def main(): url="http://rst.qinghai.gov.cn/qhrstweb/zcfg/zcfgpages.action" for i in range(1,16): print(i) data={'nodeId': '', 'title': '', 'sendDate': '', 'page': str(i), 'type': 'zcfg', 'fileNo': ''} html=post(url,data=data) parse_index(html)
def main(): url="http://gzw.ah.gov.cn/xxgk/list.jsp" for i in range(1,40): print(i) data={'strColId': '0ae0ae0d59cb48b38d86babb0edc8918', 'strTopicType': '', 'strThemeType': '', 'strWebSiteId': '1448866116912004', 'strPage': '', 'strMasTitle': '', 'year': '', '_index': '', 'PageSizeIndex': str(i), 'strIndex': '', 'strSearchContent': '', 'strTxtCnt': ''} html=post(url,data=data,code="gbk") parse_index(html)
def main(): url="http://liaoning.chinatax.gov.cn/module/web/jpage/dataproxy.jsp?" for i in range(0,25): params={'startrecord':str(i*45+1), 'endrecord': str(i*45+45), 'perpage': '15'} data={'col': '1', 'appid': '1', 'webid': '1', 'path': '/', 'columnid': '1777', 'sourceContentType': '1', 'unitid': '9237', 'webname': '国家税务总局辽宁省税务局', 'permissiontype': '0'} html=post(url,params=params,data=data) parse_index(html)
def main(): url="https://neris.csrc.gov.cn/falvfagui/rdqsHeader/informationController" for i in range(13,131): print(i) data={'pageNo': str(i), 'lawType': '1'} html=post(url,data=data,verify=False) parse_index(html)
def main(): url="http://jyt.zj.gov.cn/module/jpage/dataproxy.jsp?" for i in range(0,4): params={'startrecord':str(i*45+1), 'endrecord': str(i*45+45), 'perpage': '15'} data={'col': '1', 'appid': '1', 'webid': '3099', 'path': '/', 'columnid': '1543960', 'sourceContentType': '1', 'unitid': '4848547', 'webname': '浙江省教育厅', 'permissiontype': '0'} html=post(url,params=params,data=data) parse_index(html)
def main(): url = "http://mz.hangzhou.gov.cn/module/xxgk/search.jsp?" for i in range(1, 3): params = { 'texttype': '', 'fbtime': '', 'vc_all': '', 'vc_filenumber': '', 'vc_title': '', 'vc_number': '', 'currpage': str(i), 'sortfield': ',compaltedate:0' } data = { 'infotypeId': 'W001', 'jdid': '3085', 'area': '002489524', 'divid': 'div1530906', 'vc_title': '', 'vc_number': '', 'sortfield': ',compaltedate:0', 'currpage': str(i), 'vc_filenumber': '', 'vc_all': '', 'texttype': '', 'fbtime': '' } html = post(url, params=params, data=data) parse_index(html)
def main(): url="http://jiangsu.chinatax.gov.cn/module/web/jpage/dataproxy.jsp?" for i in range(0,13): params={'startrecord':str(i*45+1), 'endrecord': str(i*45+45), 'perpage': '15'} data={'col': '1', 'webid': '18', 'path': 'http://jiangsu.chinatax.gov.cn/', 'columnid': '8432', 'sourceContentType': '1', 'unitid': '32200', 'webname': '国家税务总局江苏省税务局网站', 'permissiontype': '0'} html=post(url,params=params,data=data) parse_index(html)
def main(): url = "http://hrss.ah.gov.cn/web/initNewsList.html" for i in range(1, 419): print(i) data = {"p2": "401", "p3": str(i)} html = post(url, data=data, headers=headers) parse_index(html)
def main(): url = "http://www.hangzhou.gov.cn/module/xxgk/search.jsp?" for i in range(1, 91): params = { 'texttype': '0', 'fbtime': '-1', 'vc_all': '', 'vc_filenumber': '', 'vc_title': '', 'vc_number': '', 'currpage': str(i), 'sortfield': ',compaltedate:0' } data = { 'infotypeId': 'F010000201', 'jdid': '149', 'area': '', 'divid': 'div1256347', 'vc_title': '', 'vc_number': '', 'sortfield': ',compaltedate:0', 'currpage': str(i), 'vc_filenumber': '', 'vc_all': '', 'texttype': '0', 'fbtime': '-1' } html = post(url, params=params, data=data) parse_index(html)
def main(): url="http://da.jiangsu.gov.cn/module/web/jpage/dimensiondataproxy.jsp?" for i in range(0,5): params={'startrecord':str(i*15+1), 'endrecord': str(i*15+45), 'perpage': '15'} data={'col': '1', 'appid': '1', 'webid': '18', 'path': '/', 'columnid': '65298', 'infodim': '213', 'infodimjj': '', 'jjtype': '0', 'sourceContentType': '3', 'unitid': '262653', 'keyWordCount': '999', 'webname': '江苏省药品监督管理局'} html=post(url,params=params,data=data) parse_index(html)
def main(): url="http://gzw.jiangxi.gov.cn/module/web/jpage/dataproxy.jsp?" for i in range(0,5): params={'startrecord':str(i*45+1), 'endrecord': str(i*45+45), 'perpage': '15'} data={'col': '1', 'webid': '175', 'path': 'http://gzw.jiangxi.gov.cn/', 'columnid': '22977', 'sourceContentType': '1', 'unitid': '341364', 'webname': '江西省国有资产监督管理委员会', 'permissiontype': '0'} html=post(url,params=params,data=data) parse_index(html)
def main(): url = "http://wsjkw.hebei.gov.cn/list/more_tzlist_43.html" for i in range(1, 201): print(i) data = {"page": str(i)} html = post(url, data=data) parse_index(html)
def main(): url="http://jilin.chinatax.gov.cn/module/web/jpage/dataproxy.jsp?" for i in range(0,5): params={'startrecord': str(75*i+1), 'endrecord': str(75*i+75), 'perpage': '25'} data={'col': '1', 'appid': '1', 'webid': '1', 'path': '/', 'columnid': '311', 'sourceContentType': '1', 'unitid': '10849', 'webname': '国家税务总局吉林省税务局', 'permissiontype': '0'} html=post(url,params=params,data=data) parse_index(html)
def main(): url = "http://wsjkw.hangzhou.gov.cn/module/xxgk/search.jsp?" for i in range(0, 133): print(i) params = { 'texttype': '0', 'fbtime': '-1', 'vc_all': '', 'vc_filenumber': '', 'vc_title': '', 'vc_number': '', 'currpage': str(i), 'sortfield': ',createdate:0,orderid:0' } data = { 'infotypeId': 'A02', 'jdid': '1305', 'area': '', 'divid': 'div1665241', 'vc_title': '', 'vc_number': '', 'sortfield': ',createdate:0,orderid:0', 'currpage': str(i), 'vc_filenumber': '', 'vc_all': '', 'texttype': '0', 'fbtime': '-1' } html = post(url, params=params, data=data) parse_index(html)
def main(): url="http://gzw.hangzhou.gov.cn/module/jpage/dataproxy.jsp?" for i in range(0,2): params={'startrecord':str(i*30+1), 'endrecord': str(i*30+30), 'perpage': '10'} data={'col': '1', 'appid': '1', 'webid': '3247', 'path': '/', 'columnid': '1689580', 'sourceContentType': '1', 'unitid': '5095353', 'webname': '杭州市人民政府国有资产监督管理委员会', 'permissiontype': '0'} html=post(url,params=params,data=data) parse_index(html) break
def main(): url="http://scjgj.jiangsu.gov.cn/module/xxgk/search.jsp?" for i in range(1,147): print(i) params={'texttype': '', 'fbtime': '', 'vc_all': '', 'vc_filenumber': '', 'vc_title': '', 'vc_number': '', 'currpage': str(i), 'sortfield': '', 'fields': '', 'fieldConfigId': '', 'hasNoPages': '', 'infoCount': ''} data={'infotypeId': '', 'jdid': '79', 'area': '01400022-0', 'divid': 'div70222', 'vc_title': '', 'vc_number': '', 'currpage': str(i), 'vc_filenumber': '', 'vc_all': '', 'texttype': '', 'fbtime': '', 'sortfield': '', 'fields': '', 'fieldConfigId': '', 'hasNoPages': '', 'infoCount': ''} html=post(url,params=params,data=data) parse_index(html)
def main(): url="http://tb.hangzhou.gov.cn/module/xxgk/search.jsp?" for i in range(1,3): print(i) params={'texttype': '', 'fbtime': '', 'vc_all': '', 'vc_filenumber': '', 'vc_title': '', 'vc_number': '', 'currpage': str(i), 'sortfield': ',compaltedate:0'} data={'infotypeId': 'F01000', 'jdid': '2934', 'area': '', 'divid': 'div1510225', 'vc_title': '', 'vc_number': '', 'sortfield': ',compaltedate:0', 'currpage': str(i), 'vc_filenumber': '', 'vc_all': '', 'texttype': '', 'fbtime': ''} html=post(url,data=data,params=params) parse_index(html)
def main(): for i in range(1,212): print(i) url="http://jshrss.jiangsu.gov.cn/module/xxgk/search.jsp?" params={'texttype': '', 'fbtime': '', 'vc_all': '', 'vc_filenumber': '', 'vc_title': '', 'vc_number': '', 'currpage': str(i), 'sortfield': 'compaltedate:0', 'fields': '', 'fieldConfigId': '', 'hasNoPages': '', 'infoCount': ''} data = {'infotypeId': '', 'jdid': '67', 'area': '550232674', 'divid': 'div51019', 'vc_title': '', 'vc_number': '', 'sortfield': 'compaltedate:0', 'currpage':str(i), 'vc_filenumber': '', 'vc_all': '', 'texttype': '', 'fbtime': '', 'fields': '', 'fieldConfigId': '', 'hasNoPages': '', 'infoCount': ''} html=post(url,data=data,params=params) parse_index(html) time.sleep(random.randint(1,2))
def main(): url = "http://111.40.217.165:29090/webpage/gkmlList.aspx" for i in range(0, 5): if i == 0: html = get(url) parse_index(html) data = get_form_data(html, i + 1) else: html = post(url, data=data) data = get_form_data(html, i + 1) parse_index(html)
def main(): url = "http://tianjin.chinatax.gov.cn/u_zlmViewMx.action" for i in range(1, 27): print(i) data = { 'lmdm': '030001', 'fjdm': '11200000000', 'page': str(i), 'd': '' } html = post(url, data=data) parse_index(html)
def main(): url = "http://sww.cq.gov.cn//api/directive/contentList" for i in range(1, 8): print(i) data = { 'showParamters': 'ture', 'categoryId': '137', 'pageIndex': str(i), 'count': '18' } html = post(url, data=data) parse_index(html)
def main(): a=[15, 18, 20, 21, 22, 24, 27, 29, 31, 32, 35, 37, 38, 39, 40, 42, 44, 45, 48, 49, 51, 52, 54, 55, 56, 57, 61, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 76, 78, 79, 80, 81, 83, 84, 85, 86, 87, 88, 89, 90, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 107, 108, 110, 112, 116, 119, 121, 124, 125, 126, 130] url="https://neris.csrc.gov.cn/falvfagui/rdqsHeader/informationController" for i in a: try: print(i) data={'pageNo': str(i), 'lawType': '1'} html=post(url,data=data,verify=False) parse_index(html) except: all_error.append(i) print("错误列表" , all_error) time.sleep(random.randint(60,120))
def main(): url = "http://www.hda.gov.cn/getHtmlInDivNormal.do?ajaxform" for i in range(0, 4): print(i) data = { 'gwcsCode': 'undefined', 'divId': '8a80948165cd561f01675499064c7b9fpagelist', "requestUrl": "http://www.hda.gov.cn/viewCmsCac.do", "cacId": "8a8094816f4a8e29016f7dd702fb1547", "offset": str(20 * i), "queryString": "cacId=8a8094816f4a8e29016f7dd702fb1547" } html = post(url, data=data) parse_index(html)
def main(): url = "http://scjg.nx.gov.cn/admin/article/zwgk" for i in range(1, 34): print(i) data = { 'website_code': 'gdscjg', 'cid': '160', 'currentPageNo': str(i), 'name': '通知公告', 'cids': '163,159,160,165,211', 'pagination_input': '' } html = post(url, data=data) parse_index(html)
def main(): url = "http://shanxi.chinatax.gov.cn/common/extQuery?" for i in range(1, 25): print(i) params = { 'sqlid': 'web_data_wz2', 'limit': '15', 'lmdm': '545', 'orgid': '11400', 'ptwz': 'Y', 'page': str(i) } data = {'start': '0'} html = post(url, data=data, params=params) parse_index(html)
def main(): for i in range(0, 19): url = "http://hrss.shandong.gov.cn/gentleCMS/search/index.do" data = { 'NAME': '', 'WJFL': '法律法规规章及规范性文件', 'PROP1': '', 'ZCWH': '', 'CHANNELID': '393dabcf-79cb-415f-b722-df55b25088f0', 'SITEID': '7f6d5d22-89b8-44d7-b0b4-f4a0185a4f8e', 'start': 15 * i, 'pageSize': '15' } html = post(url, data=data) parse_index(html)
def main(): url = "http://edu.shandong.gov.cn/module/web/jpage/dataproxy.jsp?" for i in range(0, 48): params = { 'startrecord': str(i * 45 + 1), 'endrecord': str(i * 45 + 45), 'perpage': '15' } data = { 'col': '1', 'webid': '68', 'path': 'http://edu.shandong.gov.cn/', 'columnid': '11990', 'sourceContentType': '1', 'unitid': '62603', 'webname': '山东省教育厅', 'permissiontype': '0' } html = post(url, params=params, data=data) parse_index(html)
def main(): for i in range(4, 5): print(i) url = "http://rst.nmg.gov.cn/ecdomain/portal/portlets/newslist/newslistcomponent.jsp?" params = { 'goPage': '1', 'pageNum': str(i), 'siteID': 'nmrsw', 'pageID': 'mgbolpjicokkbbofjaipjbidifhnacno', 'moduleID': 'mgccnoejcokkbbofjaipjbidifhnacno', 'moreURI': '/ecdomain/framework/nmrsw/mgbolpjicokkbbofjaipjbidifhnacno/mgccnoejcokkbbofjaipjbidifhnacno.do', 'var_temp': 'kjoafadnboaebboekdmcjknnpheemckj', 'currfolderid': 'null', 'showChildFlag': 'false', 'displayPageLinkFlag': 'true' } data = {"jspcontrols.ajax.xhtml": True} html = post(url, data=data, params=params) parse_index(html)
def main(): url = "http://gzw.zj.gov.cn/module/jslib/jquery/jpage/dataproxy.jsp?" for i in range(0, 1): params = { 'startrecord': str(i * 45 + 1), 'endrecord': str(i * 45 + 45), 'perpage': '25' } data = { 'col': '1', 'appid': '1', 'webid': '1', 'path': '/', 'columnid': '569', 'sourceContentType': '1', 'unitid': '2057', 'webname': '浙江省国资委', 'permissiontype': '0' } html = post(url, params=params, data=data) parse_index(html)
def main(): url = "http://heilongjiang.chinatax.gov.cn/module/web/jpage/dataproxy.jsp?" for i in range(0, 2): params = { 'startrecord': str(i * 15), 'endrecord': str(i * 15 + 15), 'perpage': '15' } data = { 'col': '1', 'appid': '1', 'webid': '18', 'path': 'http://heilongjiang.chinatax.gov.cn/', 'columnid': '4912', 'sourceContentType': '1', 'unitid': '43018', 'webname': '国家税务总局黑龙江省税务局', 'permissiontype': '0' } html = post(url, params=params, data=data) parse_index(html)