_index={},url={}'.format(co_index, comm_url), e)
def bu_parse(self,bu_url,co_id,co_url): build_url = "http://61.143.241.154/" + bu_url global headers headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.119Safari/537.36', 'Referer': co_url } bu_res = requests.get(build_url,headers=headers) bu_con = bu_res.content.decode('gbk') bu_pre_sale = re.search('预售许可证编号.*?blank">(.*?)</a',bu_con,re.S|re.M).group(1) bu_pre_sale_date = re.search('预售证有效日期.*?">(.*?)</td',bu_con,re.S|re.M).group(1) bu_html = etree.HTML(bu_con) bu_list = bu_html.xpath("//table[@id='donglist']//tr") for bo in bu_list: bu = Building(co_index) bu.co_id = co_id bo_url = bo.xpath("./td/a/@href")[0] bu.bu_id = re.search('dbh=(.*?)&', bo_url).group(1) bu.bu_num = bo.xpath("./td[3]/text()")[0] bu.bu_floor = bo.xpath("./td[4]/text()")[0] bu.bu_pre_sale = bu_pre_sale bu.bu_pre_sale_date = bu_pre_sale_date bu.insert_db() self.house_parse(bo_url,co_id,bu.bu_id)
def get_build_info(self, build_info_list, co_id, comm_html, url): for i in build_info_list: try: building = Building(2) bu_name = i[1] # 楼栋名称 bu_num = bu_name.split('#')[0] # 楼号 bu_all_house = i[3] # 总套数 bu_build_size = i[5] # 面积 bu_price = i[9] # 价格 # 给对象增加属性 building.bu_name = bu_name building.bu_num = bu_num building.bu_all_house = bu_all_house building.bu_build_size = bu_build_size building.bu_price = bu_price building.co_id = co_id # 小区id build_html = re.search(r'楼盘表(.*?)个楼栋信息', comm_html).group(1) build_url = re.search(r'<ahref="(.*?)">查看信息<', build_html).group(1) build_id = re.search('buildingId=(.*?)$', build_url).group(1) building.bu_id = build_id # 楼栋id building.insert_db() self.get_build_detail(build_url, co_id) except Exception as e: print('楼栋错误,co_index={},url={}'.format(co_index, url), e)
def build_info(self, bu_list, co_id): for bu in bu_list: bu_url = bu.xpath("./td[4]/a/@href")[0] build_url = self.start_url + '/' + bu_url bu_res = requests.get(build_url, headers=self.headers) bu_res.encoding = 'gbk' con = bu_res.text bu_pre_sale = re.search('预售许可证编号.*?blank">(.*?)</a', con, re.S | re.M).group(1) bu_pre_sale_date = re.search('预售证有效日期.*?">(.*?)</td', con, re.S | re.M).group(1) bu_html = etree.HTML(con) donglist = bu_html.xpath("//table[@id='donglist']/tr") for dong in donglist: dong_url = dong.xpath("./td/a/@href")[0] bu = Building(co_index) bu.co_id = co_id bu.bu_id = re.search('ID={(.*?)}', dong_url).group(1) bu.bu_num = dong.xpath("./td[3]/text()")[0] bu.bu_floor = dong.xpath("./td[4]/text()")[0] bu.bu_pre_sale = bu_pre_sale bu.bu_pre_sale_date = bu_pre_sale_date bu.insert_db() self.house_info(co_id, bu.bu_id, dong_url)
def get_build_info(self, bu_address_list, bu_num_list, bu_floor_list, bu_url_list, co_id): for i in range(len(bu_url_list)): build = Building(co_index) build.bu_address = bu_address_list[i] build.bu_num = bu_num_list[i] build.bu_floor = bu_floor_list[i] build.co_id = co_id # response = self.request_proxy('http://183.63.60.194:8808/public/web/' + bu_url_list[i]) time.sleep(1) response = self.s.get('http://183.63.60.194:8808/public/web/' + bu_url_list[i], headers=self.headers) build.bu_id = re.search('ljzid=(.*?)$', bu_url_list[i]).group(1) build.insert_db() html = response.text house_html = re.search('var _table_html_.*?</script>', html, re.S | re.M).group() house_url_list = re.findall('房屋号:<a.*?href="(.*?)"', house_html, re.S | re.M) try: self.get_house_info(house_url_list, build.bu_id) except Exception as e: print( '房号错误,co_index={},url={}'.format( co_index, 'http://183.63.60.194:8808/public/web/' + bu_url_list[i]), e)
def get_build_info(self, build_url_list, comm): for i in build_url_list: try: build_url = 'http://58.51.240.121:8503/' + i response = requests.get(build_url, headers=self.headers) html = response.text comm.co_pre_sale = re.search( 'id="PresellInfo1_lblXkzh">(.*?)<', html, re.S | re.M).group(1) comm.co_pre_sale_date = re.search( 'id="PresellInfo1_lblFzrq">(.*?)<', html, re.S | re.M).group(1) comm.insert_db() build_info_list = re.findall('<tr bgcolor="#FFFFFF">.*?</tr>', html, re.S | re.M) for i in build_info_list: build = Building(co_index) build.co_id = comm.co_id build.bu_num = re.search('<td.*?>(.*?)<', i, re.S | re.M).group(1) build.bu_floor = re.search('<td.*?<td.*?>(.*?)<', i, re.S | re.M).group(1) build.bu_all_house = re.search('<td.*?<td.*?<td.*?>(.*?)<', i, re.S | re.M).group(1) build.bu_id = re.search('PresellId=(.*?)$', build_url).group(1) build.insert_db() house_url = re.search('a href="(.*?)"', i, re.S | re.M).group(1) self.get_house_info(house_url, comm.co_id, build.bu_id) except Exception as e: print('请求错误,co_index={},url={}'.format(co_index, build_url), e)
def get_build_info(self, build_logo_list, preid): for build_logo in build_logo_list: try: build_url = 'https://www.qdfd.com.cn/qdweb/realweb/fh/FhBuildingList.jsp?preid=' + build_logo response = requests.get(build_url, headers=self.headers) html = response.text bu_num_list = re.findall( 'javascript:showHouseStatus.*?>(.*?)</a', html, re.S | re.M) bu_all_house_list = re.findall( 'javascript:showHouseStatus.*?center.*?center.*?center.*?center.*?center.*?>(.*?)<', html, re.S | re.M) house_code_list = re.findall( "javascript:showHouseStatus\((.*?)\)'>", html, re.S | re.M) for i in range(len(bu_num_list)): try: build = Building(co_index) bu_code_list = re.findall('"(.*?)"', house_code_list[i]) build.bu_num = bu_num_list[i] build.bu_all_house = bu_all_house_list[i] build.co_id = preid build.bu_id = bu_code_list[0] build.insert_db() co_id = bu_code_list[2] house_id = bu_code_list[1] self.get_house_info(build.bu_id, co_id, house_id) except Exception as e: print(e) except Exception as e: print('青岛楼栋问题,url:={}'.format(build_url), e)
def get_build_info(self, build_id_list, co_id): bu = Building(co_index) for build_id in build_id_list: formdata = {} formdata["action"] = "qeurySingleBuilding" formdata['pk'] = str(build_id) header = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36', 'Referer': 'http://hkrealestate.haikou.gov.cn/wp_myself/housequery/projectBuildingList.php' } try: build_info = self.s.post( 'http://hkrealestate.haikou.gov.cn/wp_myself/housequery/projectBuildHouseAction.php', data=formdata, headers=header) except Exception as e: print("co_idnex={},楼栋错误".format(co_index), e) build_con = build_info.text bu.bu_id = build_id bu.co_id = co_id bu.bu_num = re.search('幢名称.*?<td>(.*?)<', build_con, re.S | re.M).group(1) bu.bu_floor = re.search('总层数.*?<td>(.*?)<', build_con, re.S | re.M).group(1) bu.bu_build_size = re.search('>建筑面积.*?<td>(.*?)<', build_con, re.S | re.M).group(1) bu.bo_develops = re.search('房地产企业.*?">(.*?)</td', build_con, re.S | re.M).group(1) bu.insert_db() self.get_house_info(build_con, co_id, build_id)
def build_info(self,build_detail,co_id): build_detail_url = 'http://as.gzfcxx.cn' + build_detail res = requests.get(build_detail_url,headers=self.headers) html = etree.HTML(res.text) build_info_list = html.xpath("//div[@class='box']//font/a/@href") for build_url in build_info_list: try: url = 'http://as.gzfcxx.cn'+build_url ho_res = requests.get(url,headers=self.headers) ho_html = etree.HTML(ho_res.text) bu = Building(co_index) bu.co_id = co_id bu.bu_id = re.search('dongID=(\d+)',build_url).group(1) bu.bu_num = ho_html.xpath("//option[@selected='selected']/text()")[0] bu.insert_db() temp = re.search("\?(.*?dongID=\d+)", build_url).group(1) real_url = 'http://as.gzfcxx.cn/Controls/HouseControls/FloorView.aspx?' + temp house_res = requests.get(real_url,headers=self.headers) ho_html = etree.HTML(house_res.text) info = ho_html.xpath("//table[@class='C1 T0 F0']/..") except Exception as e: log.error('楼栋信息错误',e) continue for i in info: try: ho = House(co_index) ho_info = i.xpath("./@title")[0] ho.ho_build_size = re.search('(\d+).(\d+)',ho_info,re.S|re.M).group(1) ho.ho_name = i.xpath(".//span/text()")[0] ho.bu_id = bu.bu_id ho.co_id = co_id ho.insert_db() except Exception as e: log.error('房间信息错误',e)
def get_build_info(self, url, co_id): try: building = Building(co_index) response = requests.get(url) html = response.text tree = etree.HTML(html) co_name = tree.xpath('//*[@id="PageB_Location"]/text()')[0] # 小区名字 print(co_name) bu_name = tree.xpath('//*[@id="ItemName"]/text()')[0] # 楼栋名称 bu_num = tree.xpath('//*[@id="PageB_HouseNo"]/text()')[0] # 楼号 栋号 bu_all_house = tree.xpath('//*[@id="lb_countbulidtaoshu"]/text()')[ 0] # 总套数 bu_floor = tree.xpath('//*[@id="cell3-1"]/text()') bu_floor = self.is_none(bu_floor) # 楼层 bu_build_size = tree.xpath('//*[@id="lb_countbulidarea"]/text()')[ 0] # 建筑面积 bu_live_size = tree.xpath('//*[@id="lb_buildarea"]/text()')[ 0] # 住宅面积 bu_price = tree.xpath('//*[@id="lb_buildavg"]/text()') bu_price = self.is_none(bu_price) # 住宅价格 bu_id = re.search('\?(\d+)$', url).group(1) # 楼栋id building.co_id = co_id building.bu_name = bu_name building.bu_num = bu_num building.bu_all_house = bu_all_house building.bu_floor = bu_floor building.bu_build_size = bu_build_size building.bu_live_size = bu_live_size building.bu_price = bu_price building.bu_id = bu_id building.insert_db() house_info_html = re.findall('<tr id="row3">(.*)$', html, re.S | re.M)[0] for i in re.findall('(<td.*?>.*?</td>)', house_info_html, re.S | re.M): if '<br>' not in i: continue ho_name_list = re.findall('<td.*?>(.*?)<br>', i, re.S | re.M) ho_true_size_list = re.findall('<td.*?>.*?<br>(.*?)<br>', i, re.S | re.M) ho_type = re.findall('<td.*?>.*?<br>.*?<br>(.*?)<br>', i, re.S | re.M)[0] for i in range(len(ho_name_list)): try: if 'font' in ho_name_list[i]: ho_name = re.sub('<font.*?>', '', ho_name_list[i]) else: ho_name = ho_name_list[i] house = House(8) house.ho_name = ho_name house.ho_true_size = ho_true_size_list[i] house.co_id = co_id house.bu_id = bu_id house.ho_type = ho_type house.insert_db() except Exception as e: print(e) except BaseException as e: print(e)
def detail_parse(self, id, build_list): for build in build_list: bu_temp = re.search('<a href="(.*?)"', build).group(1) build_url = self.start_url + bu_temp try: bu_res = requests.get(build_url, headers=self.headers) time.sleep(2) bu_text = bu_res.content.decode() bu = Building(co_index) bu.bu_num = re.search('幢号:(.*?) 许', bu_text).group(1) bu.bu_pre_sale = re.search('许可证号:<span>(.*?)</span>', bu_text).group(1) bu.bu_id = int(bu.bu_pre_sale) bu.bu_all_house = re.search('套数:<span>(.*?)</span', bu_text).group(1) bu.bu_floor = re.search('地上层数:<span>(.*?)</span', bu_text).group(1) bu.bo_build_end_time = re.search('竣工日期:<span>(.*?)</span', bu_text).group(1) bu.bu_build_size = re.search('预售许可面积:<span>(.*?)</span', bu_text).group(1) bu.bu_type = re.search('用途:<span>(.*?)</span', bu_text).group(1) bu.insert_db() except Exception as e: log.error("楼栋出错{}".format(e)) continue self.house_detail(bu_text, id, bu.bu_id)
def get_build_info(self, build_lis, co_id): for build_ in build_lis: build_url = "http://xx.yyfdcw.com" + build_ try: build_res = requests.get(build_url, headers=self.headers) except Exception as e: print("co_index={},楼栋信息错误".format(co_index), e) continue con = build_res.text bu = Building(co_index) bu.co_id = co_id bu.bu_id = re.search('Bid=(\d+)', build_).group(1) bu.bu_num = re.search('名称.*?">(.*?)</spa', con).group(1) bu.bu_pre_sale = re.search("编.*?red'>(.*?)</a", con).group(1) bu.bu_pre_sale_date = re.search('颁发日期.*?Date">(.*?)</span', con).group(1) bu.bo_build_start_time = re.search('开工日期.*?">(.*?)</span', con).group(1) bu.bo_build_end_time = re.search('竣工日期.*?">(.*?)</span', con).group(1) bu.bo_develops = re.search('单位.*?">(.*?)</span', con).group(1) bu.bu_floor = re.search('层数.*?">(.*?)</span', con).group(1) bu.bu_live_size = re.search('住宅面积.*?">(.*?)</span', con).group(1) bu.size = re.search('总面积.*?">(.*?)</span', con).group(1) bu.insert_db() id = re.search('测量号.*?">(.*?)</span', con).group(1) self.get_house_info(co_id, bu.bu_id, id)
def build_info(self, build_detail, co_id): proxy = Proxy_contact(app_name='wuhan', method='get', url=build_detail, headers=self.headers) # build_res = requests.get(build_detail,headers=self.headers) build_res = proxy.contact() html = etree.HTML(build_res.decode('gb18030')) info_list = html.xpath("//tr[@bgcolor='#FFFFFF']") for info in info_list: try: bu = Building(co_index) bu.co_id = co_id bu.bu_floor = info.xpath('./td[3]/text()')[0] bu.bu_all_house = info.xpath('./td[4]/text()')[0] bu.bu_num = info.xpath('./td//span/text()')[0] temp_url = info.xpath('./td/a/@href')[0] bu.bu_id = re.search('HouseDengjh=(.*?\d+)', temp_url).group(1) bu.insert_db() except Exception as e: log.error('楼栋错误{}'.format(e)) continue a = parse.quote(re.search('DengJh=(.*?\d+)&', temp_url).group(1), encoding='gbk') b = parse.quote(re.search('HouseDengjh=(.*?\d+)', temp_url).group(1), encoding='gbk') bu_url = 'http://scxx.fgj.wuhan.gov.cn/5.asp?DengJh=' + a + '&HouseDengjh=' + b self.house_info(bu.bu_id, bu_url, co_id) time.sleep(3)
def build_parse(self, co_id): list_url = 'http://www.ccfdw.gov.cn/ecdomain/lpcs/xmxx/loulist.jsp?Id_xmxq=' + co_id res = requests.get(list_url, headers=self.headers) con = res.content.decode() build_id_list = re.findall("searchByLid\('(\d+)'\)", con) for build_id in build_id_list: try: bu_url = 'http://www.ccfdw.gov.cn/ecdomain/lpcs/xmxx/lpbxx_new.jsp?lid=' + build_id bu_res = requests.get(bu_url, headers=self.headers) bu_con = bu_res.content.decode('gbk') bu = Building(co_index) bu.co_id = co_id bu.bu_id = build_id bu.bu_num = re.search('楼栋名称.*?">(.*?)</td', bu_con, re.S | re.M).group(1) bu.bu_all_house = re.search('总套数.*?">总(.*?)套</td', bu_con, re.S | re.M).group(1) bu.bu_floor = re.search('地上层数.*?">共(.*?)层</td', bu_con, re.S | re.M).group(1) bu.bu_build_size = re.search('总建筑面积.*?">(.*?)</td', bu_con, re.S | re.M).group(1) bu.bu_pre_sale = re.search("searchysxk\('(.*?)'\)", bu_con, re.S | re.M).group(1) bu.bu_type = re.search('房屋用途.*?">(.*?)</td', bu_con, re.S | re.M).group(1) bu.insert_db() except Exception as e: log.error('{}楼栋错误{}'.format(build_id, e)) self.house_parse(co_id, build_id, bu_con)
def get_build_info(self, co_id): build_url = "http://202.103.219.149:7000/ajax/LeadingMIS.CommonModel.CommonQuery.WebUI.AjaxManage.QueryDataParser,LeadingMIS.CommonModel.CommonQuery.WebUI.ashx" querystring = {"_method": "GetDataToDynamicInXml", "_session": "rw"} payload = "xmlInfo=%263Croot%2620QueryCode%263D%2622BuildingsInfo%2622%2620PageIndex%263D%26221%2622%2620PageSize%263D%262215%2622%2620SortField%263D%2622%2620ORDER%2620BY%2620Name%2622%2620QueryString%263D%2622QueryCode%263DBuildingsInfo%2626amp%263BProjectID%263D" + co_id + "%2622%2620BeginDate%263D%2622%262000%263A00%263A00%2622%2620EndDate%263D%2622%262023%263A59%263A59%2622%2620Flag%263D%2622TitleBody%2622%2620TitlesWidthInfo%263D%2622BuildNo%267C0%2624Name%267C0%2624FloorCount%267C0%2624RoomCount%267C0%2624YCJZArea%267C0%2624Structure%267C0%2624YSXKCer%267C0%2624ZJJG%267C0%2622%2620IsUseOCache%263D%26220%2622%2620IsUserID%263D%26220%2622%2620SiteId%263D%26228907bd13-1d14-4f9e-8c01-e482d9590d10%2622%2620LockedColumn%263D%26220%2622%2620IsLocked%263D%26220%2622%2620ClientWidth%263D%26221601%2622%2620ShowModeCode%263D%2622default%2622%2620Language%263D%2622chinese%2622/%263E" try: response = requests.request("POST", build_url, data=payload, params=querystring) html = response.text build_info_list = re.findall('<tr.*?>.*?</tr>', html, re.S | re.M)[1:] for i in build_info_list: build = Building(co_index) build.co_id = co_id build.bu_num = re.search( '<span class="spanctfield".*?<span class="spanctfield".*?>.*?<a.*?>(.*?)<', i, re.S | re.M).group(1) build.bu_floor = re.search( '<span class="spanctfield".*?<span class="spanctfield".*?<span class="spanctfield".*?>(.*?)<', i, re.S | re.M).group(1) build.bu_pre_sale = re.search( '<span class="spanctfield".*?<span class="spanctfield".*?<span class="spanctfield".*?<span class="spanctfield".*?<span class="spanctfield".*?<span class="spanctfield".*?<span class="spanctfield".*?>(.*?)<', i, re.S | re.M).group(1) build.bu_id = re.search('id="Tr_(.*?)"', i, re.S | re.M).group(1) build.insert_db() self.get_house_info(co_id, build.bu_id) except Exception as e: print('请求错误,url={},data={},params={}'.format( build_url, payload, querystring))
def get_build_info(self, build_url_list): for i in build_url_list: try: build = Building(co_index) build_code = re.search('xqbm=(.*?)$', i).group(1) build_url = 'http://zjjg.0557fdc.com:9555/xiaoqu/donginfo.aspx?xqbm=' + build_code build.bu_num = 'Labeldongmc">(.*?)<' build.bu_pre_sale = 'Labelyszheng">(.*?)<' build.bu_floor = 'Labelsceng">(.*?)<' build.bu_address = 'Label1zuoluo">(.*?)<' build.bo_build_start_time = 'Label1kaigong">(.*?)<' build.co_build_structural = 'Labeljiegou">(.*?)<' build.co_id = 'donginfo.aspx\?xqbm=(.*?)"' build.bu_id = 'id="DropDownList1".*?value="(.*?)"' p = ProducerListUrl(page_url=build_url, request_type='get', encode='utf-8', analyzer_rules_dict=build.to_dict(), current_url_rule='location\.href=(.*?)"', analyzer_type='regex', headers=self.headers) house_url_list = p.get_details() self.get_house_info(house_url_list) except Exception as e: print('楼栋错误,co_index={},url={}'.format(co_index, build_url), e)
def bu_info(self, bu_list, co_id): for bu in bu_list: try: bu_url = 'http://www.fxfdcw.com/' + bu res = requests.get(bu_url, headers=self.headers) con = res.content.decode('gbk') html = etree.HTML(con) build = Building(co_index) build.co_id = co_id build.bu_id = re.search('bdid=(\d+)', bu).group(1) build.bu_num = re.search('楼号.*?">(.*?)</', con, re.S | re.M).group(1) build.bu_address = re.search('坐落.*?">(.*?)</', con, re.S | re.M).group(1) build.bu_floor = re.search('地上层数.*?">(.*?)</', con, re.S | re.M).group(1) build.bu_build_size = re.search('建筑面积.*?wrap">(.*?)</', con, re.S | re.M).group(1) build.bu_all_house = re.search('套 数.*?">(.*?)</', con, re.S | re.M).group(1) build.bu_type = re.search('用 途.*?wrap">(.*?)</', con, re.S | re.M).group(1) build.insert_db() ho_list = html.xpath("//span[@title]") except Exception as e: # log.error("楼栋信息错误{}".format(e)) print("楼栋信息错误{}".format(e)) continue self.ho_info(ho_list, co_id, build.bu_id)
def comm_info( self, con, ): # 小区及楼栋 comm = Comm(co_index) comm.co_name = con.xpath( "//span[@id='ctl00_ContentPlaceHolder2_web_item_retail1_lb_item_name']/text()" )[0] # 小区名称 co_id_str = con.xpath("//form[@id='aspnetForm']/@action")[0] # 小区id comm.co_id = re.search(r"\d+", co_id_str).group(0) comm.co_address = con.xpath( "//span[@id='ctl00_ContentPlaceHolder2_lb_item_seat']/text()")[ 0] # 小区地址 comm.co_develops = con.xpath( "//span[@id='ctl00_ContentPlaceHolder2_lb_enter_name']/text()")[ 0] # 开发商 comm.co_size = con.xpath( "//span[@id='ctl00_ContentPlaceHolder2_lb_area']/text()")[0] # 总面积 comm.co_build_size = con.xpath( "//span[@id='ctl00_ContentPlaceHolder2_lb_item_area']/text()")[ 0] # 建筑面积 comm.co_build_end_time = con.xpath( "//span[@id='ctl00_ContentPlaceHolder2_lb_item_ew_date']/text()")[ 0] # 竣工时间 comm.co_plan_pro = con.xpath( "//span[@id='ctl00_ContentPlaceHolder2_lb_program_pcode']/text()")[ 0] # 用地规划许可 comm.co_work_pro = con.xpath( "//span[@id='ctl00_ContentPlaceHolder2_lb_jg']/text()")[0] # 施工许可 comm.co_green = con.xpath( "//span[@id='ctl00_ContentPlaceHolder2_lb_item_green_rate']/text()" )[0] # 绿地百分比 comm.co_land_use = con.xpath( "//span[@id='ctl00_ContentPlaceHolder2_lb_td']/text()")[0] # 土地使用证 comm.insert_db() build = Building(co_index) build_table = con.xpath("//tr[@style='color:#000066;']") room_list = [] for build_list in build_table: build.co_id = comm.co_id build.co_name = comm.co_name build_info = build_list.xpath("./td/text()") build.bu_id = build_info[0] build.bu_num = build_info[1] build.bu_all_house = build_info[2] build.size = build_info[3] build.bu_floor = build_info[4] build.bu_pre_sale = build_info[5] build.insert_db() room_url = build_list.xpath("./td/a/@href")[0] room_list.append(room_url) return room_list
def get_comm_info(self, comm_id_list): for i in comm_id_list: try: comm = Comm(co_index) comm_url = 'http://web.xxfdc.gov.cn/onlineQuery/projectInformation.do?xmId=' + i response = requests.get(comm_url, headers=self.headers) html = response.text comm.co_name = re.search('项目名称:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_address = re.search('项目地址:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_develops = re.search('开发商:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_all_house = re.search('已售总套数:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_build_size = re.search('已售总面积:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.area = re.search('行政区别:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_volumetric = re.search('容积率:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_id = i comm.insert_db() bu_html = re.search( '<table class="table table-bordered itemInfoDetail.*?</table>', html, re.S | re.M).group() build_info_list = re.findall('<tr>.*?</tr>', bu_html, re.S | re.M)[1:] for i in build_info_list: try: build = Building(co_index) build.bu_num = re.search('<td>(.*?)<', i, re.S | re.M).group(1) build.bu_all_house = re.search( '<td>.*?<td>.*?<td>(.*?)<', i, re.S | re.M).group(1) build.bu_id = re.search('buildId=(.*?)&', i, re.S | re.M).group(1) build.co_id = comm.co_id build.insert_db() house_url = re.search('<a href="(.*?)"', bu_html, re.S | re.M).group(1) response = requests.get(house_url, headers=self.headers) html = response.text house_url_list = re.findall( '<td width="110">.*?<a.*?href="(.*?)"', html, re.S | re.M) self.get_house_info(house_url_list, build.bu_id, comm.co_id) except Exception as e: print( '楼栋错误,co_index={},url={}'.format( co_index, house_url), e) except Exception as e: print('小区错误,co_index={},url={}'.format(co_index, comm_url), e)
def get_build_info(self, build_info_list, bu_num_list, co_id, comm_url): for i in range(len(bu_num_list)): try: build = Building(co_index) build.co_id = co_id build.info = build_info_list[i] build.bu_num = bu_num_list[i] build.insert_db() except Exception as e: print('楼栋错误,co_index={},url={}'.format(co_index, comm_url), e)
def get_build_info(self, build_url_list, co_id): bu_code_list = build_url_list[0].split(';;') for i in bu_code_list: build = Building(co_index) build.co_id = co_id code = i.split(',,') build.bu_id = code[0] build.bu_num = code[1] build.insert_db() self.get_house_info(build.bu_id)
def get_comm_info(self, comm_info_list): for i in comm_info_list: build = Building(co_index) house_url = re.search('href="(.*?)"', i, re.S | re.M).group(1) build.bu_num = re.search('<a.*?>(.*?)<', i, re.S | re.M).group(1) build.bu_address = re.search('<td.*?<td.*?>(.*?)<', i, re.S | re.M).group(1) build.bu_pre_sale = re.search('<td.*?<td.*?<td.*?>(.*?)<', i, re.S | re.M).group(1) build.bu_id = re.search('slbh=(.*?)&', i, re.S | re.M).group(1) build.insert_db() self.get_house_info(house_url, build.bu_id)
def analyzer_comm_url(self, comm_url_list): all_url = [] for i in comm_url_list: try: res = requests.get(i) html = res.content.decode('gbk') c = Comm(self.co_index) c.co_name = re.search('项目名称:.*?">.*?<span.*?>(.*?)</span>', html, re.S | re.M).group(1) # 项目名称 c.co_address = re.search('项目地址:.*?">.*?<span.*?>(.*?)</span>', html, re.S | re.M).group(1) # 项目地址 c.co_develops = re.search('开发商:.*?">.*?<span.*?>(.*?)</span>', html, re.S | re.M).group(1) # 开发商 c.co_build_size = re.search( '总建筑面积:.*?">.*?<span.*?>(.*?)</span>', html, re.S | re.M).group(1) # 建筑面积 c.co_land_type = re.search( '用地依据:.*?">.*?<span.*?>(.*?)</span>', html, re.S | re.M).group(1) # 土地使用证 c.co_all_house = re.search( '>总套数:.*?">.*?<span.*?>(.*?)</span>', html, re.S | re.M).group(1) # 总套数 c.area = re.search('所在区域:.*?">.*?<span.*?>(.*?)</span>', html, re.S | re.M).group(1) # 地区 area c.co_work_pro = re.search( '施工许可证:.*?">.*?<span.*?>(.*?)</span>', html, re.S | re.M).group(1) # 施工许可证 c.co_plan_pro = re.search( '建设工程规划许可证:.*?">.*?<span.*?>(.*?)</span>', html, re.S | re.M).group(1) # 规划许可证 c.insert_db() buildlist = re.findall('onmouseover.*?</TR>', html, re.S | re.M) url_list = [] for k in buildlist: try: b = Building(self.co_index) build_list = re.findall('<TD.*?>(.*?)</TD>', k, re.S | re.M) b.co_name = build_list[1] b.bu_num = build_list[2] b.bu_type = build_list[4] b.insert_db() house_url = re.findall('href="(.*?)"', k, re.S | re.M) for j in house_url: url_list.append( 'http://www.stfcj.gov.cn/stsite/ProjectList/' + j) except Exception as e: print('楼栋错误,co_index={},url={}'.format(co_index, i), e) all_url = all_url + url_list except Exception as e: print('小区错误,co_index={},url={}'.format(co_index, i), e) return all_url
def bu_info(self, bu_list, co_id): for bu_ in bu_list[1:]: bu = Building(co_index) bu.co_id = co_id bu.bu_num = bu_.xpath("./td/a/text()")[0] bu.bu_pre_sale = bu_.xpath("./td[2]/text()")[0] bu.bu_type = bu_.xpath("./td[4]/text()")[0] bu_url = bu_.xpath("./td/a/@href")[0] bu.bu_id = re.search('buildid=(\d+)', bu_url).group(1) bu.insert_db() self.ho_info(bu_url, co_id, bu.bu_id)
def get_build_info(self, comm_url_list): for i in comm_url_list: try: sid = re.findall('\+(\d+)\+', i)[0] pid = re.findall('\+(\d+)\+', i)[1] build_url = 'http://www.jjzzfdc.com.cn/WebClient/ClientService/bldg_query.aspx?pid=' + pid + '&sid=' + sid # print(build_url) response = requests.get(build_url) html = response.text build = Building(co_index) build.bu_id = pid build.bu_num = re.search('楼栋座落.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) build.bu_address = re.search('楼栋座落.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) build.bu_pre_sale = re.search('预售证号.*?">(.*?) ', html, re.S | re.M).group(1) build.bu_pre_sale_date = re.search('时间.*?">(.*?) ', html, re.S | re.M).group(1) build.bu_all_house = re.search('dM.*?">(.*?) ', html, re.S | re.M).group(1) # build.bu_address = re.search('售楼处地址.*?">(.*?) ', html, re.S | re.M).group(1) build.insert_db() except Exception as e: print('co_index={}, 楼栋错误,url={}'.format(co_index, build_url), e) house_url = 'http://www.jjzzfdc.com.cn/WebClient/ClientService/proxp.aspx?key=WWW_LPB_001¶ms=' + sid # print(house_url) result = requests.get(house_url) html_ = result.text for house_info in re.findall('<Result.*?</Result>', html_, re.S | re.M): try: house = House(co_index) house.bu_id = build.bu_id house.bu_num = build.bu_num house.ho_name = re.search('<ONAME>(.*?)</ONAME>', house_info, re.S | re.M).group(1) house.ho_num = re.search('<OSEQ>(.*?)</OSEQ>', house_info, re.S | re.M).group(1) house.ho_build_size = re.search('<BAREA>(.*?)</BAREA>', house_info, re.S | re.M).group(1) house.ho_floor = re.search('<FORC>(.*?)</FORC>', house_info, re.S | re.M).group(1) house.ho_true_size = re.search('<PAREA>(.*?)</PAREA>', house_info, re.S | re.M).group(1) house.insert_db() except Exception as e: print('co_index={}, 房号错误'.format(co_index), e)
def get_build_info(self, build_url_list, co_name): for i in build_url_list: try: build = Building(co_index) code = i.split(',,') build.bu_num = code[1] build.co_name = co_name build.insert_db() self.get_house_info(code, co_name) except Exception as e: print(e)