def comm_info(self, comm_url_list): # 小区信息 co = Comm(co_index) build_url_list = [] for comm_url in comm_url_list: co.co_id = re.search('id=(\d+)', comm_url).group(1) detail_url = "http://ris.szpl.gov.cn/bol/" + comm_url.lstrip(".") url = "http://ris.szpl.gov.cn/bolprojectdetail.aspx?id=" + str(co.co_id) try: res = requests.get(detail_url, headers=self.headers) con = res.text co.co_pre_sale = re.search('许可证号.*?">(.*?)&', con).group(1) co.co_name = re.search('项目名称.*?">(.*?)&', con).group(1) co.co_address = re.search('所在位置.*?">(.*?)&', con).group(1) co.co_develops = re.search('发展商.*?">(.*?)&', con).group(1) co_type = re.search('住宅.*?面积.*?">(.*?)平方米.*?套数.*?">(.*?)&', con) co.co_build_size = co_type.group(1) co.co_all_house = co_type.group(2) co.insert_db() response = requests.get(url, headers=self.headers) content = etree.HTML(response.text) build_url = content.xpath("//td/a/@href") build_url_list.extend(build_url) except: continue self.build_info(build_url_list)
def get_comm_info(self, comm_url): comm = Comm(co_index) comm_url = comm_url.replace('buildingdetail', 'buildinfo') response = self.request_proxy(comm_url, headers=self.headers) html = response.content.decode('gbk') comm.co_name = re.search('class="sf_xq_xmmc">(.*?)<', html, re.S | re.M).group(1).strip() comm.area = re.search('id="Label_CityArea">(.*?)<', html, re.S | re.M).group(1).strip() comm.co_pre_sale_date = re.search('class="sf_xq_jfsj">(.*?)<', html, re.S | re.M).group(1).strip() comm.co_build_type = re.search('id="lbl_JZJG".*?>(.*?)<', html, re.S | re.M).group(1).strip() comm.co_address = re.search('id="Label_ProjectAdress">(.*?)<', html, re.S | re.M).group(1).strip() comm.co_pre_sale = re.search('id="Label_SallPreDocuments">(.*?)<', html, re.S | re.M).group(1).strip() comm.co_all_house = re.search('id="lbl_ZTS".*?>(.*?)<', html, re.S | re.M).group(1).strip() comm.co_build_size = re.search('id="lbl_JZMJ".*?>(.*?)<', html, re.S | re.M).group(1).strip() comm.co_all_size = re.search('id="lbl_ZDMJ".*?>(.*?)<', html, re.S | re.M).group(1).strip() comm.co_develops = re.search('id="Label_DevName">.*?>(.*?)<', html, re.S | re.M).group(1).strip() comm.co_id = re.search('action=.*?buildingid=(.*?)"', html, re.S | re.M).group(1).strip() comm.insert_db() buildingid = re.search('buildingid=(.*?)$', comm_url, re.S | re.M).group(1) self.get_build_info(buildingid, comm.co_id)
def get_comm_info(self, comm_url_list): for i in comm_url_list: try: comm = Comm(co_index) comm_url = 'http://221.2.144.162:8090/' + i response = requests.get(comm_url, headers=self.headers) html = response.content.decode('gbk') comm.co_id = re.search('id=(\d+)', i).group(1) comm.co_name = re.findall('项目名称:.*?<td.*?>(.*?)<', html, re.S | re.M)[0] comm.co_develops = re.findall('开 发 商:.*?<td.*?>(.*?)<', html, re.S | re.M)[0] comm.area = re.findall( '城 区:.*?<td.*?>(.*?)<', html, re.S | re.M)[0] comm.co_type = re.findall('物业类型:.*?<td.*?>(.*?)<', html, re.S | re.M)[0] comm.co_address = re.findall('物业位置:.*?<td.*?>(.*?)<', html, re.S | re.M)[0] comm.co_build_size = re.findall('建筑面积:.*?<td.*?>(.*?)<', html, re.S | re.M)[0] comm.insert_db() build_url_list = re.findall("height=20.*?<a href=(.*?) ", html, re.S | re.M) bu_pre_sale_list = re.findall("height=20.*?<Td>(.*?)<", html, re.S | re.M) self.get_build_info(build_url_list, bu_pre_sale_list, comm.co_name, comm.co_id) except Exception as e: print("co_index={},小区信息错误".format(co_index), e)
def get_comm_info(self, all_comm_url): for i in all_comm_url: try: comm = Comm(co_index) comm_url = 'http://gold.ncfdc.com.cn/' + i res = requests.get(comm_url, headers=self.headers) comm.co_name = re.search('ctl15_proname">(.*?)<', res.text, re.S | re.M).group(1) comm.co_address = re.search('ctl20_ADDRESS">(.*?)<', res.text, re.S | re.M).group(1) comm.co_develops = re.search('ctl20_developer_name">(.*?)<', res.text, re.S | re.M).group(1) comm.co_build_size = re.search('ctl20_build_area">(.*?)<', res.text, re.S | re.M).group(1) comm.area = re.search('ctl20_region_name">(.*?)<', res.text, re.S | re.M).group(1) comm.co_type = re.search('ctl20_PropertyType">(.*?)<', res.text, re.S | re.M).group(1) comm.co_green = re.search('ctl20_VIRESCENCE">(.*?)<', res.text, re.S | re.M).group(1) comm.co_volumetric = re.search('ctl20_PLAT_RATIO">(.*?)<', res.text, re.S | re.M).group(1) comm.co_id = re.search('name="form1.*?hrefID=(.*?)"', res.text, re.S | re.M).group(1) comm.insert_db() build_url_list = [] for j in re.findall('doc_nav_LD" href="(.*?)"', res.text, re.S | re.M): build_url_list.append(j) self.get_build_info(build_url_list, comm.co_id) except Exception as e: print('小区错误,co_index={}, url={}'.format(co_index, comm_url), e)
def get_comm_detail(self, comm_url): comm = Comm(co_index) co_url = 'http://tz.tmsf.com' + comm_url response = requests.get(co_url, headers=self.headers) html = response.content.decode('utf-8') comm.co_name = re.search('<span class="buidname colordg">(.*?)<', html, re.S | re.M).group(1) comm.co_address = re.search('楼盘地址:.*?<span.*?>(.*?)<', html, re.S | re.M).group(1) if '[' in comm.co_address: comm.area = re.search('\[(.*?)\]', comm.co_address, re.S | re.M).group(1) comm.co_type = re.search('物业类型:.*?<span title="(.*?)"', html, re.S | re.M).group(1) comm.co_open_time = re.search('最新开盘:</strong>(.*?)<', html, re.S | re.M).group(1) comm.co_develops = re.search('项目公司:</strong>(.*?)<', html, re.S | re.M).group(1) comm.co_build_type = re.search('建筑形式:</strong>(.*?)<', html, re.S | re.M).group(1) comm.co_id = re.search('id="propertyid".*?value="(.*?)"', html, re.S | re.M).group(1) comm.insert_db() sid = re.search('id="sid" name="sid" value="(.*?)"', html, re.S | re.M).group(1) build_url = re.search('id="index_bar">楼盘主页.*?href="(.*?)"', html, re.S | re.M).group(1) self.get_build_info(build_url, comm.co_id, sid)
def comm_parse(self, url_list, region): for co_url in url_list: comm_url = "http://110.89.45.7:8082" + co_url comm_res = requests.get(comm_url, headers=self.headers) con = comm_res.text co = Comm(co_index) co.co_id = re.search('ProjectId=(.*)', co_url).group(1) co.co_name = re.search('项目名称.*?">(.*?)</td', con, re.S | re.M).group(1) co.co_develops = re.search('公司名称.*?">(.*?)</td', con, re.S | re.M).group(1) co.co_address = re.search('项目坐落.*?">(.*?)</td', con, re.S | re.M).group(1) co.co_use = re.search('规划用途.*?">(.*?)</td', con, re.S | re.M).group(1) co.co_build_size = re.search('建筑面积.*?">(.*?)</td', con, re.S | re.M).group(1) co.area = region co.co_residential_size = re.search( '批准销售.*?">.*?</td.*?">(.*?)</td', con, re.S | re.M).group(1) co.co_pre_sale = re.search('预售许可证.*?">(.*?)</td', con, re.S | re.M).group(1) co.insert_db() co_html = etree.HTML(comm_res.text) bu_urllist = co_html.xpath("//span/a/@href") self.bu_parse(co.co_id, bu_urllist)
def get_comm_info(self, comm_url_list): for i in comm_url_list: try: comm = Comm(co_index) comm_url = 'https://www.qdfd.com.cn/qdweb/realweb/fh/FhProjectInfo.jsp' data = {'projectID': i} response = requests.post(url=comm_url, data=data, headers=self.headers) html = response.text comm.co_id = i comm.co_name = re.findall('bszn_title">(.*?)<', html, re.S | re.M)[0].strip() comm.area = re.findall('所在区县:.*?<span>(.*?)<', html, re.S | re.M)[0].strip() comm.co_address = re.findall('项目地址:.*?<span>(.*?)<', html, re.S | re.M)[0].strip() comm.co_develops = re.findall('企业名称:.*?<a.*?>(.*?)<', html, re.S | re.M)[0].strip() comm.co_all_house = re.findall( '<td>总套数.*?<td class="xxxx_list3">(.*?)<', html, re.S | re.M)[0].strip() comm.co_build_size = re.findall( '<td>总面积.*?<td class="xxxx_list3">(.*?)<', html, re.S | re.M)[0].strip() comm.insert_db() build_logo_list = re.findall( 'javascript:getBuilingList\("(.*?)"', html, re.S | re.M) self.get_build_info(build_logo_list, i) except Exception as e: print('青岛小区问题,url post data is:={}'.format(data), e)
def comm_info(self, comm_url_list): for comm_url in comm_url_list: try: co_url = 'http://222.77.178.63:7002/' + comm_url co_res = requests.get(co_url, headers=self.headers) con = co_res.content.decode('gbk') co = Comm(co_index) co.co_id = re.search('projectID=(.*)', comm_url).group(1) co.co_name = re.search('项目名称:.*?">(.*?)</', con, re.S | re.M).group(1) co.area = re.search('所在区县:.*?">(.*?)</', con, re.S | re.M).group(1) co.co_address = re.search('项目地址:.*?">(.*?)</', con, re.S | re.M).group(1) co.co_develops = re.search('企业名称:.*?blank">(.*?)</', con, re.S | re.M).group(1) co.co_all_house = re.search('>总套数.*?">(\d+)<', con, re.S | re.M).group(1) co.co_all_size = re.search('>总面积.*?">(.*?)<', con, re.S | re.M).group(1) project_name = parse.quote(co.co_name) co.insert_db() except Exception as e: # log.error('小区信息错误{}'.format(e)) print('小区信息错误{}'.format(e)) sale_url = "http://222.77.178.63:7002/Presell.asp?projectID=" + co.co_id + "&projectname=" + project_name res = requests.get(sale_url, headers=self.headers) html = etree.HTML(res.content.decode('gbk')) temp_url_list = html.xpath("//a/@href") self.build_info(co.co_id, temp_url_list)
def get_comm_info(self, comm_url_list): for i in comm_url_list: try: comm = Comm(co_index) comm_url = 'http://www.gzbjfc.com/' + i comm.co_name = 'cph_hif1_xmmc.*?<.*?>(.*?)<' comm.co_pre_sale = 'cph_hif1_xsxkz.*?<.*?>(.*?)<' comm.co_address = 'cph_hif1_zl.*?<.*?>(.*?)<' comm.co_develops = 'cph_hif1_kfs.*?<.*?>(.*?)<' comm.co_handed_time = 'cph_hif1_jfsj.*?<.*?>(.*?)<' comm.co_build_size = 'cph_hif1_jzmj.*?>(.*?)<' comm.co_all_house = 'cph_hif1_fwts.*?>(.*?)<' comm.co_id = 'hdl1_hfYszh" value="(.*?)"' p = ProducerListUrl(page_url=comm_url, request_type='get', encode='utf-8', analyzer_rules_dict=comm.to_dict(), analyzer_type='regex', headers=self.headers) p.get_details() # 楼栋信息 build_url = comm_url.replace('Info', 'Building') self.get_build_info(build_url) except Exception as e: print('小区错误,co_index={},url={}'.format(co_index, comm_url), e)
def start_crawler(self): res = requests.get(self.start_url,headers=self.headers) content = res.content.decode() count = re.search('共(\d+)条记录',content).group(1) page = math.ceil(int(count)/15) for i in range(1,int(page)+1): url = "http://218.28.223.13/zzzfdc/zhengzhou/permission.jsp?pn=&cn=&it=&pager.offset=15&page="+str(i) page_res = requests.get(url,headers=self.headers) html = etree.HTML(page_res.content.decode()) project_list = html.xpath("//table//td/a/@href") for project in project_list: try: project_url = 'http://218.28.223.13'+project co_res = requests.get(project_url,headers=self.headers) con = co_res.content.decode() co_html = etree.HTML(con) co = Comm(co_index) co.co_id = re.search('number=(.*)',project).group(1) co.co_name = re.search('LpName=(.*?)"',con,re.S|re.M).group(1) co.co_pre_sale = re.search('预售许可证号.*?">(.*?)</td',con,re.S|re.M).group(1) co.co_pre_sale_date = re.search('发证日期.*?">(.*?)</td',con,re.S|re.M).group(1) co.co_develops = re.search('开发建设单位.*?">(.*?)</td',con,re.S|re.M).group(1) co.co_address = re.search('项 目 坐 落.*?">(.*?)</td',con,re.S|re.M).group(1) co.co_build_start_time = re.search('竣工时间.*?">(.*?)-----',con,re.S|re.M).group(1) co.co_build_end_time = re.search('-----(.*?)</td',con,re.S|re.M).group(1) co.co_build_size = co_html.xpath("//tr[9]/td[1]/text()")[0] co.co_plan_pro = co_html.xpath("//tr[13]/td[4]/text()")[0] co.co_land_use = co_html.xpath("//tr[13]/td[3]/text()")[0] co.co_work_pro = co_html.xpath("//tr[13]/td[5]/text()")[0] co.insert_db() except: log.error("{}小区解析失败".format(project_url))
def comm_info(self, comm_url_list): for comm_url in comm_url_list: try: co_res = requests.get(comm_url, headers=self.headers) co = Comm(co_index) co.co_id = re.search('bh=(\d+)', comm_url).group(1) co.co_name = re.search('项目名称.*?td>(.*?)</', co_res.text, re.S | re.M).group(1) co.co_develops = re.search('公司名称.*?strong>(.*?)</s', co_res.text, re.S | re.M).group(1) co.co_address = re.search('项目坐落.*?">(.*?)</', co_res.text, re.S | re.M).group(1) co.co_pre_sale = re.search('预售证号.*?td>(.*?)</', co_res.text, re.S | re.M).group(1) co.co_pre_sale_date = re.search('批准时间.*?td>(.*?)</', co_res.text, re.S | re.M).group(1) co.co_build_size = re.search('预售面积.*?">(.*?)</', co_res.text, re.S | re.M).group(1) co.insert_db() html = etree.HTML(co_res.text) bu_info_list = html.xpath("//tr[@style]") except Exception as e: log.error('小区信息错误', e) continue self.build_info(bu_info_list, co.co_id) bu_url_list = re.findall("window.open\('(.*?)'\)", co_res.text, re.S | re.M) self.ho_info(bu_url_list, co.co_id)
def start_crawler(self): res = requests.get(self.start_url, headers=self.headers) html = etree.HTML(res.text) comm_url_list = html.xpath("//div[@class='post']//a/@href") for comm_url in comm_url_list: try: url = 'http://www.ggsfcw.com/' + comm_url comm_res = requests.get(url, headers=self.headers) com_html = etree.HTML(comm_res.text) comm = Comm(co_index) comm.co_name = re.search('<h3.*?">(.*?)</', comm_res.text).group(1) comm.co_id = re.search('n=(\d+)', comm_res.text).group(1) comm.co_address = re.search('地址.*?">(.*?)</', comm_res.text).group(1) comm.area = re.search('区县.*?">(.*?)</', comm_res.text).group(1) comm.co_develops = re.search('开发商.*?">(.*?)</', comm_res.text).group(1) comm.co_use = re.search('规划用途.*?">(.*?)</', comm_res.text).group(1) comm.insert_db() except Exception as e: log.error("小区信息错误", e) continue bu_list = com_html.xpath("//div[@id='MainContent_divResult']/a") self.build_info(bu_list, comm.co_id)
def start_crawler(self): for i in range(1, 10000): formdata = { "currentpage": i, "pagesize": 20, } try: res = requests.post( "http://fdc.xmtfj.gov.cn:8001/home/Getzslp", data=formdata, headers=self.headers) con = json.loads(res.text) body = con['Body'] info_dict = json.loads(body)['bodylist'] for i in info_dict: comm = Comm(co_index) comm.co_name = i['XMMC'] comm.co_id = i['TRANSACTION_ID'] comm.co_address = i['XMDZ'] comm.co_pre_sale = i['YSXKZH'] comm.co_all_house = i['PZTS'] comm.co_build_size = i['PZMJ'] comm.co_area = i['XMDQ'] comm.co_pre_date = i['GETDATE'] comm.insert_db() except Exception as e: print( '小区错误,co_index={},url={},data'.format( co_index, 'http://fdc.xmtfj.gov.cn:8001/home/Getzslp', formdata), 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 get_comm_info(self, comm_url_list): for i in comm_url_list: try: comm = Comm(co_index) comm_url = i.replace('view', 'detail') comm.co_type = '物业类型:.*?<dd>(.*?)<' comm.area = '区域所属:.*?<dd>(.*?)<' comm.co_build_size = '建筑面积:.*?<dd>(.*?)<' comm.co_size = '占地面积:.*?<dd>(.*?)<' comm.co_green = '绿化率:.*?<dd><.*?>(.*?)<' comm.co_build_type = '楼 层:.*?<dd>(.*?)<' comm.co_volumetric = '容积率:.*?<dd><.*?>(.*?)<' comm.co_id = '楼盘首页.*?newhouse/.*?/(.*?)/' comm.co_name = '<h1 class="title">(.*?)<' comm.co_address = '楼盘地址:.*?<dd>(.*?)<' comm.co_develops = '开发商:.*?<dd(.*?)<' p = ProducerListUrl(page_url=comm_url, request_type='get', encode='gbk', analyzer_rules_dict=comm.to_dict(), analyzer_type='regex', headers=self.headers) p.get_details() except Exception as e: print(e)
def get_comm_detail(self, comm_list): for i in comm_list: try: comm = Comm(co_index) comm_url = 'http://house.bffdc.gov.cn/public/project/' + i response = requests.get(comm_url) html = response.text comm.co_name = re.search('PROJECT_XMMC">(.*?)<', html, re.S | re.M).group(1) comm.co_develops = re.search('PROJECT_KFQY_NAME">(.*?)<', html, re.S | re.M).group(1) comm.co_address = re.search('PROJECT_XMDZ">(.*?)<', html, re.S | re.M).group(1) comm.area = re.search('PROJECT_SZQY">(.*?)<', html, re.S | re.M).group(1) comm.co_pre_sale = re.search('YSXKZH">(.*?)<', html, re.S | re.M).group(1) comm.insert_db() build_info = re.search('id="buildInfo".*?value="(.*?)"', html, re.S | re.M).group(1) build_url_list = build_info.split(';;') self.get_build_info(build_url_list, comm.co_name) global count count += 1 print(count) except Exception as e: print(e)
def get_comm_detail(self, comm_detail_url): comm_url = 'http://www.kmhouse.org' + comm_detail_url try: comm = Comm(co_index) response = requests.get(comm_url, headers=self.headers) html = response.content.decode('gbk') co_id = re.search('Preid=(.*?)&', comm_detail_url).group(1) co_name = re.search('楼盘名称.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) area = re.search('所在地区.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) co_address = re.search('楼盘地址.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) co_pre_sale = re.search('预售证号.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) co_volumetric = re.search('容 积 率.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) co_green = re.search('绿 化 率.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) co_build_start_time = re.search('开工时间.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_name = co_name comm.area = area comm.co_id = co_id comm.co_address = co_address comm.co_pre_sale = co_pre_sale comm.co_volumetric = co_volumetric comm.co_green = co_green comm.co_build_start_time = co_build_start_time comm.insert_db() global count count += 1 print('count:', count) except Exception as e: print('小区详情错误,co_index={},url={}'.format(co_index, comm_url), e)
def get_comm_info(self, comm_list): for i in comm_list: try: comm = Comm(co_index) comm_url = 'http://www.ytfcjy.com/public/project/' + i response = requests.get(comm_url, headers=self.headers) html = response.text comm.co_name = re.findall('PROJECT_XMMC">(.*?)<', html, re.S | re.M)[0] comm.co_id = re.findall('ProjectInfo.aspx\?code=(.*?)&', html, re.S | re.M)[0] comm.co_address = re.findall('PROJECT_XMDZ">(.*?)<', html, re.S | re.M)[0] comm.co_develops = re.findall('PROJECT_KFQY_NAME">(.*?)<', html, re.S | re.M)[0] comm.area = re.findall('PROJECT_SZQY">(.*?)<', html, re.S | re.M)[0] comm.co_volumetric = re.findall('PROJECT_RJL">(.*?)<', html, re.S | re.M)[0] comm.co_build_size = re.findall('PROJECT_GHZJZMJ">(.*?)<', html, re.S | re.M)[0] comm.co_pre_sale = re.findall('YSXKZH">(.*?)<', html, re.S | re.M)[0] comm.co_all_house = re.findall('YSZTS">(.*?)<', html, re.S | re.M)[0] comm.co_plan_pro = re.findall('id="ghxkzInfo" value=".*?,,(.*?)"', html, re.S | re.M)[0] comm.co_work_pro = re.findall('id="sgxkzInfo" value=".*?,,(.*?)"', html, re.S | re.M)[0] comm.co_land_use = re.findall('id="tdzInfo" value=".*?,,(.*?)"', html, re.S | re.M)[0] comm.insert_db() global count count += 1 print(count) build_url_list = re.findall('id="buildInfo" value="(.*?)"', html, re.S | re.M) self.get_build_info(build_url_list, comm.co_id) except Exception as e: print(e)
def get_comm_info(self, comm_url_list): for i in comm_url_list: try: comm = Comm(co_index) comm.co_id = '楼盘首页.*?aid-(.*?)/' comm.co_name = 'class="ls">(.*?)<' comm.co_type = '物业类型</em>(.*?)<' comm.area = '区域所属:</em>(.*?)<' comm.co_green = '绿 化 率:</em>(.*?)<' comm.co_volumetric = '容 积 率:</em>(.*?)<' comm.co_build_type = '楼 层:</em>(.*?)<' comm.co_size = '占地面积:</em>(.*?)<' comm.co_build_size = '建筑面积:</em>(.*?)<' comm.co_develops = '开 发 商:</em><.*?target="_blank">(.*?)<' comm.co_address = '项目地址:</em>(.*?)<' data_list = comm.to_dict() p = ProducerListUrl( page_url=i, request_type='get', encode='gbk', analyzer_rules_dict=data_list, current_url_rule= 'colspan="3" align="right"><a href="(.*?)"', analyzer_type='regex', headers=self.headers) more_build_url = p.get_details() self.get_build_info(more_build_url) except Exception as e: print(e)
def get_comm_detail(self, comm_list): for i in comm_list: comm_url = 'http://www.yzfdc.cn/' + i try: comm = Comm(co_index) content = self.s.get(comm_url, headers=self.headers) html = content.text comm.co_name = re.search('class="zxlp_08".*?>(.*?)<', html, re.S | re.M).group(1) comm.co_id = re.search( 'class="zxlp_08" href=.*?ProjectId=(.*?)"', html, re.S | re.M).group(1) comm.co_develops = re.search('开 发 商:.*?<span.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_type = re.search('项目类型:.*?<span.*?>(.*?)<', html, re.S | re.M).group(1) comm.area = re.search('所属区位:.*?<span.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_build_size = re.search('建筑面积:.*?<span.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_open_time = re.search('开盘日期:.*?<span.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_handed_time = re.search('交付日期:.*?<span.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_address = re.search('项目具体地址:.*?<span.*?>(.*?)<', html, re.S | re.M).group(1) comm.insert_db() build_url = re.search( '(/BuildingDish_Publicity.aspx\?Projectid=.*?)"', html, re.S | re.M).group(1) self.get_build_info(build_url, comm.co_id) except Exception as e: print('小区错误,co_index={},url={}'.format(co_index, comm_url), e)
def start_crawler(self): for i in range(1, 478): data = { "method": "GetYszData", "page": str(i), "ysxkz": '', "kfs": '', "lpmc": '' } res = requests.post(self.start_url, headers=self.headers, data=data) info = res.json() comm = json.loads(info) for detail in comm['Rows']: co = Comm(co_index) co.co_name = detail['PRJNAME'] co.co_pre_sale = detail['PRENUM'] co.area = detail['CZAREA'] co.co_pre_sale_date = detail['PresaleCertificateDate'] co.co_address = detail['BSIT'] co.co_develops = detail['NAME'] co.co_build_size = detail['YSROOMBAREA'] co.co_all_house = detail['YSROOMNUMS'] co.insert_db()
def start_crawler(self): for region in self.region.items(): region_code = region[0] region_name = region[1] url = self.start_url + region_code + '.html' b = AllListUrl( first_page_url=url, request_method='get', analyzer_type='regex', encode='utf-8', page_count_rule='共(\d+)页>', ) page = b.get_page_count() for i in range(1, int(page) + 1): new_url = url + "?page=" + str(i) res = requests.get(new_url, headers=self.headers) html = etree.HTML(res.text) co_list = html.xpath("//dl[@class='spf_lp_searchlist bg1']") for co in co_list: comm = Comm(co_index) co_url = co.xpath("./dt/h4/a/@href")[0] comm.co_name = co.xpath("./dt/h4/a/text()")[0] comm.co_address = co.xpath(".//address/text()")[0] comm.co_id = re.search('\d+', co_url).group(0) comm.co_develops = co.xpath( "./dd[@class='dev']/a/text()")[0] comm.co_plan_pro = co.xpath("./dt/h4/span/text()")[0] comm.co_type = co.xpath(".//p/span[2]/text()")[0] comm.area = region_name comm.insert_db() detail_url = "http://www.zstmsf.com" + co_url self.bu_parse(detail_url, comm.co_id)
def start_crawler(self): data = {"Submit": "(unable to decode value)"} res = requests.post(self.start_url, data=data, headers=self.headers) html = etree.HTML(res.content.decode('gbk')) comm_url_list = html.xpath( "//tr//span[@style='width:270px; color:#006']//a/@href") for comm_url in comm_url_list: try: url = 'http://www.fxfdcw.com/' + comm_url com_res = requests.get(url, headers=self.headers) con = com_res.content.decode('gbk') co = Comm(co_index) co.co_id = re.search('xmid=(\d+)', comm_url).group(1) co.co_name = re.search('项目名称.*?">(.*?)</', con, re.S | re.M).group(1) co.co_develops = re.search('开发企业:(.*?)  ', con, re.S | re.M).group(1) co.co_address = re.search('项目地址.*?">(.*?)</', con, re.S | re.M).group(1) co.co_build_size = re.search('建筑面积.*?">(.*?)</', con, re.S | re.M).group(1) co.co_all_house = re.search('总套数.*?">(.*?)</', con, re.S | re.M).group(1) co.insert_db() bu_list = re.findall("window.open\('(.*?)'\)", con, re.S | re.M) except Exception as e: # log.error("小区信息错误{}".format(e)) print("小区信息错误{}".format(e)) continue self.bu_info(bu_list, co.co_id)
def start_crawler(self): querystring = {"_method": "GetDataToDynamicInXml", "_session": "rw"} payload = "xmlInfo=%263Croot%2620QueryCode%263D%2622ProjectIntroduce%2622%2620PageIndex%263D%26221%2622%2620PageSize%263D%262215%2622%2620SortField%263D%2622%2620ORDER%2620BY%2620Name%2622%2620QueryString%263D%2622QueryCode%263DProjectIntroduce%2626amp%263BShowModeCode%263Ddefault%2622%2620BeginDate%263D%2622%262000%263A00%263A00%2622%2620EndDate%263D%2622%262023%263A59%263A59%2622%2620Flag%263D%2622TitleBody%2622%2620TitlesWidthInfo%263D%2622EnterPriseName%267C0%2624Name%267C0%2624Location%267C0%2624SoilUse%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" response = requests.request("POST", url, data=payload, params=querystring) html = response.text comm_info_list = re.findall('class="tdctfield tdctwidthset ".*?</tr>', html, re.S | re.M) for i in comm_info_list: comm = Comm(co_index) comm.co_develops = re.search('class="spanctfield".*?>(.*?)<', i, re.S | re.M).group(1) comm.co_name = re.search( 'class="spanctfield".*?class="spanctfield".*?<a.*?>(.*?)<', i, re.S | re.M).group(1) comm.co_address = re.search( 'class="spanctfield".*?class="spanctfield".*?class="spanctfield".*?>(.*?)<', i, re.S | re.M).group(1) comm.co_type = re.search( 'class="spanctfield".*?class="spanctfield".*?class="spanctfield".*?class="spanctfield".*?>(.*?)<', i, re.S | re.M).group(1) comm.co_id = re.search('EnterPriseName_(.*?)"', i, re.S | re.M).group(1) comm.insert_db() self.get_build_info(comm.co_id)
def get_comm_detail(self, comm_detail_url, co_id): comm = Comm(co_index) try: response = requests.get(comm_detail_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_type = re.search('项目主体性质:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_develops = re.search('主开发商:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_address = re.search('项目建设地址:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_all_size = re.search('项目总规划面积(㎡):.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_build_start_time = re.search('计划开工日期:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_build_end_time = re.search('计划竣工日期:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_id = co_id comm.insert_db() build_info_list = re.findall('id="lpan".*?</tr>', html, re.S | re.M) self.get_build_info(build_info_list, co_id) except Exception as e: print('小区错误,co_index={},url={}'.format(co_index, comm_detail_url), e)
def get_comm_info(self, comm_url_list): for i in comm_url_list: try: code = i.split(',') comm_url = 'http://www.tmsf.com/newhouse/property_' + code[ 0] + '_' + code[1] + '_info.htm' comm = Comm(co_index) comm.co_name = 'buidname.*?>(.*?)<' comm.co_address = '--位置行--.*?<span.*?title="(.*?)"' comm.co_build_type = '建筑形式:<.*?>(.*?)<' comm.co_develops = '项目公司:<.*?>(.*?)<' comm.co_volumetric = '容 积 率:</span>(.*?)<' comm.co_green = '绿 化 率:</span>(.*?)<' comm.co_size = '占地面积:</span>(.*?)<' comm.co_build_size = '总建筑面积:</span>(.*?)<' comm.co_all_house = '总户数:</span>(.*?)<' comm.co_id = 'info" href="/newhouse/property_(.*?)_info' p = ProducerListUrl(page_url=comm_url, request_type='get', encode='utf-8', analyzer_rules_dict=comm.to_dict(), current_url_rule='一房一价<.*?href="(.*?)"', analyzer_type='regex', headers=self.headers) build_all_url = p.get_details() global count count += 1 print('comm:', count) self.get_build_info(build_all_url) except Exception as e: print('小区页面,co_index={},url={}'.format(co_index, comm_url), e)
def get_comm_info(self, comm_url_list): for i in comm_url_list: comm_url = 'http://www.fjlyfdc.com.cn/' + i try: comm = Comm(co_index) response = requests.get(comm_url, headers=self.headers) html = response.text comm.co_develops = re.search('公司名称:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_name = re.search('项目名称:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_pre_sale = re.search('预售许可证:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_address = re.search('项目坐落:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_type = re.search('规划用途:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_build_size = re.search('建筑面积:.*?<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_green = re.search('绿地率:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_open_time = re.search('开工日期:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_build_end_time = re.search('竣工日期:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_all_house = re.search('批准销售:.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_all_size = re.search('批准销售:.*?<td.*?<td.*?>(.*?)<', html, re.S | re.M).group(1) comm.co_id = re.search('CaseId=(.*?)$', comm_url).group(1) comm.insert_db() build_url_list = re.findall('href="(/House/BuildingInfo\?buildingInfoID=.*?&caseID=.*?)"', html, re.S | re.M) self.get_build_info(build_url_list, comm.co_id) except Exception as e: print('楼栋错误,co_index={},url={}'.format(co_index, comm_url), e)
def start_crawler(self): b = AllListUrl(first_page_url=self.start_url, request_method='get', analyzer_type='regex', encode='utf-8', page_count_rule='共(\d+)页', ) page = b.get_page_count() for i in range(1,int(page)+1): url = self.start_url + '?pageIndex=2' + str(page) page_res = requests.get(url,headers=self.headers) html = etree.HTML(page_res.text) comm_info_list = html.xpath("//ul/li/div") for comm_info in comm_info_list: try: co = Comm(co_index) co.co_name = comm_info.xpath("./p/a/text()")[0] deve = comm_info.xpath("./p[2]/text()")[0] addr = comm_info.xpath("./p[3]/text()")[0] co.co_develops = re.search('开发商:(.*)',deve).group(1) co.co_address = re.search('楼盘地址.*?:(.*)',addr).group(1) comm_url = comm_info.xpath("./p/a/@href")[0] co.co_id = re.search('projectId=(\d+)',comm_url).group(1) co.insert_db() co_url = 'http://www.bdfdc.net' + comm_url co_res = requests.get(co_url,headers=self.headers) time.sleep(5) bu_html = etree.HTML(co_res.text) bu_url_list = bu_html.xpath("//div[@style]/a")[1:] except Exception as e: # log.error("小区信息错误{}".format(e)) print("小区信息错误{}".format(e)) continue self.bu_info(bu_url_list,co.co_id)
def start_crawler(self): for i in range(1, 40): url = 'http://zfbzj.baotou.gov.cn/index.php?m=content&c=permit&a=init&page=' + str( i) res = requests.get(url, headers=self.headers) html = etree.HTML(res.content.decode()) temp_list = html.xpath("//tr/td[@align='left']/a") for temp in temp_list: try: temp_url = temp.xpath("./@href")[0] co_res = requests.get(temp_url, headers=self.headers) content = co_res.content.decode() co = Comm(co_index) co.co_id = re.search('id=(\d+)', temp_url).group(1) co.co_name = re.search('项 目 名 称.*?">(.*?)</td', content, re.S | re.M).group(1) co.co_develops = re.search('开发建设单位.*?">(.*?)</td', content, re.S | re.M).group(1) co.co_address = re.search('项 目 座 落.*?">(.*?)</td', content, re.S | re.M).group(1) co.co_pre_sale = re.search('预销售许可证号.*?">(.*?)</td', content, re.S | re.M).group(1) co.co_pre_sale_date = re.search('发证日期.*?">(.*?)</td', content, re.S | re.M).group(1) co.insert_db() except Exception as e: log.error("{}小区解析失败{}".format(temp_url, e)) continue
def get_comm_info(self, comm_url_list): for i in comm_url_list: try: response = requests.get(i, headers=self.headers) html = response.text comm = Comm(co_index) comm.co_name = re.findall('PROJECT_XMMC">(.*?)<', html, re.S | re.M)[0] comm.co_develops = re.findall('PROJECT_KFQY_NAME">(.*?)<', html, re.S | re.M)[0] comm.co_address = re.findall('PROJECT_XMDZ">(.*?)<', html, re.S | re.M)[0] comm.area = re.findall('PROJECT_SZQY">(.*?)<', html, re.S | re.M)[0] comm.co_volumetric = re.findall('PROJECT_RJL">(.*?)<', html, re.S | re.M)[0] comm.co_build_size = re.findall('PROJECT_GHZJZMJ">(.*?)<', html, re.S | re.M)[0] comm.co_pre_sale = re.findall('YSXKZH">(.*?)<', html, re.S | re.M)[0] comm.co_id = re.findall('PROJECT_XMBH">(.*?)<', html, re.S | re.M)[0] comm.insert_db() global count count += 1 print(count) bu_info = re.search('id="buildInfo".*?value="(.*?)"', html, re.S | re.M).group(1) self.get_build_info(bu_info, comm.co_id, i) except Exception as e: print('小区错误,co_index={},url={}'.format(co_index, i), e)