python\u6279\u91cf\u722c\u53d6\u57df\u540d\u5907\u6848\u5c0f\u5de5\u5177–\u63a5\u53e3\u662f\u7ad9\u957f\u4e4b\u5bb6<\/p>\n
import re, requests, time, xlrd, random, csv\r\nfrom lxml import etree\r\n\r\ndomain_list = []\r\n# workbook = xlrd.open_workbook('\u672a\u722c.xls')\r\n# sheet0 = workbook.sheet_by_index(0)\r\n# cols = sheet0.col_slice(0,1)\r\n# for col in cols:\r\n# domain_list.append(col.value)\r\n\r\nwith open('111.txt',encoding='utf-8',newline='')as fk:\r\n for i in fk:\r\n domain = re.sub(r'\\r\\n$','',i)\r\n domain_list.append(domain)\r\n\r\nuser_Agent_list = [\r\n \"Mozilla\/5.0 (Windows NT 10.0; WOW64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/85.0.4183.102 Safari\/537.36\",\r\n \"Mozilla\/5.0 (Windows NT 10.0; WOW64; rv:6.0) Gecko\/20100101 Firefox\/6.0\",\r\n \"Mozilla\/5.0 (Windows NT 10.0; WOW64) AppleWebKit\/534.50 (KHTML, like Gecko) Version\/5.1 Safari\/534.50\",\r\n \"Opera\/9.80 (Windows NT 10.0; U; zh-cn) Presto\/2.9.168 Version\/11.50\",\r\n \"Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/87.0.4280.66 Safari\/537.36\"\r\n]\r\n\r\na = 0\r\nurl = 'http:\/\/icp.chinaz.com\/searchs'\r\nwith open('test1.csv','a',newline='')as fk:\r\n writer = csv.writer(fk)\r\n csv_header = ['\u57df\u540d','\u4e3b\u529e\u5355\u4f4d\u540d\u79f0','\u5355\u4f4d\u6027\u8d28','\u7f51\u7ad9\u5907\u6848\/\u8bb8\u53ef\u8bc1\u53f7','\u7f51\u7ad9\u540d\u79f0','\u5ba1\u6838\u65f6\u95f4']\r\n writer.writerow(csv_header)\r\n for num in range(len(domain_list)\/\/20-a\/\/20+1):\r\n local_time = int(time.time())\r\n Cookie = 'UM_distinctid=176dabed56b80a-080978cc77e73-376b4502-1fa400-176dabed56c952; __guid=31546918.3636803744203470000.1610026817897.5715; __gads=ID=2c6886bd82b7280d-2280524a92c500e4:T=1610026898:RT=1610026898:S=ALNI_MbyH5W7HulKDaCwCpZdoBvNfCv5fg; toolbox_urls=www.ccbechina.cn|www.apple.iducs.cn; qHistory=aHR0cDovL3dob2lzLmNoaW5hei5jb20vK1dob2lz5p+l6K+ifGh0dHA6Ly90b29sLmNoaW5hei5jb21f56uZ6ZW\/5bel5YW3fGh0dHA6Ly9yYW5rLmNoaW5hei5jb20vcmFua2FsbC9f5p2D6YeN57u85ZCI5p+l6K+ifGh0dHA6Ly9zZW8uY2hpbmF6LmNvbV9TRU\/nu7zlkIjmn6Xor6J8aHR0cDovL3Rvb2wuY2hpbmF6LmNvbS9kbnMvX0Ruc+afpeivog==; Hm_lvt_aecc9715b0f5d5f7f34fba48a3c511d6=1614822213,1614822577,1614822679,1614823108; CNZZDATA5082706=cnzz_eid%3D817694234-1610023182-%26ntime%3D1615443601; Hm_lvt_ca96c3507ee04e182fb6d097cb2a1a4c=1614158602,1614757255,1615271947,1615445490; .AspNetCore.Antiforgery.-Z5WMyCX4K0=CfDJ8GYV1qq4FPhNvMPl1WmHHp4TJ3UkqvXhcEpr97APD9DsO6WWhvHhS1Ur7lynrac2voNvP_6CKjUNJ7GfxR0Y8Hvzh5CzvnqGj1zDfZqI-uOal1z6njEfqbHpCtZTRIzvCbnZaH2ylkWKvQ8HYwdptNY; bbsmax_user=a3edcb67-4488-4058-ac01-ec29ef25c2d3; avatarId=14f364b2-af95-4174-a58f-b95415e9ad1c-; .AspNetCore.Session=CfDJ8GYV1qq4FPhNvMPl1WmHHp7xuHiscEHg0wvC5lfyLapGtl8WJLhWLk%2BrvYNFAM9CCKxQ6RnvIiEgR86UrCH%2FavX838WgaU%2BU%2FbXLz305a97b8qWufBUMzpsSVhMKMMBzfgT%2F9LSOKw1wTwgn9ND7ySHWDWbXg%2BXyPKaPVWG7dFdm; monitor_count=4; Hm_lpvt_ca96c3507ee04e182fb6d097cb2a1a4c={0}'.format(local_time)\r\n headers = {\r\n 'User-Agent': random.choice(user_Agent_list),\r\n 'Cookie':Cookie,\r\n 'Host':'icp.chinaz.com',\r\n 'Referer':'http:\/\/icp.chinaz.com\/web'\r\n }\r\n form_data = {\r\n 'hosts':','.join(domain_list[a:a+20])\r\n }\r\n\r\n res = requests.post(url,headers=headers,data=form_data)\r\n # print(res.content.decode('utf-8'))\r\n html = etree.HTML(res.content.decode('utf-8'))\r\n trs = html.xpath('\/\/tbody[@id=\"result_table\"]\/tr')\r\n for tr in trs:\r\n domain = tr.xpath('.\/td[1]\/\/text()')[0]\r\n organizer = tr.xpath('.\/td[2]\/\/text()')[0]\r\n unit_nature = tr.xpath('.\/td[3]\/\/text()')[0]\r\n passcord = tr.xpath('.\/td[4]\/\/text()')[0]\r\n website_name = tr.xpath('.\/td[5]\/\/text()')[0]\r\n audit_time = tr.xpath('.\/td[8]\/\/text()')[0]\r\n csv_content = [domain,organizer,unit_nature,passcord,website_name,audit_time]\r\n print(csv_content)\r\n writer.writerow(csv_content)\r\n a += 20\r\n time.sleep(1)\r\n print('\u73b0\u5728\u662f\u7b2c%s\u4e2a'% a)\r\n # print(form_data)\r\n<\/pre>\n <\/p>\n","protected":false},"excerpt":{"rendered":"
python\u6279\u91cf\u722c\u53d6\u57df\u540d\u5907\u6848\u5c0f\u5de5\u5177–\u63a5\u53e3\u662f\u7ad9\u957f\u4e4b\u5bb6 import re, requests, ti […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[279],"tags":[236,296],"class_list":["post-1704","post","type-post","status-publish","format-standard","hentry","category-pyhton","tag-python","tag-296"],"_links":{"self":[{"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/posts\/1704","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/comments?post=1704"}],"version-history":[{"count":2,"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/posts\/1704\/revisions"}],"predecessor-version":[{"id":1875,"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/posts\/1704\/revisions\/1875"}],"wp:attachment":[{"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/media?parent=1704"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/categories?post=1704"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/tags?post=1704"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}