{}
'.format(status)) 292 | 293 | -------------------------------------------------------------------------------- /Webdriver/chromedriver.exe: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AlcatrazChris/AutoProductEvalution/e8ac3c024d234dd2f2406b3e23da3dd6fa545c0a/Webdriver/chromedriver.exe -------------------------------------------------------------------------------- /Webdriver/msedgedriver.exe: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AlcatrazChris/AutoProductEvalution/e8ac3c024d234dd2f2406b3e23da3dd6fa545c0a/Webdriver/msedgedriver.exe -------------------------------------------------------------------------------- /data/JDdata1688264511.5914738.csv: -------------------------------------------------------------------------------- 1 | Unnamed: 0,ID,商品,价格,店铺,店铺地址,购买人数,发货地,详情页,图片,店铺信息,score,score_normalized 2 | 0,100030264685,浪莎丝袜女超薄性感黑丝显瘦美腿袜纯欲风长筒打底连裤袜 2条装,19.9,浪莎(LangSha)内衣京东自营专卖店,//mall.jd.com/index-1000285849.html?from=pc,,江苏,//item.jd.com/100030264685.html,//img10.360buyimg.com/n7/jfs/t1/60090/22/20218/361154/62d75ae4E075ab990/323ef90085c2f60c.jpg,"{'标签': '自营', '店铺信誉': '95'}",167,0.7766497461928934 3 | 1,2357395,浪莎丝袜女超薄款黑丝6双连裤袜性感长筒黑色春夏打底袜 黑色6双 均码,39.0,浪莎内衣京东自营官方旗舰店,//mall.jd.com/index-1000081341.html?from=pc,,江苏,//item.jd.com/2357395.html,//img10.360buyimg.com/n7/jfs/t1/79223/10/23952/74303/63c768baF423e3814/78537a8e9560ad94.jpg,"{'标签': '自营', '店铺信誉': '97'}",187,0.8781725888324873 4 | 2,10045672966898,涓涓细语黑丝袜女夏季黑丝网红ins潮春秋肉色性感连裤袜jk学生打底袜 黑色1条-【丝袜】 适合75-125斤【高品质贴身】,7.99,涓涓细语宏佳专卖店,//mall.jd.com/index-11819144.html?from=pc,,江苏,//item.jd.com/10045672966898.html,//img13.360buyimg.com/n7/jfs/t1/113724/37/25478/108612/6221e964E7644c1f4/4f87a52629b6a460.jpg,"{'标签': '无', '店铺信誉': '90'}",162,0.751269035532995 5 | 3,6482440,浪莎丝袜女性感开档免脱裤袜超薄情调丝袜连裤袜均码 黑肤各1双,29.9,浪莎京东自营官方旗舰店,//mall.jd.com/index-1000072731.html?from=pc,,江苏,//item.jd.com/6482440.html,//img10.360buyimg.com/n7/jfs/t1/16160/24/18099/167011/62c638b4E9fe6f714/08d03e74a23226a3.jpg,"{'标签': '自营', '店铺信誉': '97'}",207,0.9796954314720813 6 | 4,100032996566,俞兆林3双超薄手撕一次性丝袜女黑色易撕情调灰连裤袜黑丝情趣性感透明 【性感黑】可撕情调丝袜3双 均码,19.9,俞兆林京东自营旗舰店,//mall.jd.com/index-1000374541.html?from=pc,,江苏,//item.jd.com/100032996566.html,//img11.360buyimg.com/n7/jfs/t1/165049/17/27570/404715/6200dc87E461d51fd/5b651669a3ad96dd.jpg,"{'标签': '自营', '店铺信誉': '96'}",200,0.9441624365482234 7 | 5,10033186163119,骁芬暗黑英文B字母黑丝袜ins网红jk性感网袜打底裤袜防勾丝薄款显瘦 黑色巴黎B字母(薄款防勾丝)产品质量保证7天无理由退换货提供保障,9.8,骁芬旗舰店,//mall.jd.com/index-11354098.html?from=pc,,江苏,//item.jd.com/10033186163119.html,//img14.360buyimg.com/n7/jfs/t1/180256/37/11526/157607/60dc20e3E995a0661/1c2c889dff8971b2.jpg,"{'标签': '无', '店铺信誉': '93'}",169,0.7868020304568528 8 | 6,10068563719446,浪莎丝袜女超薄6双春夏款性感黑丝防勾丝高透性显瘦美腿打底裤袜 肤色6双 均码,39.0,浪莎旗舰店,//mall.jd.com/index-597286.html?from=pc,,江苏,//item.jd.com/10068563719446.html,//img11.360buyimg.com/n7/jfs/t1/118169/16/31957/59461/63e4adf8F5e29a87d/3d2e67f03220f202.jpg,"{'标签': '无', '店铺信誉': '10'}",30,0.08121827411167512 9 | 7,10052955024659,哥哥撕开裆丝袜黑丝女夏易插长筒袜蕾丝吊带性感情调制服jk过膝袜 蝴蝶结纯黑 均码(隐私发货),8.0,右爱内衣专营店,//mall.jd.com/index-996237.html?from=pc,,江苏,//item.jd.com/10052955024659.html,//img14.360buyimg.com/n7/jfs/t1/219189/4/19377/412391/628d1270E3c343c93/5645c5c2f604cb15.jpg,"{'标签': '无', '店铺信誉': '93'}",179,0.8375634517766497 10 | 8,10033208128070,骁芬 性感吊带丝袜女免脱一体式连裤袜开裆蕾丝过膝丝袜 黑色一体 均码产品质量保证7天无理由退换货提供保障,16.9,骁芬旗舰店,//mall.jd.com/index-11354098.html?from=pc,,江苏,//item.jd.com/10033208128070.html,//img10.360buyimg.com/n7/jfs/t1/203830/25/24710/147793/61b9bd64E2cd62c43/9feac46f5ab2d7e0.jpg,"{'标签': '无', '店铺信誉': '95'}",161,0.7461928934010152 11 | 9,10033321996177,骁芬jk黑丝袜女薄款性感夏季网红流行ins女学生春夏季显瘦防勾丝 JK黑色产品质量保证7天无理由退换货提供保障,9.8,骁芬旗舰店,//mall.jd.com/index-11354098.html?from=pc,,江苏,//item.jd.com/10033321996177.html,//img12.360buyimg.com/n7/jfs/t1/194075/2/11170/171756/60dfd333E7dce435b/4bb2927f1906f822.jpg,"{'标签': '无', '店铺信誉': '91'}",179,0.8375634517766497 12 | 10,100031440326,俞兆林2双黑色丝袜女ins春夏光腿神器连裤袜超薄性感JK黑丝女士长筒打底裤袜薄款 【性感黑】2双 均码,19.9,俞兆林京东自营旗舰店,//mall.jd.com/index-1000374541.html?from=pc,,江苏,//item.jd.com/100031440326.html,//img11.360buyimg.com/n7/jfs/t1/166834/37/22304/136098/61c30278E8402cccc/4a08ea24569ad41f.jpg,"{'标签': '自营', '店铺信誉': '93'}",211,1.0 13 | 11,10033496952379,骁芬内衣丝袜可撕免脱开档性感黑色连裤袜开档好撕黑丝打底袜 黑色 均码 (精装)产品质量保证7天无理由退换货提供保障,8.5,骁芬旗舰店,//mall.jd.com/index-11354098.html?from=pc,,江苏,//item.jd.com/10033496952379.html,//img14.360buyimg.com/n7/jfs/t1/192175/10/12048/135859/60e45ba8E786f5c13/68186891dc1c5847.jpg,"{'标签': '无', '店铺信誉': '93'}",187,0.8781725888324873 14 | 12,100018246849,浪莎字母丝袜女夏季超薄性感黑丝袜渔网情趣美腿长筒打底连裤袜 4条装,39.9,浪莎(LangSha)内衣京东自营专卖店,//mall.jd.com/index-1000285849.html?from=pc,,江苏,//item.jd.com/100018246849.html,//img14.360buyimg.com/n7/jfs/t1/116877/4/21681/93250/623005b5Efd93cc98/d51423c9975710b1.jpg,"{'标签': '自营', '店铺信誉': '13'}",69,0.27918781725888325 15 | 13,100053432287,俞兆林丝袜女性感高筒包芯丝袜子女不易勾丝长筒黑丝肉色防滑过膝丝袜,9.9,俞兆林内衣京东自营专区,//mall.jd.com/index-1000414601.html?from=pc,,江苏,//item.jd.com/100053432287.html,//img12.360buyimg.com/n7/jfs/t1/204582/36/36428/170407/64917848F66fd26d4/de320dd51c314bb9.jpg,"{'标签': '自营', '店铺信誉': '92'}",123,0.5532994923857868 16 | 14,10068239957922,伦洛弗丝袜黑色性感开档免脱吊带丝袜撞色假内裤套装连裤袜 黑色 均码(80-130斤),13.9,伦洛弗正通(诸暨)专卖店,//mall.jd.com/index-677143.html?from=pc,,江苏,//item.jd.com/10068239957922.html,//img12.360buyimg.com/n7/jfs/t1/208990/3/29407/72921/63dd03cbFc3710cdb/c1ad2c96a6b3378f.jpg,"{'标签': '无', '店铺信誉': '92'}",83,0.350253807106599 17 | 15,4734745,浪莎丝袜女6双春夏超薄连裤袜美腿外穿黑肉色女士长筒打底袜薄款显瘦光腿丝袜 黑色6双 均码618年中盛典开启!5月24-28号跨店3件7折!万千好物等你来挑!点击抢购~,39.0,浪莎京东自营官方旗舰店,//mall.jd.com/index-1000072731.html?from=pc,,江苏,//item.jd.com/4734745.html,//img10.360buyimg.com/n7/jfs/t1/127477/16/22299/300447/6285f43dEb8b69537/7e43c146638b9d56.jpg,"{'标签': '自营', '店铺信誉': '97'}",163,0.7563451776649747 18 | 16,100011523772,浪莎丝袜女硅胶防滑性感黑丝过膝长筒袜高筒大腿袜2双 黑1白1 均码,29.9,浪莎内衣京东自营官方旗舰店,//mall.jd.com/index-1000081341.html?from=pc,,江苏,//item.jd.com/100011523772.html,//img12.360buyimg.com/n7/jfs/t1/91437/38/32794/124569/63c609a2F4eaaafda/8d1af41eeb19a569.jpg,"{'标签': '自营', '店铺信誉': '96'}",170,0.7918781725888325 19 | 17,10068563719448,浪莎丝袜女超薄6双春夏款性感黑丝防勾丝高透性显瘦美腿打底裤袜 黑色6双 均码超薄款性感显瘦美腿款光腿神器防勾丝连体裤丝袜,39.0,浪莎旗舰店,//mall.jd.com/index-597286.html?from=pc,,江苏,//item.jd.com/10068563719448.html,//img13.360buyimg.com/n7/jfs/t1/118169/16/31957/59461/63e4adf8F5e29a87d/3d2e67f03220f202.jpg,"{'标签': '无', '店铺信誉': '96'}",116,0.5177664974619289 20 | 18,10027267698134,浪莎大码丝袜女夏季款胖mm200斤加肥高腰弹力大防勾丝连裤袜高透黑丝双加裆--黑2肤2浅咖1 加大码双加裆连裤袜【5条装】,99.0,浪莎闪闪专卖店,//mall.jd.com/index-862944.html?from=pc,,江苏,//item.jd.com/10027267698134.html,//img14.360buyimg.com/n7/jfs/t1/166600/28/9591/83162/6041f518Ebad11059/518e6b60de0bc179.jpg,"{'标签': '无', '店铺信誉': '14'}",14,0.0 21 | 19,100037404678,涞觅润丝【0.01】开裆丝袜丝滑超薄免脱连裤袜透明性感女袜 黑色 M码,33.12,涞觅润丝(Limerence M)京东自营旗舰店,//mall.jd.com/index-1000415662.html?from=pc,,江苏,//item.jd.com/100037404678.html,//img13.360buyimg.com/n7/jfs/t1/200068/32/21980/246643/6257c74aEf877ca04/ea13f4c712353383.jpg,"{'标签': '自营', '店铺信誉': '96'}",190,0.8934010152284264 22 | 20,10050408591856,骁芬 性感白丝开裆免脱连裤袜长筒黑色丝袜 黑色开档 (精装)均码产品质量保证7天无理由退换货提供保障,9.9,骁芬旗舰店,//mall.jd.com/index-11354098.html?from=pc,,江苏,//item.jd.com/10050408591856.html,//img11.360buyimg.com/n7/jfs/t1/164056/19/22514/176416/626662dbE6e561725/fcb3991fada52aa1.jpg,"{'标签': '无', '店铺信誉': '94'}",140,0.6395939086294417 23 | 21,100028213817,浪莎丝袜女2双超薄纯欲长筒过膝丝袜女长筒袜高筒性感大腿袜红边黑丝,29.9,浪莎京东自营官方旗舰店,//mall.jd.com/index-1000072731.html?from=pc,,江苏,//item.jd.com/100028213817.html,//img12.360buyimg.com/n7/jfs/t1/166766/25/26376/246885/63bbb3f5Fa2932b81/7428fd2f0e28eaeb.jpg,"{'标签': '自营', '店铺信誉': '97'}",187,0.8781725888324873 24 | 22,10055805393738,爱心东东莱惑三双装一次性手撕丝袜超薄性感透明易撕烂黑丝破洞可撕火辣连裤袜 性感撕袜(黑色)三双装 闭档款(均码)京仓直发隐私发出,19.0,莱惑旗舰店,//mall.jd.com/index-12208314.html?from=pc,,江苏,//item.jd.com/10055805393738.html,//img13.360buyimg.com/n7/jfs/t1/198490/24/24764/146292/62c3ed01E763cc97d/b83095476f5fde9b.jpg,"{'标签': '无', '店铺信誉': '98'}",159,0.7360406091370558 25 | 23,100041935356,雪茜曼吊带丝袜性感一体式过膝袜黑色纯欲腿精超薄黑丝长筒蕾丝袜 黑色,29.9,雪茜曼(XUEXIMAN)内衣官方京东自营旗舰店,//mall.jd.com/index-1000443763.html?from=pc,,江苏,//item.jd.com/100041935356.html,//img11.360buyimg.com/n7/jfs/t1/123347/17/29856/92736/63b77f7dF047a151a/d5d03b9d92c1a90b.jpg,"{'标签': '自营', '店铺信誉': '94'}",136,0.6192893401015228 26 | 24,10069943288844,馋东馋西LL女薄款连裤袜春秋菠萝防勾超薄长筒光腿黑丝肉色神器性感LL8 黑色6 【加裆防】(适合80-130斤),299.0,南迁服饰专营店,//mall.jd.com/index-804892.html?from=pc,,江苏,//item.jd.com/10069943288844.html,//img14.360buyimg.com/n7/jfs/t1/167624/40/34708/95547/640550acFff0d3967/ba94845c47cfc5ae.jpg,"{'标签': '无', '店铺信誉': ''}",50,0.18274111675126903 27 | 25,100019679118,猫人丝袜女高透0d黑丝超薄光腿神器夏季肉色连裤袜性感渔网袜3双装猫人精品内衣,正品有保证,万千新品等你来挑!产品优惠多多,发货迅速,快来选购吧~查看,39.9,猫人京东自营旗舰店,//mall.jd.com/index-1000081910.html?from=pc,,江苏,//item.jd.com/100019679118.html,//img13.360buyimg.com/n7/jfs/t1/49074/30/21864/227869/64240fc6Fedeedbf3/20ccd329146ebfbf.jpg,"{'标签': '自营', '店铺信誉': '93'}",179,0.8375634517766497 28 | 26,10060277993173,美奈貂性感黑丝吊带袜红边开裆免脱薄款丝袜女连裤袜子 黑纹黑丝开档款均码(80到150斤)时尚开档性感,保密包装,13.5,美奈貂旗舰店,//mall.jd.com/index-11811307.html?from=pc,,江苏,//item.jd.com/10060277993173.html,//img13.360buyimg.com/n7/jfs/t1/198109/24/27119/48394/631c01d9E2e66de28/b3142569f624b7c7.jpg,"{'标签': '无', '店铺信誉': '92'}",114,0.5076142131979695 29 | 27,100042153916,FitonTon吊带丝袜女性感一体黑丝情调开档长筒丝袜SW0001 黑色 均码,29.9,FitonTon京东自营旗舰店,//mall.jd.com/index-1000366502.html?from=pc,,江苏,//item.jd.com/100042153916.html,//img11.360buyimg.com/n7/jfs/t1/209462/8/29168/91229/63bf77d3Fe6cf728d/83ac50a5910241ea.jpg,"{'标签': '自营', '店铺信誉': '91'}",123,0.5532994923857868 30 | 28,100041397366,俞兆林性感情趣开裆丝袜薄款女士超薄连裤性感免脱一体连体黑丝可撕,19.9,俞兆林京东自营旗舰店,//mall.jd.com/index-1000374541.html?from=pc,,江苏,//item.jd.com/100041397366.html,//img11.360buyimg.com/n7/jfs/t1/58425/18/22898/50896/63a40081E5440d133/541c60f29b1fc40f.jpg,"{'标签': '自营', '店铺信誉': '98'}",156,0.7208121827411168 31 | 29,100019519527,浪莎2条装吊带黑丝袜女性感情趣免脱长筒过膝袜蕾丝花边美腿裤袜女 黑1白1+内裤 均码,49.0,浪莎(LangSha)内衣京东自营专卖店,//mall.jd.com/index-1000285849.html?from=pc,,江苏,//item.jd.com/100019519527.html,//img12.360buyimg.com/n7/jfs/t1/207004/28/19350/335841/623ec08aEe2c4b46a/2c45ec6c1a55bac2.jpg,"{'标签': '自营', '店铺信誉': '93'}",203,0.9593908629441624 32 | -------------------------------------------------------------------------------- /data/JDdata1688264584.7149756.csv: -------------------------------------------------------------------------------- 1 | Unnamed: 0,ID,商品,价格,店铺,店铺地址,购买人数,发货地,详情页,图片,店铺信息,score,score_normalized 2 | 0,10044456688314,TOMMY HILFIGER女装潮流时髦签名字体刺绣LOGO高腰牛仔背带裤DW0DW12381 牛仔蓝1AB L,1251.0,TommyHilfiger官方旗舰店,//mall.jd.com/index-44241.html?from=pc,,江苏,//item.jd.com/10044456688314.html,//img14.360buyimg.com/n7/jfs/t1/137453/16/37731/245606/649e7b39F3b821949/bb6d2f2214f5d14c.jpg,"{'标签': '无', '店铺信誉': '13'}",13,0.0 3 | 1,10055368660713,岚烨设计感水洗贴标牛仔背带裤女网红款炸街减龄美式宽松阔腿拖地长裤 牛仔背带裤M(110-125)加购有惊喜!加购有惊喜!!重要的事情说三遍!加购有惊喜!!!关注店铺领取优惠加购有惊喜!!!点击关注店铺领取优惠,92.0,岚烨旗舰店,//mall.jd.com/index-688820.html?from=pc,,江苏,//item.jd.com/10055368660713.html,//img13.360buyimg.com/n7/jfs/t1/15298/8/17839/203344/62bc3084Eea7eefc3/2842bbc2cefd8edf.jpg,"{'标签': '无', '店铺信誉': '99'}",123,0.7236842105263158 4 | 2,10051790374320,七小铺潮牌清纯甜美牛仔背带裤套装女2023年新款夏季盐系网红背带裙两件 蓝色 均码【建议85-155斤】潮牌女装限时限量折扣惊喜特惠,春夏上新多买多实惠!支持7天无理由退货!点击查看有惊喜!!点击查看有惊喜,219.0,七小铺旗舰店,//mall.jd.com/index-11574928.html?from=pc,,江苏,//item.jd.com/10051790374320.html,//img10.360buyimg.com/n7/jfs/t1/56029/1/18520/306999/6279e155E36ce682a/f40a25dfd5f250c7.jpg,"{'标签': '无', '店铺信誉': '96'}",111,0.6447368421052632 5 | 3,53531219728,MELROSEMOOD牛仔背带裤女宽松阔腿裤女装新款显瘦显高直筒拖地背带牛仔裤子 蓝色 M【背带牛仔裤】【关注店铺领5元红包】,158.0,MELROSEMOOD服饰官方旗舰店,//mall.jd.com/index-712994.html?from=pc,,江苏,//item.jd.com/53531219728.html,//img13.360buyimg.com/n7/jfs/t1/44003/24/10368/658985/5d3db4ccE80f4929e/a855e198207eead3.jpg,"{'标签': '无', '店铺信誉': '98'}",140,0.8355263157894737 6 | 4,10057186449307,马登工装 复古卡其做旧甲板背带裤直筒宽松休闲连体长裤子男潮 浅卡其(宽松版型) L,179.9,马登男装旗舰店,//mall.jd.com/index-929180.html?from=pc,,江苏,//item.jd.com/10057186449307.html,//img12.360buyimg.com/n7/jfs/t1/218950/9/30167/83219/649ae338F832ae103/2c538eb895775a4a.jpg,"{'标签': '无', '店铺信誉': '100'}",105,0.6052631578947368 7 | 5,10048946858708,爱心东东古娅妍夏季套装日系学院风宽松显瘦牛仔背带裤少女学生粉色衬衫 白色背带裤【版】 M新品上架,限时低价促销!!!关注店铺加入购物车下单优先发货【支持7天无理由退换】,59.0,古娅妍女装旗舰店,//mall.jd.com/index-11894520.html?from=pc,,江苏,//item.jd.com/10048946858708.html,//img13.360buyimg.com/n7/jfs/t1/222665/9/15321/153906/62545991Eaab9f119/24a03329c9eb6650.jpg,"{'标签': '无', '店铺信誉': '91'}",100,0.5723684210526315 8 | 6,10077002329089,Otto ortee轻奢潮流新款洋气减龄设计感牛仔背带裤女夏季宽松显瘦遮肉短裤小 蓝色背带短裤 2XL,298.0,Otto ortee女装旗舰店,//mall.jd.com/index-12778796.html?from=pc,,江苏,//item.jd.com/10077002329089.html,//img14.360buyimg.com/n7/jfs/t1/128840/33/37469/235387/6474c19aF5c73b222/dcec07aa36596322.jpg,"{'标签': '无', '店铺信誉': ''}",50,0.24342105263157895 9 | 7,10070912822399,EDUX阔腿牛仔背带裤学院风女装裤子夏季2023款宽松设计感五分短裤 深蓝色 L,42.0,EDUX旗舰店,//mall.jd.com/index-12536893.html?from=pc,,江苏,//item.jd.com/10070912822399.html,//img14.360buyimg.com/n7/jfs/t1/62459/16/26553/169661/6461cb97Fc4b8e21d/90cf84d42d5cf5d2.jpg,"{'标签': '无', '店铺信誉': '100'}",100,0.5723684210526315 10 | 8,10074892933106,娇朵娅美式复古粉色牛仔背带裤女夏季新款宽松小众设计感直筒拖地裤玫粉色 M,92.0,娇朵娅女装旗舰店,//mall.jd.com/index-11656207.html?from=pc,,江苏,//item.jd.com/10074892933106.html,//img11.360buyimg.com/n7/jfs/t1/166507/40/37299/82666/6454ffd8F5b709858/ad52d21a548808f1.jpg,"{'标签': '无', '店铺信誉': '100'}",100,0.5723684210526315 11 | 9,10074250021021,FOURDATRY牛仔背带短裤女2023新款夏季显瘦修身短裤设计感减龄宽松阔腿裤子 深蓝色 M,49.9,FOURDATRY女装官方旗舰店,//mall.jd.com/index-12687946.html?from=pc,,江苏,//item.jd.com/10074250021021.html,//img11.360buyimg.com/n7/jfs/t1/108472/39/36543/60700/645c6b8fF504c783d/c833d297d6c1ec44.jpg,"{'标签': '无', '店铺信誉': '100'}",100,0.5723684210526315 12 | 10,10063701375632,郎捷凯坤坤格子背带裤男鸡你太美休闲长裤男ikun打篮球吊带裤坤坤同款背带裤XL质量好,优惠多,下单随机赠送小礼品点击领取,149.0,郎捷凯服饰旗舰店,//mall.jd.com/index-10177687.html?from=pc,,江苏,//item.jd.com/10063701375632.html,//img12.360buyimg.com/n7/jfs/t1/104453/8/34212/37865/6353ae35E813a94a4/749f2f1be178f0f6.jpg,"{'标签': '无', '店铺信誉': '95'}",95,0.5394736842105263 13 | 11,10069521339545,三彩2023春季新款纯棉减龄牛仔裤长裤背带裤宽松显瘦学院时尚女 奶白 155/64A/S1件9折3件8折叠满300-50,低至63折!折扣专区叠券1件33折起!活动仅限7.1-7.10点击,198.0,三彩女装旗舰店,//mall.jd.com/index-44033.html?from=pc,,江苏,//item.jd.com/10069521339545.html,//img10.360buyimg.com/n7/jfs/t1/148413/11/37030/151808/649f0157F8c0eaac0/59fae3cdddcd930f.jpg,"{'标签': '无', '店铺信誉': '100'}",100,0.5723684210526315 14 | 12,10077002206617,Otto ortee轻奢潮流盐系牛仔背带裤女春夏复古童趣减龄小个子宽松潮牌显瘦阔 蓝色背带裤L,288.0,Otto ortee女装旗舰店,//mall.jd.com/index-12778796.html?from=pc,,江苏,//item.jd.com/10077002206617.html,//img12.360buyimg.com/n7/jfs/t1/219098/32/30895/120696/6474c0c3F7fcbd745/c3ef979ef805e807.jpg,"{'标签': '无', '店铺信誉': ''}",50,0.24342105263157895 15 | 13,10069696709925,"元乐申小个子桔梗背带裤女夏季洋气减龄直筒牛仔裤高腰可盐可甜阔腿裤子 高质量黑色(小个子版) M (建议90-斤)新品冲量,低价促销!关注店铺加入购物车下单优先发货【支持7天无理由退换】",49.1,元乐申旗舰店,//mall.jd.com/index-11482847.html?from=pc,,江苏,//item.jd.com/10069696709925.html,//img10.360buyimg.com/n7/jfs/t1/182419/28/33351/62164/63fba3f0F2329a017/e8a44c459bb3ad6c.jpg,"{'标签': '无', '店铺信誉': '100'}",100,0.5723684210526315 16 | 14,10072878288718,对白工装风天丝背带裤套装女2023夏新款短袖T恤休闲束脚裤两件套 焦糖咖 M,499.0,对白旗舰店,//mall.jd.com/index-658534.html?from=pc,,江苏,//item.jd.com/10072878288718.html,//img13.360buyimg.com/n7/jfs/t1/145986/28/37808/54725/649c0af5F0b1a0817/45e22b94e02bbcbc.jpg,"{'标签': '无', '店铺信誉': '100'}",100,0.5723684210526315 17 | 15,10074266224311,诗凡黎('SEIFINI)【明星同款】甜酷背带裤2023夏新款女小众独特显瘦百搭裤子女 玫红(针织衫) 160/84A/M,259.0,诗凡黎女装旗舰店,//mall.jd.com/index-11659180.html?from=pc,,江苏,//item.jd.com/10074266224311.html,//img11.360buyimg.com/n7/jfs/t1/164194/26/26612/32404/64535eb6F567e9b1a/8e06cb34c5de7705.jpg,"{'标签': '无', '店铺信誉': '100'}",108,0.625 18 | 16,10070472613096,UR2023夏季新款女装甜酷少女洗水蓝色宽松牛仔背带裤UWV832086 蓝色 27,239.0,UR官方旗舰店,//mall.jd.com/index-11035956.html?from=pc,,江苏,//item.jd.com/10070472613096.html,//img11.360buyimg.com/n7/jfs/t1/192429/15/34101/118959/643d4191F5cb8d0f0/ef33b4a99548e439.jpg,"{'标签': '无', '店铺信誉': '100'}",100,0.5723684210526315 19 | 17,10027734403892,马登工装 美式复古甲板背带裤春秋水洗丹宁直筒牛仔裤男潮 牛仔蓝 XL纯棉透气舒适|工装甲板背带裤,189.9,马登男装旗舰店,//mall.jd.com/index-929180.html?from=pc,,江苏,//item.jd.com/10027734403892.html,//img12.360buyimg.com/n7/jfs/t1/211831/22/33100/131146/649ae32eF95ce15e5/09bd56296bcef104.jpg,"{'标签': '无', '店铺信誉': '98'}",138,0.8223684210526315 20 | 18,10077041572135,淘町女童背带裤短裤夏季2023新款中大童宽松蓝色牛仔裤洋气透气五分裤 蓝色 150cm,119.0,淘町童装官方旗舰店,//mall.jd.com/index-12741246.html?from=pc,,江苏,//item.jd.com/10077041572135.html,//img10.360buyimg.com/n7/jfs/t1/199774/2/33716/52034/6475971fFf438b391/17b272ac97105108.jpg,"{'标签': '无', '店铺信誉': ''}",50,0.24342105263157895 21 | 19,10069800021057,欧若婷雅休闲裤女装夏季薄款韩版时尚垂感阔腿裤减龄背带裤两件套套装裤子 套装 L,138.0,欧若婷雅女装旗舰店,//mall.jd.com/index-10302187.html?from=pc,,江苏,//item.jd.com/10069800021057.html,//img12.360buyimg.com/n7/jfs/t1/158096/40/33667/52799/63fdb595F6d8b7326/4bb8e793c12af9a6.jpg,"{'标签': '无', '店铺信誉': '100'}",100,0.5723684210526315 22 | 20,10069768537113,拉夏贝尔高腰显瘦牛仔背带裤套装女小个子夏季洋气减龄直筒休闲连 单件背带裤[法式桔梗背带裤/春 XL拉夏贝尔时尚女装高效配送七天无理由退换运费险,189.0,拉夏贝尔冷冰玉专卖店,//mall.jd.com/index-12264396.html?from=pc,,江苏,//item.jd.com/10069768537113.html,//img13.360buyimg.com/n7/jfs/t1/122357/31/34846/41391/63fe04c8F13df7dc7/d2337b0dd1bc2afe.jpg,"{'标签': '无', '店铺信誉': '100'}",100,0.5723684210526315 23 | 21,10070465997111,派菲洛牛仔背带裤女韩版宽松春夏季2023新款酷盐系设计感小众阔 蓝色 L,55.0,派菲洛旗舰店,//mall.jd.com/index-12568010.html?from=pc,,江苏,//item.jd.com/10070465997111.html,//img11.360buyimg.com/n7/jfs/t1/91913/4/34050/86003/6461ac0bFf2bc1d53/bee60d7677aa9d5b.jpg,"{'标签': '无', '店铺信誉': '100'}",100,0.5723684210526315 24 | 22,65854691446,箐冉儿泫雅风新款牛仔背带裤女直筒韩版宽松可爱复古港味减龄日系 深蓝 M学院风,原宿,可爱,减龄,俏皮活泼,高腰,显瘦,129.0,箐冉儿官方旗舰店,//mall.jd.com/index-10140348.html?from=pc,,江苏,//item.jd.com/65854691446.html,//img11.360buyimg.com/n7/jfs/t1/88797/28/13242/257656/5e5741a7E0d3ff318/572e491841d31307.jpg,"{'标签': '无', '店铺信誉': '97'}",165,1.0 25 | 23,10053857734926,君芳雅(junfangya)背带裤套装女学生夏季新款韩版宽松印花T恤+休闲连体短裤两件套潮 T恤+背带裤【两】 S 建议80-斤换季低价促销,先到先得,试穿+无理由退换,59.0,美凤服装专营店,//mall.jd.com/index-10064417.html?from=pc,,江苏,//item.jd.com/10053857734926.html,//img11.360buyimg.com/n7/jfs/t1/186003/39/24749/95883/629c7a04E69f7f5aa/3392c9c7ccf53334.jpg,"{'标签': '无', '店铺信誉': '87'}",87,0.4868421052631579 26 | 24,10068122050164,牧狮德工装牛仔背带裤女春秋2023宽松韩版九分减龄高腰显瘦可盐可甜炸街 深蓝色 M,139.0,牧狮德官方旗舰店,//mall.jd.com/index-10343420.html?from=pc,,江苏,//item.jd.com/10068122050164.html,//img14.360buyimg.com/n7/jfs/t1/165280/26/31797/181390/63d9d353F7159ef84/8c0a8da99e0f71fa.jpg,"{'标签': '无', '店铺信誉': '9'}",50,0.24342105263157895 27 | 25,10058425985806,织迷150cm小个子牛仔背带裤女秋冬新款设计感小众裤子宽松阔腿连体裤蓝色 高质量收藏 L(建议105-115斤)新品上架,限时低价促销!!!关注店铺加入购物车下单优先发货【支持7天无理由退换】,76.0,织迷女装旗舰店,//mall.jd.com/index-11518202.html?from=pc,,江苏,//item.jd.com/10058425985806.html,//img11.360buyimg.com/n7/jfs/t1/183168/2/25754/224302/62f8633bEfe538718/fb38582393a62c7f.jpg,"{'标签': '无', '店铺信誉': '100'}",100,0.5723684210526315 28 | 26,100045606480,森马(Semir)牛仔裤女纯棉阔腿裤复古夏2023渐变背带裤潮酷103323124006,298.0,森马京东自营旗舰店,//mall.jd.com/index-1000013241.html?from=pc,,江苏,//item.jd.com/100045606480.html,//img10.360buyimg.com/n7/jfs/t1/145746/38/37553/34030/649f8a3eFb4617634/7d620947041c2c59.jpg,"{'标签': '自营', '店铺信誉': '100'}",130,0.7697368421052632 29 | 27,10033577269291,【商场同款】Dickies连体裤多口袋蓝白条纹直筒连体裤背带裤男士秋冬长裤 9401 蓝白条纹 L爆款冰点价,只“暑”于你!实付169 购物车+29元换购斜挎包,速抢!,499.0,Dickies官方旗舰店,//mall.jd.com/index-37571.html?from=pc,,江苏,//item.jd.com/10033577269291.html,//img11.360buyimg.com/n7/jfs/t1/176556/28/18808/175021/60e6af2cEa22d4bf6/fec78f4801ac09f1.jpg,"{'标签': '无', '店铺信誉': '100'}",100,0.5723684210526315 30 | 28,10069882620461,UR2023夏季女装休闲减龄小个子显瘦宽松牛仔背带裤UWL832079 蓝色 26,299.0,UR官方旗舰店,//mall.jd.com/index-11035956.html?from=pc,,江苏,//item.jd.com/10069882620461.html,//img11.360buyimg.com/n7/jfs/t1/192096/36/33653/67005/6426d781Ffdfae93d/e00afe2eebd71c6a.jpg,"{'标签': '无', '店铺信誉': '100'}",100,0.5723684210526315 31 | 29,100026716841,Semir森马背带裤女明线设计春秋款纯棉显瘦阔腿裤复古潮酷109522127070,179.99,森马京东自营旗舰店,//mall.jd.com/index-1000013241.html?from=pc,,江苏,//item.jd.com/100026716841.html,//img11.360buyimg.com/n7/jfs/t1/65836/21/24197/55072/649eb018Fef65b312/c9fe160735f84c89.jpg,"{'标签': '自营', '店铺信誉': '93'}",138,0.8223684210526315 32 | -------------------------------------------------------------------------------- /font/msyh.ttc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AlcatrazChris/AutoProductEvalution/e8ac3c024d234dd2f2406b3e23da3dd6fa545c0a/font/msyh.ttc -------------------------------------------------------------------------------- /font/msyhbd.ttc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AlcatrazChris/AutoProductEvalution/e8ac3c024d234dd2f2406b3e23da3dd6fa545c0a/font/msyhbd.ttc -------------------------------------------------------------------------------- /font/msyhl.ttc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AlcatrazChris/AutoProductEvalution/e8ac3c024d234dd2f2406b3e23da3dd6fa545c0a/font/msyhl.ttc -------------------------------------------------------------------------------- /img/img.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AlcatrazChris/AutoProductEvalution/e8ac3c024d234dd2f2406b3e23da3dd6fa545c0a/img/img.png -------------------------------------------------------------------------------- /img/img0000.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AlcatrazChris/AutoProductEvalution/e8ac3c024d234dd2f2406b3e23da3dd6fa545c0a/img/img0000.png -------------------------------------------------------------------------------- /img/img1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AlcatrazChris/AutoProductEvalution/e8ac3c024d234dd2f2406b3e23da3dd6fa545c0a/img/img1.png -------------------------------------------------------------------------------- /img/img2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AlcatrazChris/AutoProductEvalution/e8ac3c024d234dd2f2406b3e23da3dd6fa545c0a/img/img2.png -------------------------------------------------------------------------------- /img/img_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AlcatrazChris/AutoProductEvalution/e8ac3c024d234dd2f2406b3e23da3dd6fa545c0a/img/img_1.png -------------------------------------------------------------------------------- /img/menu.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AlcatrazChris/AutoProductEvalution/e8ac3c024d234dd2f2406b3e23da3dd6fa545c0a/img/menu.png -------------------------------------------------------------------------------- /img/test.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AlcatrazChris/AutoProductEvalution/e8ac3c024d234dd2f2406b3e23da3dd6fa545c0a/img/test.png -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- 1 | from PyQt5.QtWidgets import QApplication 2 | from UI import App 3 | import datetime 4 | import sys 5 | if __name__ == '__main__': 6 | app = QApplication(sys.argv) 7 | ex = App() 8 | ex.show() 9 | sys.exit(app.exec_()) 10 | -------------------------------------------------------------------------------- /readme.md: -------------------------------------------------------------------------------- 1 | # 淘宝、京东商品爬虫及评价系统 2 | ## 1. 使用说明 3 | 1. 安装项目所依赖的库 4 | 打开项目所在文件夹,进入Terminal,输入 5 | 6 | ```Terminal 7 | pip install -r requirements.txt 8 | ``` 9 | 2. 从文件夹进入Terminal(文件路径处输入:cmd) 10 | 3. 在Terminal中输入: 11 | ```Terminal 12 | Python main.py 13 | ``` 14 | 4. 成功运行后的界面如下: 15 |  16 | 5. 使用方法:在输入框中输入商品名称,然后在左侧下拉框中选择平台(京东/淘宝),点击搜索即可得到搜索结果。在搜索完成以后可以点击保存数据,系统会自动将数据保存在data文件夹中,并且会弹出保存成功的提示,具体如下图。 17 |  18 | 由于电商网站的反爬比较严重,可能会有请求被反爬程序拦截的问题,此时程序可能会意外退出。遇到此类情况,请在Spider.py文件中的‘def __init__(self, url, timeout):’中的'self.headers'里替换自己的cookies后重试。 19 | 20 | 21 | 6. 关于自动评价的用法:自动评价是基于商品的商家信息和商品的评论自动给出推荐等级的方法,具体的算法看请看后面部分的说明。使用方法为在加载完数据后点击自动评价。 22 | 若评价成功(正常情况下),界面会刷新,并在原来商品的页面下方新增一行:推荐指数。 23 | 推荐指数有5个档次,分别是1、2、3、4、5,越大则是从算法角度来说越好的商品。 24 |  25 | 当然由于网站经常会有反爬虫或者数据未加载完全便进行评价的问题,也有可能会评价不成功,此时会显示 26 |  27 | 如果显示不成功,建议等待片刻后再次点击“自动评价”,如果仍然不成功,建议重新搜索后等待片刻再使用“自动评价”。若前两种方法均不能成功,请更改关键词或平台尝试。 28 | ## 2. 我的想法 29 | 为什么我会想做这个系统? 30 | 现在在网上购物是在是太难挑了,所以我基本选择不购物,但是有时候真的需要购物时如何快速的对比商品之间谁更加值得购买呢? 31 | 我想结合自己的购物挑选物品的习惯将爬虫技术与NLP(其实不能算NLP吧,本次项目我仅仅使用了LSTM对商品的评论进行分类) ,实现购物的快速预比对。 32 | 当然了,这只是我自己写来做测试的,后续我自己是不是会使用本程序进行物品挑选也还是未可知,如本程序出现任何问题而对您的购物 33 | 产生了任何不愉快的影响与我无关:yum: ^o^ 34 | ## 3. 具体实现 35 | ### 3.0 文件结构 36 | ```commandline 37 | - .idea 38 | - __pycache__ 39 | - data 40 | - img 41 | + Model 42 | | - data 43 | | - model 44 | | - test.py 45 | | - train.py 46 | + temp 47 | | + data 48 | | | - JDdata.csv 49 | | | - page.txt 50 | | | - TBdata.csv 51 | | - img 52 | | - JD_comment 53 | | - TB_comment 54 | - main.py 55 | - Spider.py 56 | - Evalution.py 57 | - UI.py 58 | - utils.py 59 | - readme.md 60 | - requirements.txt 61 | ``` 62 | 本项目的文件结构如上所示。.idea和__pycache__均为pycharm配置环境时自动生成,不必理会。data文件夹用于存放点击“保存数据”存放的数据。img为本文件(readme.md)中图片的存放位置, 63 | Model为LSTM模型的存放地址,Model/data为数据集,其中有多个数据集,部分是我自己的,还有一些是网上开源的数据集。Model/model中是已经训练好的模型和分词词典及索引,用于商品评价的分类,test.py为测试程序,train.py为训练程序 64 | temp文件夹是程序的临时数据,每次进行搜索时会自动清理。data中是网页源码和京东、淘宝爬取完后的数据。img为商品图片, 65 | JD_comment和TB_comment是京东和淘宝评论的存放文件夹。main.py是主程序,Spider.py是爬虫程序,Evaluation.py 66 | 是使用LSTM进行商品评论分类及对商品评分的程序,UI.py是整个界面的源代码,utils.py是一些程序所需要的工具函数,比如clear_folder, 67 | readme.md为本文件,requirements.txt为本项目的依赖文件。 68 | ### 3.1 爬虫部分的实现 69 | #### 3.1.1 URL部分 70 | **1.淘宝** 71 | 在淘宝搜索商品是,url的构成通常是 72 | https://s.taobao.com/search?q= +keyword 73 | 因此我们可以考虑在将前一部分'https://s.taobao.com/search?q=' 固定,然后将输入框的keyword加入url构成一个完整的淘宝链接。 74 | **2.京东** 75 | 在京东搜索商品是,url的构成通常是 76 | https://search.jd.com/Search?keyword= +keyword 77 | 因此我们可以考虑将前一部分 'https://search.jd.com/Search?keyword=' 固定,然后将输入框的keyword加入url构成一个完整的京东链接 78 | 代码实现 79 | ```Python 80 | def search(self): 81 | Spider.clear_folder('temp/img') 82 | url_dict = { 83 | '京东': 'https://search.jd.com/Search?keyword=', 84 | '淘宝': 'https://s.taobao.com/search?q=' 85 | } 86 | goods = quote(self.inputLine.text()) 87 | platform = self.comboBox.currentText() 88 | url = url_dict.get(platform, None) + goods 89 | ``` 90 | #### 3.1.2 请求返回的数据 91 | 前面我们已经成功生成了url,使用get命令可以轻松获得淘宝或者京东网页的数据,当然,前提是需要有一个有效的cookies(在header中修改) 92 | ```Python 93 | def get_page(self): 94 | """获取网页源代码""" 95 | try: 96 | page = requests.get(self.url, headers=self.header, timeout=self.timeout) 97 | page.raise_for_status() 98 | with open('temp/data/page.txt', 'w', encoding='utf-8', errors='ignore') as f: 99 | f.write(page.text) 100 | print("成功获取信息!") 101 | return page.text 102 | except requests.exceptions.RequestException as err: 103 | print("获取信息失败!:", str(err)) 104 | return None 105 | ``` 106 | 得到返回的数据后,我们将它保存在(‘temp/data/page.txt')中,通过查看淘宝与京东返回的信息,我们可以使用数据处理工具得到我们所需要的信息。 107 | #### 3.1.3 处理返回的数据 108 | 淘宝返回的格式与京东返回的格式是不一样的,因此我们分开考虑 109 | **1. 淘宝** 110 | ```json 111 | g_page_config = {"pageName":"mainsrp","mods": 112 | {"shopcombotip":{"status":"hide"},"phonenav":{"status":"hide"},"debugbar":{"status":"hide"},"shopcombo":{"status":"hide"},"itemlist":{"status":"show","data":{"postFeeText":"运费","trace":"msrp_auction","auctions": 113 | [{"p4p":1,"p4pSameHeight":true,"nid":"667665852631","category":"50019780","categoryp":"50019780","pid":"","title":"【顺丰速发 12期免息】三星Samsung Galaxy Tab S8/S8+/S8 Ultra 系列平板\u003cspan class\u003dH\u003e电脑\u003c/span\u003e追剧智能2022新款学生学习办公", 114 | "raw_title":"三星Samsung Galaxy Tab S8/S8+/S8 Ultra","pic_url":"//g-search1.alicdn.com/img/bao/uploaded/i4/imgextra/i2/15237275/O1CN01pT4wAN23c0EGYuBz8_!!0-saturn_solar.jpg", 115 | "detail_url":"https://click.simba.taobao.com/cc_im?p\u003d%B5%E7%C4%D4\u0026s\u003d258036029\u0026k\u003d941\u0026e\u003d7MhVImNq06g4FU297ykXkL0lr8Y%2BWJnH2BSzT98RTKmCN0ks99GXa3%2BkNwBOgeUJ264aitxLH9Xs7C86hJXoc2Zuwt5lUHX8%2FvJhJiJ2j9NaaWVQ00QGKVXZPZ51zaOF83L0YmhDqENIZXKKqgcL8Uk%2BsXf%2FzuXHKJ101vM08FKtMegztztPKowLjr8NwZsaV3K2ZC%2FRHKPfFL9%2FXi0sjssMaZzMfFqmpUkGp0RWL7WLQX3h%2FvnxLVGn3W0uWPg0xKK0Ib9iLfNFMbAqedjepIwAT5fCOpCXxLcHJkEbXSQuuwibxsb899yGPEslrJ4m6EMo7qFbr4pGkLqW7bG5aGo0LWE3m6azH%2Fcxh4K5P7e7KJwcjwaBPfp%2BI8%2FQIrQDfx5Fai9iU2nkABk2OYNFPq%2Ffem9c6rr73zYyJ%2FSxPZpR2CgTXsvg%2BX4E5Z8y0agm%2FZkg%2BP1KXGvvOhSIpPZpHNcp%2Bm7zxYfkq6cmPThFYeHeRDDMKL8fA5I12i54GTIddT9kN4cAmGpNeQDBvJR4gyT2gcNBBXWr7vO%2FjlXKb%2BH9G%2BA786GmXnb1Aqdjk7F8aM8IjgQ4sR3SuDF2CXTS0LGE0GoFz9CTYndyMA%2F%2FZajeJ0YWKagglrF5lj9YUXvK1MjujltwM9fK%2FKHL8Sv%2Bsi9R8AHwrJq%2BH5tRvZ7qers4Y4fLZ972bJFz8rHwRaLgiuXa%2FSlo%2FC1vjEMG2nmv8ZC7VJ6NGPHIiC0X8LPtSrt%2BdiLshbz0%2F1tbaXReyERznGumSKkJdhF3cXm7Vbc0OjICCASfrUBGcATQKVRc%2BNCJ%2FoWR8%2FJNYDF3%2FzJlhvGTxNgXcJMkKgCYFt%2FFco%2B%2FrxVgTc%2FyCWRBm4kgW3TMr3154qWZaNNiMM4QfHC5bvXnmCvbyAmBQIhguGi3Z8s8KBRrradrrKO79vQSJh5lkIg%3D", 116 | "view_price":"4299.00","view_fee":"0.00","item_loc":"北京","view_sales":"300+人付款","comment_count":"","user_id":"370627083","nick":"三星官方旗舰店","shopcard":{"levelClasses":[],"isTmall":true,"delivery":[],"description":[],"service":[],"encryptedUserId":"UvGcWMCIuvmgG"},"icon":[{"title":"2023-618 狂欢日-天猫\u0026飞猪","dom_class":"icon-new-fest-2023khrb","position":"0","show_type":"0", 117 | "icon_category":"baobei","outer_text":"0","html":"","icon_key":"icon-new-fest-2023khrb","trace":"srpservice","traceIdx":0,"innerText":"2023-618 狂欢日-天猫\u0026飞猪"},{"title":"掌柜热卖宝贝","dom_class":"icon-service-remai","position":"1","show_type":"0","icon_category":"baobei","outer_text":"0","html":"","icon_key":"icon-service-remai","trace":"srpservice","traceIdx":1,"innerText":"掌柜热卖宝贝","url":"//re.taobao.com/search?keyword\u003d%B5%E7%C4%D4\u0026refpid\u003d420432_1006\u0026frcatid\u003d\u0026"}, 118 | {"title":"尚天猫,就购了","dom_class":"icon-service-tianmao","position":"1","show_type":"0","icon_category":"baobei","outer_text":"0","html":"","icon_key":"icon-service-tianmao","trace":"srpservice","traceIdx":2,"innerText":"天猫宝贝"}],"isHideIM":true,"isHideNick":false,"comment_url":"https://click.simba.taobao.com/cc_im?p\u003d%B5%E7%C4%D4\u0026s\u003d258036029\u0026k\u003d941\u0026e\u003d7MhVImNq06g4FU297ykXkL0lr8Y%2BWJnH2BSzT98RTKmCN0ks99GXa3%2BkNwBOgeUJ264aitxLH9Xs7C86hJXoc2Zuwt5lUHX8%2FvJhJiJ2j9NaaWVQ00QGKVXZPZ51zaOF83L0YmhDqENIZXKKqgcL8Uk%2BsXf%2FzuXHKJ101vM08FKtMegztztPKowLjr8NwZsaV3K2ZC%2FRHKPfFL9%2FXi0sjssMaZzMfFqmpUkGp0RWL7WLQX3h%2FvnxLVGn3W0uWPg0xKK0Ib9iLfNFMbAqedjepIwAT5fCOpCXxLcHJkEbXSQuuwibxsb899yGPEslrJ4m6EMo7qFbr4pGkLqW7bG5aGo0LWE3m6azH%2Fcxh4K5P7e7KJwcjwaBPfp%2BI8%2FQIrQDfx5Fai9iU2nkABk2OYNFPq%2Ffem9c6rr73zYyJ%2FSxPZpR2CgTXsvg%2BX4E5Z8y0agm%2FZkg%2BP1KXGvvOhSIpPZpHNcp%2Bm7zxYfkq6cmPThFYeHeRDDMKL8fA5I12i54GTIddT9kN4cAmGpNeQDBvJR4gyT2gcNBBXWr7vO%2FjlXKb%2BH9G%2BA786GmXnb1Aqdjk7F8aM8IjgQ4sR3SuDF2CXTS0LGE0GoFz9CTYndyMA%2F%2FZajeJ0YWKagglrF5lj9YUXvK1MjujltwM9fK%2FKHL8Sv%2Bsi9R8AHwrJq%2BH5tRvZ7qers4Y4fLZ972bJFz8rHwRaLgiuXa%2FSlo%2FC1vjEMG2nmv8ZC7VJ6NGPHIiC0X8LPtSrt%2BdiLshbz0%2F1tbaXReyERznGumSKkJdhF3cXm7Vbc0OjICCASfrUBGcATQKVRc%2BNCJ%2FoWR8%2FJNYDF3%2FzJlhvGTxNgXcJMkKgCYFt%2FFco%2B%2FrxVgTc%2FyCWRBm4kgW3TMr3154qWZaNNiMM4QfHC5bvXnmCvbyAmBQIhguGi3Z8s8KBRrradrrKO79vQSJh5lkIg%3D\u0026on_comment\u003d1", 119 | "shopLink":"https://click.simba.taobao.com/cc_im?p\u003d%B5%E7%C4%D4\u0026s\u003d258036029\u0026k\u003d897\u0026e\u003dZaQW5fRjigU4FU297ykXkL0lr8Y%2BWJnH2BSzT98RTKmCN0ks99GXa3%2BkNwBOgeUJ264aitxLH9XkK9atyv2jJmZuwt5lUHX8%2FvJhJiJ2j9NaaWVQ00QGKVXZPZ51zaOF83L0YmhDqENIZXKKqgcL8Uk%2BsXf%2FzuXHKJ101vM08FKtMegztztPKowLjr8NwZsaV3K2ZC%2FRHKPfFL9%2FXi0sjssMaZzMfFqmpUkGp0RWL7WLQX3h%2FvnxLVGn3W0uWPg0xKK0Ib9iLfNFMbAqedjepIwAT5fCOpCXxLcHJkEbXSQuuwibxsb899yGPEslrJ4m6EMo7qFbr4pGkLqW7bG5aGo0LWE3m6azH%2Fcxh4K5P7c9uq5tu8VVR4Z1zvMnd1UT840%2BjTL9MX%2Bh2%2BKnReLmOvxDJTGDRakn3Z8GwhrCzUFiW005oJXLWyRIHV5nqcI5mBbfxXKPv68LwW3Hds6kjuFva8qmFXDhFADm9aIp7YOZCJ6wC8Tk%2B6U217HG1rsmEvQiVSL21pVO121vAYPdds00pPeXxWzmnzrbgzt5PNt%2FetidrPDWwfvUCqaxtp8OFVrOmMkcdFfu8fDL5umru9hZ2ippdKzZonZC93GhBFXEF7z4FfbdOkkx919nTrPzZ7%2F4MMT3%2B5H976uWwukfCag8ziYR9CkwRfp1soi9I7raPfC8344HlrWzL4KCrtp%2FLni%2Fc8tkdtqSy5rUupewA3vvDo8opv2j%2FLOWpCoybLuQ8oO5SiOFaxNMdHdDm7%2BsqMW5X1pjwOFUp%2B4%2BObp4yGr0fThp%2BpsssXjavqTAtOYtkwRM6802kL8s893SgNRAv55LdjCpZaU%2Bzpazwv7ejuOJC7c41U14PQ2yeGFDW9kJDY%2BFJM8x7f7lG532mye7", 120 | "shopName":"三星官方旗舰店"},} 121 | ``` 122 | 这是一个json格式的数据,因此我们可以使用json库进行处理。先定位到"auctions",然后对其中数据进行解析: 123 | |各个字段的意义| 124 | |:----| 125 | |"nid": 商品的唯一标识符。| 126 | |"title": 商品的标题。| 127 | |"pic_url": 商品的图片URL| 128 | |"detail_url": 商品的详情页URL。| 129 | |"view_price": 商品的显示价格| 130 | |"item_loc": 商品所在地。| 131 | |"view_sales": 商品的销量。| 132 | |"shopcard": 卖家店铺的信息,包括店铺等级、是否天猫店铺等。| 133 | |"shopName": 卖家店铺的名称。| 134 | 135 | 将解析出的数据保存到temp/data/TBdata.csv中。源代码如下: 136 | ```Python 137 | def taobao_prase_page(self, page): 138 | """解析淘宝网页数据""" 139 | data_list = [] 140 | page_info = re.findall('g_page_config = (.*);', page)[0] 141 | page_info = json.loads(page_info) 142 | info = page_info['mods']['itemlist']['data']['auctions'] 143 | executor = ThreadPoolExecutor(max_workers=30) 144 | clear_folder('temp/TB_comment') 145 | for index in info: 146 | level_classes = index['shopcard']['levelClasses'] 147 | seller_credit = level_classes[0].get('sellerCredit') if level_classes else None 148 | total_rate = level_classes[0].get('totalRate') if level_classes else None 149 | data_dict = { 150 | "ID": index['nid'], 151 | "商品": index['raw_title'], 152 | "价格": index['view_price'], 153 | "店铺": index['nick'], 154 | "店铺地址": index['shopLink'], 155 | "购买人数": index['view_sales'], 156 | "发货地": index['item_loc'], 157 | "详情页": index['detail_url'], 158 | "图片": index['pic_url'], 159 | "店铺信息": { 160 | '天猫' if level_classes and any( 161 | d.get('levelClass') == 'icon-supple-level-jinguan' for d in level_classes) else '无', 162 | seller_credit, 163 | total_rate 164 | } 165 | } 166 | data_list.append(data_dict) 167 | 168 | # 针对每一个商品启动一个新的线程来获取评论 169 | 170 | pd.DataFrame(data_list).to_csv('temp/data/TBdata.csv', header=True) 171 | ``` 172 | **2. 京东** 173 | ```html 174 |