{"id":100283,"date":"2025-03-06T06:27:41","date_gmt":"2025-03-06T02:57:41","guid":{"rendered":"https:\/\/nabfollower.com\/blog\/cai-ji-bai-du-zhi-shu-1n1j\/"},"modified":"2025-03-06T06:27:41","modified_gmt":"2025-03-06T02:57:41","slug":"cai-ji-bai-du-zhi-shu-1n1j","status":"publish","type":"post","link":"https:\/\/nabfollower.com\/blog\/cai-ji-bai-du-zhi-shu-1n1j\/","title":{"rendered":"\u0641\u0647\u0631\u0633\u062a Baidu \u0631\u0627 \u062c\u0645\u0639 \u06a9\u0646\u06cc\u062f"},"content":{"rendered":"
\n
\"\"\"<\/span>\n\u767e\u5ea6\u6307\u6570\u722c\u866b 2025\u5e743\u6708\n<\/span>\"\"\"<\/span>\nimport<\/span> json<\/span>\nfrom<\/span> traceback<\/span> import<\/span> format_exc<\/span>\nimport<\/span> time<\/span>\n\nimport<\/span> requests<\/span>\nfrom<\/span> datetime<\/span> import<\/span> datetime<\/span>,<\/span> timedelta<\/span>\nimport<\/span> numpy<\/span> as<\/span> np<\/span>\nimport<\/span> pandas<\/span> as<\/span> pd<\/span>\nimport<\/span> random<\/span>\nfrom<\/span> requests.exceptions<\/span> import<\/span> RequestException<\/span>\n\ncookies_dict<\/span> =<\/span> {<\/span>\n    \"<\/span>BAIDUID_BFESS<\/span>\"<\/span>:<\/span> \"<\/span>03C87F7E8DAB230EF3CF68E2E4CCB7AC:FG=1<\/span>\"<\/span>,<\/span>\n    \"<\/span>Hm_lvt_d101ea4d2a5c67dab98251f0b5de24dc<\/span>\"<\/span>:<\/span> \"<\/span>1740900295<\/span>\"<\/span>,<\/span>\n    \"<\/span>HMACCOUNT<\/span>\"<\/span>:<\/span> \"<\/span>70309D756AB7564A<\/span>\"<\/span>,<\/span>\n    \"<\/span>ppfuid<\/span>\"<\/span>:<\/span> \"<\/span>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<\/span>\"<\/span>,<\/span>\n    \"<\/span>BDUSS<\/span>\"<\/span>:<\/span> \"<\/span>ndtMC1BVXpUdFF6Z3NGTHVCZlRmTXJVSXN3WUZXSkpTUXg5NU1iZGRCNlJsZXRuSVFBQUFBJCQAAAAAAAAAAAEAAAAK5OqRyqLH6cPOAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJEIxGeRCMRnV<\/span>\"<\/span>,<\/span>\n    \"<\/span>SIGNIN_UC<\/span>\"<\/span>:<\/span> \"<\/span>70a2711cf1d3d9b1a82d2f87d633bd8a04909129477oUCDVgDuFIWQq0I5Qh%2BRYVI211tn6l6RtVzEcHQHKEeV3UqjZrdEN2J58qMq3yI6SH4Pf5yaO3wsYp7rDl7owf8Vxw8nV7J6HDde92bSfNLB%2BLYSDn8mcJUeJZ9DvByeHYEh5HZIEmBqjEW9Kp1nhY39kd0%2FMKxlLMEZywpREcfeqkBuNDImGT1swOphjUr0m7yoFRuoRONhZO0DhIUp8qMp%2BI%2BGZ9URB2%2FDv3g%2FwZ0nXnjrScjtkdIga7hBOF4Os4RsqXflHU7INYd10uoQ2Ecn99qPwcD5%2BuKJ7%2BtRR94%3D59476045678983651647832308115528<\/span>\"<\/span>,<\/span>\n    \"<\/span>__cas__rn__<\/span>\"<\/span>:<\/span> \"<\/span>490912947<\/span>\"<\/span>,<\/span>\n    \"<\/span>__cas__st__212<\/span>\"<\/span>:<\/span> \"<\/span>eb761014eef2d40b7c2bad261c6098e983f5ecc9a335b83a0f261f17f01cab78142cd91d640c0bff5197630b<\/span>\"<\/span>,<\/span>\n    \"<\/span>__cas__id__212<\/span>\"<\/span>:<\/span> \"<\/span>40927145<\/span>\"<\/span>,<\/span>\n    \"<\/span>CPTK_212<\/span>\"<\/span>:<\/span> \"<\/span>1776632285<\/span>\"<\/span>,<\/span>\n    \"<\/span>CPID_212<\/span>\"<\/span>:<\/span> \"<\/span>40927145<\/span>\"<\/span>,<\/span>\n    \"<\/span>Hm_lpvt_d101ea4d2a5c67dab98251f0b5de24dc<\/span>\"<\/span>:<\/span> \"<\/span>1740900504<\/span>\"<\/span>,<\/span>\n    \"<\/span>BDUSS_BFESS<\/span>\"<\/span>:<\/span> \"<\/span>ndtMC1BVXpUdFF6Z3NGTHVCZlRmTXJVSXN3WUZXSkpTUXg5NU1iZGRCNlJsZXRuSVFBQUFBJCQAAAAAAAAAAAEAAAAK5OqRyqLH6cPOAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJEIxGeRCMRnV<\/span>\"<\/span>,<\/span>\n    \"<\/span>bdindexid<\/span>\"<\/span>:<\/span> \"<\/span>jcohnli710phtu4po08tnl0o33<\/span>\"<\/span>,<\/span>\n    \"<\/span>ab_sr<\/span>\"<\/span>:<\/span> \"<\/span>1.0.1_MTk4MzQ0NWIxNmJjZGNiODQzM2I2OGU2MjY0M2ExODNhZmMwMjY4MjQ5YzJkM2IzZTZjNTc1ODA1ZDdkNmFhM2QyZDMyNWZkMWRmNGMyZmNjYjFiMTJiYzgwMzc5YzA5ZDVkM2U1M2ZiNTdkN2VlZWY0ODZiNmE1MTg3Y2YzZjVhYWU5ZDZhZmIyMGY2ZWQwMzM5ODM2ZTI3ODY5Nzk5ZQ==<\/span>\"<\/span>,<\/span>\n    \"<\/span>RT<\/span>\"<\/span>:<\/span> \"<\/span>z=1&dm=baidu.com&si=f3786353-627c-486d-b8e5-ea5d83dc0735&ss=m7rb5t0k&sl=6&tt=p5z&bcn=https%3A%2F%2Ffclog.baidu.com%2Flog%2Fweirwood%3Ftype%3Dperf&ld=6czl<\/span>\"<\/span>\n}<\/span>\n\ncredential<\/span> =<\/span> {<\/span>\n    \"<\/span>cipherText<\/span>\"<\/span>:<\/span> \"<\/span>1740888411355_1740901282164_aLrE9Za0dpKtlO3CQw1IR\/Yz3hP8cGXzHI\/2BnYqUk5XRMPS4pr5kfk3slC7+G60AS9KjhhlCPNuQnqbFhpZS9Z7MUVTxUeQ8XlgGhrmV+FapK3+nQuTdrm1pz8Jy5qhWO0pOhQyUqv\/AR5RFI0hKsasKjMYDQfng+XPMhygTo0rCb3PLrFDflBQ1riNlJ7Bg8s6TfsE3OMaJPAQsjhaZlZO1bXUAhFIY0EMqIxq2DAkMVEatrHKmDbkb0f2NJw988jZkhDEZTAJ06iAXqSLbKnbF0bPCUIqaT\/a5yeqr2KtCwbJYH4flHQSoThN40a6t\/XiyTqUc1Mdds6w27Q\/qOyR+nPe8978fEsEB3UssJ9LPc62xsjzLmY1x5qH7eA\/j7eJAgbbWVvYW8H\/4N3iaauKg0D1F8NqUHMGoGVpAQSj0\/HLx5pUebCoFBVBnbA2kMYD8kvavD1WzPEMte2sp2uhlSGB4IIDMkqz13eaIsc=<\/span>\"<\/span>,<\/span>\n    \"<\/span>cookie_BDUSS<\/span>\"<\/span>:<\/span> cookies_dict<\/span>[<\/span>'<\/span>BDUSS<\/span>'<\/span>]<\/span>\n}<\/span>\n\ndef<\/span> generate_http_headers<\/span>(<\/span>credential<\/span>):<\/span>\n    http_headers<\/span> =<\/span> {<\/span>\n        '<\/span>Cookie<\/span>'<\/span>:<\/span> '<\/span>BDUSS=<\/span>'<\/span> +<\/span> credential<\/span>[<\/span>\"<\/span>cookie_BDUSS<\/span>\"<\/span>],<\/span>\n        '<\/span>Cipher-Text<\/span>'<\/span>:<\/span> credential<\/span>[<\/span>\"<\/span>cipherText<\/span>\"<\/span>],<\/span>\n        '<\/span>Accept<\/span>'<\/span>:<\/span> '<\/span>application\/json, text\/plain, *\/*<\/span>'<\/span>,<\/span>\n        '<\/span>Accept-Encoding<\/span>'<\/span>:<\/span> '<\/span>gzip, deflate, br<\/span>'<\/span>,<\/span>\n        '<\/span>Accept-Language<\/span>'<\/span>:<\/span> '<\/span>zh-CN,zh;q=0.9<\/span>'<\/span>,<\/span>\n        '<\/span>Connection<\/span>'<\/span>:<\/span> '<\/span>keep-alive<\/span>'<\/span>,<\/span>\n        '<\/span>Referer<\/span>'<\/span>:<\/span> '<\/span>https:\/\/index.baidu.com\/v2\/main\/index.html<\/span>'<\/span>,<\/span>\n        '<\/span>Host<\/span>'<\/span>:<\/span> '<\/span>index.baidu.com<\/span>'<\/span>,<\/span>\n        '<\/span>User-Agent<\/span>'<\/span>:<\/span> '<\/span>Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.110 Safari\/537.3<\/span>'<\/span>\n    }<\/span>\n    return<\/span> http_headers<\/span>\n\n\ndef<\/span> calculate_yearly_averages<\/span>(<\/span>start_date<\/span>,<\/span> end_date<\/span>,<\/span> data_series<\/span>):<\/span>\n    # Convert the start and end dates to datetime objects\n<\/span>    start<\/span> =<\/span> datetime<\/span>.<\/span>strptime<\/span>(<\/span>start_date<\/span>,<\/span> '<\/span>%Y-%m-%d<\/span>'<\/span>)<\/span>\n    end<\/span> =<\/span> datetime<\/span>.<\/span>strptime<\/span>(<\/span>end_date<\/span>,<\/span> '<\/span>%Y-%m-%d<\/span>'<\/span>)<\/span>\n    days_span<\/span> =<\/span> (<\/span>end<\/span> -<\/span> start<\/span>).<\/span>days<\/span> +<\/span> 1<\/span>\n\n    # Split the data series into a list and replace empty strings with '0'\n<\/span>    data_points<\/span> =<\/span> data_series<\/span>.<\/span>split<\/span>(<\/span>'<\/span>,<\/span>'<\/span>)<\/span>\n    data_points<\/span> =<\/span> [<\/span>'<\/span>0<\/span>'<\/span> if<\/span> point<\/span> ==<\/span> ''<\/span> else<\/span> point<\/span> for<\/span> point<\/span> in<\/span> data_points<\/span>]<\/span>\n    data_points<\/span> =<\/span> np<\/span>.<\/span>array<\/span>(<\/span>data_points<\/span>,<\/span> dtype<\/span>=<\/span>float<\/span>)<\/span>\n\n    if<\/span> days_span<\/span> <=<\/span> 366<\/span>:<\/span>\n        dates<\/span> =<\/span> pd<\/span>.<\/span>date_range<\/span>(<\/span>start<\/span>,<\/span> periods<\/span>=<\/span>len<\/span>(<\/span>data_points<\/span>))<\/span>\n    else<\/span>:<\/span>\n        weeks_span<\/span> =<\/span> len<\/span>(<\/span>data_points<\/span>)<\/span>\n        dates<\/span> =<\/span> pd<\/span>.<\/span>date_range<\/span>(<\/span>start<\/span>,<\/span> periods<\/span>=<\/span>weeks_span<\/span>,<\/span> freq<\/span>=<\/span>'<\/span>W<\/span>'<\/span>)<\/span>\n\n    # Create a DataFrame with the dates and data points\n<\/span>    df<\/span> =<\/span> pd<\/span>.<\/span>DataFrame<\/span>({<\/span>'<\/span>Date<\/span>'<\/span>:<\/span> dates<\/span>,<\/span> '<\/span>Data<\/span>'<\/span>:<\/span> data_points<\/span>})<\/span>\n    df<\/span>.<\/span>set_index<\/span>(<\/span>'<\/span>Date<\/span>'<\/span>,<\/span> inplace<\/span>=<\/span>True<\/span>)<\/span>\n\n    # Calculate the yearly average\n<\/span>    yearly_averages<\/span> =<\/span> df<\/span>.<\/span>resample<\/span>(<\/span>'<\/span>YE<\/span>'<\/span>).<\/span>mean<\/span>().<\/span>reset_index<\/span>()<\/span>\n    yearly_averages<\/span>[<\/span>'<\/span>Year<\/span>'<\/span>]<\/span> =<\/span> yearly_averages<\/span>[<\/span>'<\/span>Date<\/span>'<\/span>].<\/span>dt<\/span>.<\/span>year<\/span>\n    yearly_averages<\/span>.<\/span>drop<\/span>(<\/span>'<\/span>Date<\/span>'<\/span>,<\/span> axis<\/span>=<\/span>1<\/span>,<\/span> inplace<\/span>=<\/span>True<\/span>)<\/span>\n    yearly_averages<\/span>.<\/span>rename<\/span>(<\/span>columns<\/span>=<\/span>{<\/span>'<\/span>Data<\/span>'<\/span>:<\/span> '<\/span>Average<\/span>'<\/span>},<\/span> inplace<\/span>=<\/span>True<\/span>)<\/span>\n    # Convert DataFrame to list of tuples (year, average)\n<\/span>    yearly_averages_list<\/span> =<\/span> list<\/span>(<\/span>yearly_averages<\/span>.<\/span>itertuples<\/span>(<\/span>index<\/span>=<\/span>False<\/span>,<\/span> name<\/span>=<\/span>None<\/span>))<\/span>\n    print<\/span>(<\/span>yearly_averages_list<\/span>)<\/span>\n\n    return<\/span> yearly_averages_list<\/span>\n\n\n# \u89e3\u5bc6\n<\/span>def<\/span> decrypt<\/span>(<\/span>ptbk<\/span>,<\/span> index_data<\/span>):<\/span>\n    n<\/span> =<\/span> len<\/span>(<\/span>ptbk<\/span>)<\/span> \/\/<\/span> 2<\/span>\n    a<\/span> =<\/span> dict<\/span>(<\/span>zip<\/span>(<\/span>ptbk<\/span>[:<\/span>n<\/span>],<\/span> ptbk<\/span>[<\/span>n<\/span>:]))<\/span>\n    return<\/span> \"\"<\/span>.<\/span>join<\/span>([<\/span>a<\/span>[<\/span>s<\/span>]<\/span> for<\/span> s<\/span> in<\/span> index_data<\/span>])<\/span>\n\n\ndef<\/span> keywords2json<\/span>(<\/span>keyword<\/span>):<\/span>\n    import<\/span> json<\/span>\n    converted_keywords<\/span> =<\/span> [[{<\/span>\"<\/span>name<\/span>\"<\/span>:<\/span> keyword<\/span>,<\/span> \"<\/span>wordType<\/span>\"<\/span>:<\/span> 1<\/span>}]]<\/span>\n    # Convert the list of lists of dictionaries into a JSON string\n<\/span>    json_string<\/span> =<\/span> json<\/span>.<\/span>dumps<\/span>(<\/span>converted_keywords<\/span>,<\/span> ensure_ascii<\/span>=<\/span>False<\/span>)<\/span>\n    print<\/span>(<\/span>json_string<\/span>)<\/span>\n    return<\/span> json_string<\/span>\n\n#\n# def namely(keywords):\n#     return '+'.join(keywords)\n<\/span>\n\ndef<\/span> crawl_request<\/span>(<\/span>keyword<\/span>,<\/span> startDate<\/span>,<\/span> endDate<\/span>,<\/span> regionCode<\/span>,<\/span> credential<\/span>,<\/span> expectedInterval<\/span>,<\/span> autoSave<\/span>,<\/span> regionName<\/span>,<\/span> data_combine<\/span>):<\/span>\n    print<\/span>(<\/span>'<\/span>\u6b63\u5728\u67e5\u8be2\uff1a<\/span>'<\/span>,<\/span> keyword<\/span>,<\/span> startDate<\/span>,<\/span> endDate<\/span>,<\/span> regionCode<\/span>)<\/span>\n    words<\/span> =<\/span> keywords2json<\/span>(<\/span>keyword<\/span>)<\/span>\n\n    # \u7b2c\u4e00\u7ea7\u4ee5\u9017\u53f7\u5206\u9694\uff0c\u7b2c\u4e8c\u7ea7\u4ee5\u52a0\u53f7\u5206\u9694\n<\/span>    testwordset<\/span> =<\/span> keyword<\/span>\n    max_retries<\/span> =<\/span> 3<\/span>  # \u6700\u5927\u91cd\u8bd5\u6b21\u6570\n<\/span>    retries<\/span> =<\/span> 0<\/span>  # \u5f53\u524d\u91cd\u8bd5\u6b21\u6570\n<\/span>\n    while<\/span> retries<\/span> <<\/span> max_retries<\/span>:<\/span>\n        try<\/span>:<\/span>\n            url<\/span> =<\/span> f<\/span>'<\/span>https:\/\/index.baidu.com\/api\/AddWordApi\/checkWordsExists?word=<\/span>{<\/span>testwordset<\/span>}<\/span>'<\/span>\n            rsp<\/span> =<\/span> requests<\/span>.<\/span>get<\/span>(<\/span>url<\/span>,<\/span> headers<\/span>=<\/span>generate_http_headers<\/span>(<\/span>credential<\/span>),<\/span> timeout<\/span>=<\/span>10<\/span>).<\/span>json<\/span>()<\/span>\n            # \u82e5data\u7684result\u4e0d\u4e3a\u7a7a\uff0c\u5219\u8bf4\u660e\u5173\u952e\u8bcd\u4e0d\u5b58\u5728\uff0c\u62a5\u9519\u5e76\u9000\u51fa\n<\/span>            if<\/span> rsp<\/span>[<\/span>'<\/span>data<\/span>'<\/span>][<\/span>'<\/span>result<\/span>'<\/span>]:<\/span>\n                print<\/span>(<\/span>f<\/span>'<\/span>{<\/span>testwordset<\/span>}<\/span>\u5173\u952e\u8bcd\u4e0d\u5b58\u5728\u6216\u7ec4\u5408\u91cc\u6709\u4e0d\u5b58\u5728\u7684\u5173\u952e\u8bcd\uff0c\u8bf7\u68c0\u67e5<\/span>'<\/span>)<\/span>\n                return<\/span> -<\/span>1<\/span>\n\n            url<\/span> =<\/span> f<\/span>'<\/span>http:\/\/index.baidu.com\/api\/SearchApi\/index?area=0&word=<\/span>{<\/span>words<\/span>}<\/span>&area=<\/span>{<\/span>regionCode<\/span>}<\/span>&startDate=<\/span>{<\/span>startDate<\/span>}<\/span>&endDate=<\/span>{<\/span>endDate<\/span>}<\/span>'<\/span>\n            rsp<\/span> =<\/span> requests<\/span>.<\/span>get<\/span>(<\/span>url<\/span>,<\/span> headers<\/span>=<\/span>generate_http_headers<\/span>(<\/span>credential<\/span>),<\/span> timeout<\/span>=<\/span>10<\/span>).<\/span>json<\/span>()<\/span>\n\n            # \u83b7\u53d6\u89e3\u5bc6\u79d8\u94a5\n<\/span>            data<\/span> =<\/span> rsp<\/span>[<\/span>'<\/span>data<\/span>'<\/span>][<\/span>'<\/span>userIndexes<\/span>'<\/span>]<\/span>\n            uniqid<\/span> =<\/span> rsp<\/span>[<\/span>'<\/span>data<\/span>'<\/span>][<\/span>'<\/span>uniqid<\/span>'<\/span>]<\/span>\n            url<\/span> =<\/span> f<\/span>'<\/span>https:\/\/index.baidu.com\/Interface\/ptbk?uniqid=<\/span>{<\/span>uniqid<\/span>}<\/span>'<\/span>\n            ptbk<\/span> =<\/span> requests<\/span>.<\/span>get<\/span>(<\/span>url<\/span>,<\/span> headers<\/span>=<\/span>generate_http_headers<\/span>(<\/span>credential<\/span>),<\/span> timeout<\/span>=<\/span>10<\/span>).<\/span>json<\/span>()[<\/span>'<\/span>data<\/span>'<\/span>]<\/span>\n\n            # \u6570\u636e\u89e3\u5bc6\n<\/span>            res<\/span> =<\/span> [<\/span>0<\/span> for<\/span> _<\/span> in<\/span> range<\/span>(<\/span>len<\/span>(<\/span>data<\/span>))]<\/span>\n            for<\/span> i<\/span> in<\/span> range<\/span>(<\/span>len<\/span>(<\/span>data<\/span>)):<\/span>\n                index_data<\/span> =<\/span> decrypt<\/span>(<\/span>ptbk<\/span>,<\/span> data<\/span>[<\/span>i<\/span>][<\/span>'<\/span>all<\/span>'<\/span>][<\/span>'<\/span>data<\/span>'<\/span>])<\/span>\n                yearly_averages<\/span> =<\/span> calculate_yearly_averages<\/span>(<\/span>startDate<\/span>,<\/span> endDate<\/span>,<\/span> index_data<\/span>)<\/span>\n                for<\/span> tuple_item<\/span> in<\/span> yearly_averages<\/span>:<\/span>\n                    index_d<\/span> =<\/span> round<\/span>(<\/span>tuple_item<\/span>[<\/span>0<\/span>],<\/span>2<\/span>)<\/span>\n                    year<\/span> =<\/span> tuple_item<\/span>[<\/span>1<\/span>]<\/span>\n                    if<\/span> year<\/span> ><\/span> 2022<\/span>:<\/span>\n                        continue<\/span>\n                    if<\/span> year<\/span> in<\/span> data_combine<\/span>:<\/span>\n                        data_combine<\/span>[<\/span>year<\/span>].<\/span>append<\/span>(<\/span>index_d<\/span>)<\/span>\n                    else<\/span>:<\/span>\n                        data_combine<\/span>[<\/span>year<\/span>]<\/span> =<\/span> [<\/span>year<\/span>,<\/span> regionName<\/span>,<\/span> index_d<\/span>]<\/span>\n            return<\/span> res<\/span>\n        except<\/span> Exception<\/span> as<\/span> e<\/span>:<\/span>\n            print<\/span>(<\/span>f<\/span>'<\/span>\u8bf7\u6c42\u5931\u8d25\uff0c\u9519\u8bef\u4fe1\u606f\uff1a<\/span>{<\/span>e<\/span>}<\/span>'<\/span>)<\/span>\n            retries<\/span> +=<\/span> 1<\/span>\n            print<\/span>(<\/span>f<\/span>'<\/span>\u91cd\u8bd5\u7b2c<\/span>{<\/span>retries<\/span>}<\/span>\u6b21...<\/span>'<\/span>)<\/span>\n            time<\/span>.<\/span>sleep<\/span>(<\/span>random<\/span>.<\/span>randint<\/span>(<\/span>1<\/span>,<\/span> 3<\/span>))<\/span>  # \u5728\u91cd\u8bd5\u524d\u7b49\u5f85\u4e00\u6bb5\u65f6\u95f4\n<\/span>    if<\/span> retries<\/span> ==<\/span> max_retries<\/span>:<\/span>\n        print<\/span>(<\/span>f<\/span>'<\/span>\u8bf7\u6c42\u5931\u8d25\u6b21\u6570\u8fc7\u591a\uff0c\u5df2\u8fbe\u5230\u6700\u5927\u91cd\u8bd5\u6b21\u6570<\/span>{<\/span>max_retries<\/span>}<\/span>\uff0c\u8df3\u8fc7\u5f53\u524d\u8fde\u63a5<\/span>'<\/span>)<\/span>\n        return<\/span> -<\/span>1<\/span>\n\n\n# regions = {}\n<\/span>provinces<\/span> =<\/span> {<\/span>\n            901<\/span>:<\/span> \"<\/span>\u5c71\u4e1c<\/span>\"<\/span>,<\/span>\n            902<\/span>:<\/span> \"<\/span>\u8d35\u5dde<\/span>\"<\/span>,<\/span>\n            903<\/span>:<\/span> \"<\/span>\u6c5f\u897f<\/span>\"<\/span>,<\/span>\n            904<\/span>:<\/span> \"<\/span>\u91cd\u5e86<\/span>\"<\/span>,<\/span>\n            905<\/span>:<\/span> \"<\/span>\u5185\u8499\u53e4<\/span>\"<\/span>,<\/span>\n            906<\/span>:<\/span> \"<\/span>\u6e56\u5317<\/span>\"<\/span>,<\/span>\n            907<\/span>:<\/span> \"<\/span>\u8fbd\u5b81<\/span>\"<\/span>,<\/span>\n            908<\/span>:<\/span> \"<\/span>\u6e56\u5357<\/span>\"<\/span>,<\/span>\n            909<\/span>:<\/span> \"<\/span>\u798f\u5efa<\/span>\"<\/span>,<\/span>\n            910<\/span>:<\/span> \"<\/span>\u4e0a\u6d77<\/span>\"<\/span>,<\/span>\n            911<\/span>:<\/span> \"<\/span>\u5317\u4eac<\/span>\"<\/span>,<\/span>\n            912<\/span>:<\/span> \"<\/span>\u5e7f\u897f<\/span>\"<\/span>,<\/span>\n            913<\/span>:<\/span> \"<\/span>\u5e7f\u4e1c<\/span>\"<\/span>,<\/span>\n            914<\/span>:<\/span> \"<\/span>\u56db\u5ddd<\/span>\"<\/span>,<\/span>\n            915<\/span>:<\/span> \"<\/span>\u4e91\u5357<\/span>\"<\/span>,<\/span>\n            916<\/span>:<\/span> \"<\/span>\u6c5f\u82cf<\/span>\"<\/span>,<\/span>\n            917<\/span>:<\/span> \"<\/span>\u6d59\u6c5f<\/span>\"<\/span>,<\/span>\n            918<\/span>:<\/span> \"<\/span>\u9752\u6d77<\/span>\"<\/span>,<\/span>\n            919<\/span>:<\/span> \"<\/span>\u5b81\u590f<\/span>\"<\/span>,<\/span>\n            920<\/span>:<\/span> \"<\/span>\u6cb3\u5317<\/span>\"<\/span>,<\/span>\n            921<\/span>:<\/span> \"<\/span>\u9ed1\u9f99\u6c5f<\/span>\"<\/span>,<\/span>\n            922<\/span>:<\/span> \"<\/span>\u5409\u6797<\/span>\"<\/span>,<\/span>\n            923<\/span>:<\/span> \"<\/span>\u5929\u6d25<\/span>\"<\/span>,<\/span>\n            924<\/span>:<\/span> \"<\/span>\u9655\u897f<\/span>\"<\/span>,<\/span>\n            925<\/span>:<\/span> \"<\/span>\u7518\u8083<\/span>\"<\/span>,<\/span>\n            926<\/span>:<\/span> \"<\/span>\u65b0\u7586<\/span>\"<\/span>,<\/span>\n            927<\/span>:<\/span> \"<\/span>\u6cb3\u5357<\/span>\"<\/span>,<\/span>\n            928<\/span>:<\/span> \"<\/span>\u5b89\u5fbd<\/span>\"<\/span>,<\/span>\n            929<\/span>:<\/span> \"<\/span>\u5c71\u897f<\/span>\"<\/span>,<\/span>\n            930<\/span>:<\/span> \"<\/span>\u6d77\u5357<\/span>\"<\/span>,<\/span>\n            931<\/span>:<\/span> \"<\/span>\u53f0\u6e7e<\/span>\"<\/span>,<\/span>\n            # 932: \"\u897f\u85cf\",\n<\/span>            933<\/span>:<\/span> \"<\/span>\u9999\u6e2f<\/span>\"<\/span>,<\/span>\n            934<\/span>:<\/span> \"<\/span>\u6fb3\u95e8<\/span>\"<\/span>\n        }<\/span>\n\nregions<\/span> =<\/span> provinces<\/span>\n\ndef<\/span> crawl<\/span>(<\/span>regionCode<\/span>,<\/span> credential<\/span>,<\/span> expectedInterval<\/span>,<\/span> autoSave<\/span>,<\/span> regionName<\/span>,<\/span> data_combine<\/span>):<\/span>\n    # \u83b7\u53d611\u5e74\u523022\u5e74\u7684\u6570\u636e\n<\/span>    startDate<\/span> =<\/span> '<\/span>2011-01-01<\/span>'<\/span>\n    endDate<\/span> =<\/span> '<\/span>2022-12-31<\/span>'<\/span>\n    # \u6e05\u6d17\u5173\u952e\u8bcd\n<\/span>    keywords<\/span> =<\/span> [<\/span>'<\/span>\u7b2c\u4e09\u65b9\u652f\u4ed8<\/span>'<\/span>,<\/span> '<\/span>\u5728\u7ebf\u652f\u4ed8<\/span>'<\/span>,<\/span> '<\/span>\u79fb\u52a8\u652f\u4ed8<\/span>'<\/span>,<\/span> '<\/span>\u7f51\u8d37<\/span>'<\/span>,<\/span> '<\/span>\u4e92\u8054\u7f51\u7406\u8d22<\/span>'<\/span>,<\/span> '<\/span>\u4e92\u8054\u7f51\u4fdd\u9669<\/span>'<\/span>,<\/span> '<\/span>\u5728\u7ebf\u7406\u8d22<\/span>'<\/span>,<\/span> '<\/span>\u7535\u5b50\u94f6\u884c<\/span>'<\/span>,<\/span> '<\/span>\u7f51\u94f6<\/span>'<\/span>,<\/span> '<\/span>\u5927\u6570\u636e<\/span>'<\/span>,<\/span> '<\/span>\u4e91\u8ba1\u7b97<\/span>'<\/span>,<\/span> '<\/span>\u4eba\u5de5\u667a\u80fd<\/span>'<\/span>,<\/span> '<\/span>\u533a\u5757\u94fe<\/span>'<\/span>,<\/span> '<\/span>\u751f\u7269\u8bc6\u522b<\/span>'<\/span>]<\/span>\n\n    # res = {regionCode: []}\n<\/span>    for<\/span> keyword<\/span> in<\/span> keywords<\/span>:<\/span>\n        if<\/span> regionCode<\/span> !=<\/span> '<\/span>999<\/span>'<\/span>:<\/span>\n            try<\/span>:<\/span>\n                crawl_request<\/span>(<\/span>keyword<\/span>,<\/span> startDate<\/span>,<\/span> endDate<\/span>,<\/span> regionCode<\/span>,<\/span> credential<\/span>,<\/span> expectedInterval<\/span>,<\/span> autoSave<\/span>,<\/span> regionName<\/span>,<\/span> data_combine<\/span>)<\/span>\n            except<\/span>:<\/span>\n                print<\/span>(<\/span>format_exc<\/span>())<\/span>\n            # res[regionCode].extend\n<\/span>            # \u6bcf\u6b21\u67e5\u8be2\u540e\u4f11\u606f\u4e00\u5230\u4e94\u79d2\uff0c\u5b9e\u9645\u4e0a\u5728\u8d26\u53f7\u5f88\u591a\u7684\u60c5\u51b5\u4e0b\uff0c\u8fd9\u4e2a\u65f6\u95f4\u53ef\u4ee5\u7f29\u77ed\n<\/span>            time<\/span>.<\/span>sleep<\/span>(<\/span>expectedInterval<\/span> \/<\/span> 1000<\/span> +<\/span> random<\/span>.<\/span>randint<\/span>(<\/span>1<\/span>,<\/span> 3<\/span>)<\/span> \/<\/span> 2<\/span>)<\/span>\nif<\/span> __name__<\/span> ==<\/span> '<\/span>__main__<\/span>'<\/span>:<\/span>\n    import<\/span> csv<\/span>\n    # # \u6e05\u6d17\u5173\u952e\u8bcd\n<\/span>    # titles = ['\u5e74\u4efd', '\u533a\u57df', '\u7b2c\u4e09\u65b9\u652f\u4ed8', '\u5728\u7ebf\u652f\u4ed8', '\u79fb\u52a8\u652f\u4ed8', '\u7f51\u8d37', '\u4e92\u8054\u7f51\u7406\u8d22', '\u4e92\u8054\u7f51\u4fdd\u9669', '\u5728\u7ebf\u7406\u8d22', '\u7535\u5b50\u94f6\u884c', '\u7f51\u94f6',\n<\/span>    #             '\u5927\u6570\u636e', '\u4e91\u8ba1\u7b97', '\u4eba\u5de5\u667a\u80fd',\n<\/span>    #             '\u533a\u5757\u94fe', '\u751f\u7269\u8bc6\u522b']\n<\/span>    # with open('combine_backup.csv', 'a', encoding='utf-8-sig', newline=\"\") as csvfile:\n<\/span>    #     writer = csv.writer(csvfile)\n<\/span>    #     writer.writerow(titles)\n<\/span>\n    for<\/span> regionCode<\/span> in<\/span> regions<\/span>:<\/span>\n        # regionCode = 928\n<\/span>        # regionName=\"\u5b89\u5fbd\"\n<\/span>        regionName<\/span> =<\/span> regions<\/span>[<\/span>regionCode<\/span>]<\/span>\n        data_combine<\/span> =<\/span> {}<\/span>\n\n\n        crawl<\/span>(<\/span>regionCode<\/span>,<\/span> credential<\/span>,<\/span> 10<\/span>,<\/span> True<\/span>,<\/span> regionName<\/span>,<\/span> data_combine<\/span>)<\/span>\n        data_list<\/span> =<\/span> []<\/span>\n        for<\/span> i<\/span> in<\/span> data_combine<\/span>:<\/span>\n                data_list<\/span>.<\/span>append<\/span>(<\/span>data_combine<\/span>[<\/span>i<\/span>])<\/span>\n        with<\/span> open<\/span>(<\/span>'<\/span>combine_backup.csv<\/span>'<\/span>,<\/span> '<\/span>a<\/span>'<\/span>,<\/span> encoding<\/span>=<\/span>'<\/span>utf-8-sig<\/span>'<\/span>,<\/span> newline<\/span>=<\/span>''<\/span>)<\/span> as<\/span> csvfile<\/span>:<\/span>\n            writer<\/span> =<\/span> csv<\/span>.<\/span>writer<\/span>(<\/span>csvfile<\/span>)<\/span>\n            writer<\/span>.<\/span>writerows<\/span>(<\/span>data_list<\/span>)<\/span>\n\n<\/code><\/pre>\n<\/div>\n","protected":false},"excerpt":{"rendered":"
“”” \u767e\u5ea6\u6307\u6570\u722c\u866b 2025\u5e743\u6708 “”” import json from traceback import format_exc import time import requests from datetime import datetime, timedelta import numpy as np import pandas as pd import random from requests.exceptions import RequestException cookies_dict = { “BAIDUID_BFESS”: “03C87F7E8DAB230EF3CF68E2E4CCB7AC:FG=1”, “Hm_lvt_d101ea4d2a5c67dab98251f0b5de24dc”: “1740900295”, “HMACCOUNT”: “70309D756AB7564A”, “ppfuid”: “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”, “BDUSS”: “ndtMC1BVXpUdFF6Z3NGTHVCZlRmTXJVSXN3WUZXSkpTUXg5NU1iZGRCNlJsZXRuSVFBQUFBJCQAAAAAAAAAAAEAAAAK5OqRyqLH6cPOAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJEIxGeRCMRnV”, “SIGNIN_UC”: “70a2711cf1d3d9b1a82d2f87d633bd8a04909129477oUCDVgDuFIWQq0I5Qh%2BRYVI211tn6l6RtVzEcHQHKEeV3UqjZrdEN2J58qMq3yI6SH4Pf5yaO3wsYp7rDl7owf8Vxw8nV7J6HDde92bSfNLB%2BLYSDn8mcJUeJZ9DvByeHYEh5HZIEmBqjEW9Kp1nhY39kd0%2FMKxlLMEZywpREcfeqkBuNDImGT1swOphjUr0m7yoFRuoRONhZO0DhIUp8qMp%2BI%2BGZ9URB2%2FDv3g%2FwZ0nXnjrScjtkdIga7hBOF4Os4RsqXflHU7INYd10uoQ2Ecn99qPwcD5%2BuKJ7%2BtRR94%3D59476045678983651647832308115528”, “__cas__rn__”: “490912947”, “__cas__st__212”: “eb761014eef2d40b7c2bad261c6098e983f5ecc9a335b83a0f261f17f01cab78142cd91d640c0bff5197630b”, “__cas__id__212”: “40927145”, “CPTK_212”: …<\/p>\n","protected":false},"author":2,"featured_media":100284,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"","fifu_image_alt":"","footnotes":""},"categories":[339],"tags":[],"class_list":["post-100283","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-dev"],"_links":{"self":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/posts\/100283","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/comments?post=100283"}],"version-history":[{"count":0,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/posts\/100283\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/media\/100284"}],"wp:attachment":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/media?parent=100283"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/categories?post=100283"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/tags?post=100283"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}