折腾：
【未解决】用Python爬取汽车之家的车型车系详细数据
期间，经过调试，已经支持了新版的 车系详情页面
具体细节是：
从入口
研究后发现是：
每个车系，都可以从
英文字母页面获取到
从：
到：
总结成：
1 | https://www.autohome.com.cn/grade/carhtml/%s.html |
针对每个页面去：
找到车系的一些数据：
分别对应着：
- carBrandName：奥迪
- carMerchantName：一汽-大众奥迪
- carSeriesName：奥迪A3
- carSeriesMsrp：19.32-23.46万
- carSeriesMsrpUrl：https://www.autohome.com.cn/3170/price.html#pvareaid=101446
然后进去 车系主页=车系详情页
上图中多数信息前面已抓取
只需要抓剩余的信息即可
另外加上相关的内容，此处是：
- carSeriesId：2123
- 从url中提取
和 从源码中js：
1 2 3 4 5 6 7 8 9 10 11 | <script type="text/javascript"> 。。。 var seriesid = '2123'; var seriesname='哈弗H6'; var yearid = '0'; var brandid = '181'; var levelid = '17'; var levelname='紧凑型SUV'; var fctid = '4'; var SeriesMinPrice='9.80'; var SeriesMaxPrice='14.10'; |
提取出的：
- carSeriesId：2123
- carBrandId：181
- carSeriesLevelId：17
- 用于后续获取停产车型数据的请求的参数
- carSeriesLevelName：紧凑型SUV
- carSeriesMinPrice：9.80
- 单位：万元
- carSeriesMaxPrice：14.10
- 单位：万元
另外还要抓取：
相关html：
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 | <!--即将上市 start--> <div class="spec-wrap active" id="specWrap-1"> <dl class="halt-spec"> <dt> <div class="spec-name"> <span>参数配置未公布</span> </div> <dl class="halt-spec"> <dt> <div class="spec-name"> <span>1.5升 涡轮增压 169马力 国VI</span> </div> |
解析出内容：
- carModelGroupName：1.5升 涡轮增压 169马力 国VI
相关html
1 | <dd data-sift1="2020款" data-sift2="国VI" data-sift3="1.5T" data-sift4="7挡双离合" class=""> |
解析内容：
- carModelYear：2020款
- carModelEmissionStandards：国VI
- carModelPower：1.5T
- carModelGearBox：7挡双离合
相关html：
1 2 3 4 5 6 7 8 9 | <div class="spec-name"> <div class="name-param"> <p data-gcjid="41511" id="spec_41511"> <a href="/spec/41511/#pvareaid=3454492" class="name">2020款 1.5GDIT 自动铂金舒适版</a> <span class="athm-badge athm-badge--grey is-plain">停产在售</span> <span class="athm-badge athm-badge--orange">特惠</span></p> <p><span class="type-default">前置前驱</span><span class="type-default">7挡双离合</span></p> </div> </div> |
解析出：
- carModelName：2020款 1.5GDIT 自动铂金舒适版
- carModelSpecUrl：https://www.autohome.com.cn/spec/41511/#pvareaid=3454492
- spec=specification=规范=（汽车的）参数配置
- carModelDriveType：前置前驱
- carModelGearBox：7挡双离合
相关html：
1 2 3 4 5 6 7 8 9 10 11 | <div class="spec-guidance"> <p class="guidance-price"> <span>10.40万</span> <a href="//j.autohome.com.cn/pc/carcounter?type=1&specId=41511&pvareaid=3454617"><i class="athm-iconpng athm-iconpng-calculator"></i></a> </p> </div> <div class="spec-guidance"> <p class="guidance-price"> <span><span>暂无</span></span> |
解析出：
- carModelMsrp：10.40万
- 或 暂无 -》 再替换成 空字符串
以及对于 停售款 也要抓取：
此处经研究，停售款的数据，是单独发送请求，返回json数据的
请求 举例
1 | https://www.autohome.com.cn/ashx/car/Spec_ListByYearId.ashx?seriesid=2123&syearid=10379&levelid=17 |
返回的json数据，很全面。
举例：
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 | [ { "name": "1.5升 涡轮增压 169马力", "speclist": [ { "specid": 36955, "specname": "2019款 红标 1.5GDIT 自动舒适版", "specstate": 40, "minprice": 102000, "maxprice": 102000, "fueltype": 1, "fueltypedetail": 1, "driveform": "前置前驱", "drivetype": "前驱", "gearbox": "7挡双离合", "evflag": "", "newcarflag": "", "subsidy": "", "paramisshow": 1, "videoid": 0, "price2sc": "7.58万", "price": "10.20万", "syear": 2019 }, { "specid": 36956, "specname": "2019款 红标 1.5GDIT 自动都市版", "specstate": 40, "minprice": 109000, "maxprice": 109000, "fueltype": 1, "fueltypedetail": 1, "driveform": "前置前驱", "drivetype": "前驱", "gearbox": "7挡双离合", "evflag": "", "newcarflag": "", "subsidy": "", "paramisshow": 1, "videoid": 0, "link2sc": "", "price2sc": "", "price": "10.90万", "syear": 2019 },。。。 |
只取用部分字段即可。
核心逻辑是：
1 2 3 4 5 6 7 8 9 10 11 12 13 14 | carModelYear = "%s款" % eachModelDict["syear"] # carModelSpecUrl = "%s/%s" % (CarSpecPrefix, eachModelDict["specid"]) carModelSpecUrl = self.genSpecUrl(eachModelDict["specid"]) curCarModelDict["carModelGroupName"] = modelGroupName curCarModelDict["carModelYear"] = carModelYear curCarModelDict["carModelEmissionStandards"] = "" curCarModelDict["carModelPower"] = "" curCarModelDict["carModelDriveType"] = eachModelDict["drivetype"] curCarModelDict["carModelGearBox"] = eachModelDict["gearbox"] curCarModelDict["carModelName"] = eachModelDict["specname"] curCarModelDict["carModelSpecUrl"] = carModelSpecUrl curCarModelDict["carModelMsrp"] = eachModelDict["price"] |
即可。
完整代码如下：
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 | #!/usr/bin/env python# -*- encoding: utf-8 -*-# Created on 2020-08-19 22:19:20# Project: autohome_20200819import stringimport reimport copyfrom lxml import etreefrom pyspider.libs.base_handler import *class Handler(BaseHandler): UserAgent_Mac_Chrome = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36" crawl_config = { "headers": { "User-Agent": UserAgent_Mac_Chrome, } } def genSpecUrl(self, specId): # return "%s/%s" % (CarSpecPrefix, specId) return "%s/%s/" % (CarSpecPrefix, specId) # @every(minutes=24 * 60) def on_start(self): # autohomeEntryUrl = "https://www.autohome.com.cn/car/" # self.crawl(autohomeEntryUrl, callback=self.carBrandListCallback) for eachLetter in list(string.ascii_lowercase): letterUpper = eachLetter.upper() # # for debug # letterUpper = "H" print("letterUpper=%s" % letterUpper) save={"initials": letterUpper}, callback=self.gradCarHtmlPage) @catch_status_code_error def gradCarHtmlPage(self, response): print("gradCarHtmlPage: response=", response) # picSeriesItemList = response.doc('.rank-list-ul li div a[href*="/pic/series"]').items() # print("picSeriesItemList=", picSeriesItemList) # print("len(picSeriesItemList)=%s"%(len(picSeriesItemList))) # for each in picSeriesItemList: # self.crawl(each.attr.href, callback=self.picSeriesPage) saveDict = response.save print("saveDict=", saveDict) initials = saveDict["initials"] print("initials=", initials) respText = response.text # print("respText=", respText) """ <dl id="33" olr="6"> <dt><a href="//car.autohome.com.cn/price/brand-33.html#pvareaid=2042362"><img width="50" height="50" src="//car2.autoimg.cn/cardfs/series/g26/M0B/AE/B3/100x100_f40_autohomecar__wKgHEVs9u5WAV441AAAKdxZGE4U148.png"></a> <div><a href="//car.autohome.com.cn/price/brand-33.html#pvareaid=2042362">奥迪</a></div> </dt> """ # brandDoc = response.doc('dl dt') # print("brandDoc=%s" % brandDoc) # brandListDoc = response.doc('dl[id and orl] dt') # dlListDoc = response.doc('dl[id and orl]').items() # dlListDoc = response.doc("dl[id*=''][orl*='']").items() # dlListDoc = response.doc("dl[orl*='']").items() # dlListDoc = response.doc("dl").items() # dlListDoc = response.doc("dl:regex(id, \d+)").items() # dlListDoc = response.doc("dl:regex(id,[0-9])").items() # dlListDoc = response.doc("dl[id]").items() dlListDoc = response.doc("dl[olr]").items() print("type(dlListDoc)=%s" % type(dlListDoc)) dlList = list(dlListDoc) print("len(dlList)=%s" % len(dlList)) print("dlList=%s" % dlList) for curBrandIdx, eachDlDoc in enumerate(dlList): print("%s [%d] %s" % ('#'*30, curBrandIdx, '#'*30)) dtDoc = eachDlDoc.find("dt") # print("dtDoc=%s" % dtDoc) # <a href="//car.autohome.com.cn/price/brand-33.html#pvareaid=2042362"><img width="50" height="50" src="//car2.autoimg.cn/cardfs/series/g26/M0B/AE/B3/100x100_f40_autohomecar__wKgHEVs9u5WAV441AAAKdxZGE4U148.png"></a> brandLogoDoc = dtDoc.find('a img') # print("brandLogoDoc=%s" % brandLogoDoc) carBrandLogoUrl = brandLogoDoc.attr["src"] print("carBrandLogoUrl=%s" % carBrandLogoUrl) # <div><a href="//car.autohome.com.cn/price/brand-33.html#pvareaid=2042362">奥迪</a></div> brandNameDoc = dtDoc.find('div a') # print("brandNameDoc=%s" % brandNameDoc) carBrandName = brandNameDoc.text() print("carBrandName=%s" % carBrandName) # <div class="h3-tit"><a href="//car.autohome.com.cn/price/brand-33-9.html#pvareaid=2042363">一汽-大众奥迪</a></div> # merchantDocGenerator = response.doc("dd div[class='h3-tit'] a").items() # ddDoc = eachDlDoc.find("dd") ddDoc = eachDlDoc.find("dd") # print("ddDoc=%s" % ddDoc) merchantDocGenerator = ddDoc.items("div[class='h3-tit'] a") merchantDocList = list(merchantDocGenerator) # print("merchantDocList=%s" % merchantDocList) merchantDocLen = len(merchantDocList) print("merchantDocLen=%s" % merchantDocLen) # <ul class="rank-list-ul" 0> # merchantRankDocGenerator = response.doc("dd ul[class='rank-list-ul']") # merchantRankDocGenerator = response.doc("dd ul[class='rank-list-ul']").items() merchantRankDocGenerator = ddDoc.items("ul[class='rank-list-ul']") merchantRankDocList = list(merchantRankDocGenerator) # print("merchantRankDocList=%s" % merchantRankDocList) merchantRankDocListLen = len(merchantRankDocList) print("merchantRankDocListLen=%s" % merchantRankDocListLen) for curIdx, merchantItem in enumerate(merchantDocList): # for curIdx, merchantItem in enumerate(merchantDocGenerator): # print("%s" % "="*80) print("%s [%d] %s" % ('='*30, curIdx, '='*30)) # print("type(merchantItem)=%s" % type(merchantItem)) # print("[%d] merchantItem=%s" % (curIdx, merchantItem)) # print("[%d] merchantItem=%s" % (curIdx, merchantItem)) carMerchantName = merchantItem.text() print("carMerchantName=%s" % carMerchantName) merchantItemAttr = merchantItem.attr # print("merchantItemAttr=%s" % merchantItemAttr) carMerchantUrl = merchantItemAttr["href"] print("carMerchantUrl=%s" % carMerchantUrl) # curSubBrandDict = { # "brandName": brandName, # "carBrandLogoUrl": carBrandLogoUrl, # "carMerchantName": carMerchantName, # "carMerchantUrl": carMerchantUrl, # } # self.send_message(self.project_name, curSubBrandDict, url=carMerchantUrl) merchantRankDoc = merchantRankDocList[curIdx] # print("merchantRankDoc=%s" % merchantRankDoc) # print("type(merchantRankDoc)=%s" % type(merchantRankDoc)) # type(merchantRankDoc)=<class 'lxml.html.HtmlElement'> # merchantRankHtml = etree.tostring(merchantRankDoc) # type(merchantRankDoc)=<class 'pyquery.pyquery.PyQuery'> # merchantRankHtml = merchantRankDoc.html() # print("merchantRankHtml=%s" % merchantRankHtml) # <li id="s3170"> # carSeriesDocGenerator = merchantRankDoc.find("li") # carSeriesDocGenerator = merchantRankDoc.find("li[id*='s']") carSeriesDocGenerator = merchantRankDoc.items("li[id*='s']") # print("type(carSeriesDocGenerator)=%s" % type(carSeriesDocGenerator)) carSeriesDocList = list(carSeriesDocGenerator) # print("type(carSeriesDocList)=%s" % type(carSeriesDocList)) # print("carSeriesDocList=%s" % carSeriesDocList) carSeriesDocListLen = len(carSeriesDocList) # print("carSeriesDocListLen=%s" % carSeriesDocListLen) for curSeriesIdx, eachCarSeriesDoc in enumerate(carSeriesDocList): print("%s [%d] %s" % ('-'*30, curSeriesIdx, '-'*30)) # print("[%d] eachCarSeriesDoc=%s" % (curSeriesIdx, eachCarSeriesDoc)) # print("type(eachCarSeriesDoc)=%s" % type(eachCarSeriesDoc)) # type(eachCarSeriesDoc)=<class 'lxml.html.HtmlElement'> # <h4><a href="//www.autohome.com.cn/3170/#levelsource=000000000_0&pvareaid=101594">奥迪A3</a></h4> carSeriesInfoDoc = eachCarSeriesDoc.find("h4 a") # print("type(carSeriesInfoDoc)=%s" % type(carSeriesInfoDoc)) # print("carSeriesInfoDoc=%s" % carSeriesInfoDoc) carSeriesName = carSeriesInfoDoc.text() print("carSeriesName=%s" % carSeriesName) carSeriesUrl = carSeriesInfoDoc.attr.href print("carSeriesUrl=%s" % carSeriesUrl) # <div>指导价：<a class="red" href="//www.autohome.com.cn/3170/price.html#pvareaid=101446">19.32-23.46万</a></div> # 厂商指导价=厂商建议零售价格=MSRP=Manufacturer's Suggested Retail Price # carSeriesMsrpDoc = eachCarSeriesDoc.find("div a") carSeriesMsrpDoc = eachCarSeriesDoc.find("div a[class='red']") # print("carSeriesMsrpDoc=%s" % carSeriesMsrpDoc) carSeriesMsrp = carSeriesMsrpDoc.text() print("carSeriesMsrp=%s" % carSeriesMsrp) carSeriesMsrpUrl = carSeriesMsrpDoc.attr.href print("carSeriesMsrpUrl=%s" % carSeriesMsrpUrl) carSeriesDict = { "carBrandName": carBrandName, "carBrandLogoUrl": carBrandLogoUrl, "carMerchantName": carMerchantName, "carMerchantUrl": carMerchantUrl, "carSeriesName": carSeriesName, "carSeriesUrl": carSeriesUrl, "carSeriesMsrp": carSeriesMsrp, "carSeriesMsrpUrl": carSeriesMsrpUrl, } # self.send_message(self.project_name, carSeriesDict, url=carSeriesUrl) self.crawl(carSeriesUrl, callback=self.carSeriesDetailPage, save=carSeriesDict, ) def on_message(self, project, msg): print("on_message: msg=%s" % msg) return msg @catch_status_code_error def carSeriesDetailPage(self, response): carSeriesDict = response.save print("carSeriesDict=%s" % carSeriesDict) carSeriesUrl = response.url print("carSeriesUrl=%s" % carSeriesUrl) carSeriesMainImgUrl = "" carSeriesId = "" carSeriesLevelId = "" carSeriesMsrp = "" carSeriesMinPrice = "" carSeriesMaxPrice = "" carSeriesHtml = response.text print("type(carSeriesHtml)=%s" % type(carSeriesHtml)) # <class 'str'> # print("carSeriesHtml=%s" % carSeriesHtml) carModelDict = copy.deepcopy(carSeriesDict) # carSeriesUrl=https://www.autohome.com.cn/2123/#levelsource=000000000_0&pvareaid=101594 foundSeriesId = re.search("www\.autohome\.com\.cn/(?P<seriesId>\d+)/", carSeriesUrl) carSeriesId = foundSeriesId.group("seriesId") # carSeriesId = int(carSeriesId) print("carSeriesId=%s" % carSeriesId) # 2123 carModelDict["carSeriesId"] = carSeriesId """ <div class="information-pic"> <div class="pic-main"> 。。。 <picture> 。。。 <img sizes="380px" width="380" height="285" src="//car2.autoimg.cn/cardfs/product/g1/M04/0B/F0/380x285_0_q87_autohomecar__ChwFqV8YG-aACch8AAkAdoJoSYM874.jpg" srcset="//car2.autoimg.cn/cardfs/product/g1/M04/0B/F0/380x285_0_q87_autohomecar__ChwFqV8YG-aACch8AAkAdoJoSYM874.jpg 380w, //car2.autoimg.cn/cardfs/product/g1/M04/0B/F0/760x570_0_q87_autohomecar__ChwFqV8YG-aACch8AAkAdoJoSYM874.jpg 760w"> </picture> """ mainImgDoc = response.doc("div[class='information-pic'] div[class='pic-main'] picture img") print("mainImgDoc=%s" % mainImgDoc) carSeriesMainImgUrl = mainImgDoc.attr["src"] print("carSeriesMainImgUrl=%s" % carSeriesMainImgUrl) carModelDict["carSeriesMainImgUrl"] = carSeriesMainImgUrl """ <script type="text/javascript"> 。。。 var seriesid = '2123'; var seriesname='哈弗H6'; var yearid = '0'; var brandid = '181'; var levelid = '17'; var levelname='紧凑型SUV'; var fctid = '4'; var SeriesMinPrice='9.80'; var SeriesMaxPrice='14.10'; """ infoKeyList = [ "seriesid", # "seriesname", # has got # "yearid", # no need "brandid", "levelid", "levelname", # "fctid", # unknown meaning "SeriesMinPrice", "SeriesMaxPrice", ] InfoDict = {} for eachInfoKey in infoKeyList: curPattern = "var\s+%s\s*=\s*'(?P<infoValue>[^']+)'\s*;" % eachInfoKey print("curPattern=%s" % curPattern) foundInfo = re.search(curPattern, carSeriesHtml) print("foundInfo=%s" % foundInfo) # if foundInfo: infoValue = foundInfo.group("infoValue") print("infoValue=%s" % infoValue) InfoDict[eachInfoKey] = infoValue print("InfoDict=%s" % InfoDict) # if "seriesid" in InfoDict: carSeriesId = InfoDict["seriesid"] # 2123 carModelDict["carSeriesId"] = carSeriesId # carModelDict["carSeriesName"] = InfoDict["seriesname"] # 哈弗H6 # if "brandid" in InfoDict: carModelDict["carBrandId"] = InfoDict["brandid"] # 181 # if "levelid" in InfoDict: carSeriesLevelId = InfoDict["levelid"] # 17 carModelDict["carSeriesLevelId"] = carSeriesLevelId # if "levelname" in InfoDict: carModelDict["carSeriesLevelName"] = InfoDict["levelname"] # 紧凑型SUV # if "SeriesMinPrice" in InfoDict: carSeriesMinPrice = InfoDict["SeriesMinPrice"] # 9.80 carModelDict["carSeriesMinPrice"] = carSeriesMinPrice # if "SeriesMaxPrice" in InfoDict: carSeriesMaxPrice = InfoDict["SeriesMaxPrice"] # 14.10 carModelDict["carSeriesMaxPrice"] = carSeriesMaxPrice """ <div class="series-list"> 。。。 <li class="more-dropdown"> <a href="javascript:void(0);" target="_self" data-toggle="tab" class="tab-disabled" data-target="#specWrap-3">停售款 <i class="athm-iconfont athm-iconfont-arrowdown"></i></a> <ul class="dropdown-con" id="haltList"> <li><a href="javascript:void(0);" target="_self" data-toggle="tab" data-yearid="11691">2019款</a></li> ... <li><a href="javascript:void(0);" target="_self" data-toggle="tab" data-yearid="3100">2011款</a></li> </ul> </li> """ haltAListDoc = response.doc("li[class='more-dropdown'] ul[id='haltList'] li a").items() print("type(haltAListDoc)=%s" % type(haltAListDoc)) print("haltAListDoc=%s" % haltAListDoc) for curLiIdx, eachHatADoc in enumerate(haltAListDoc): print("%s [%d] %s" % ('%'*30, curLiIdx, '%'*30)) print("eachHatADoc=%s" % eachHatADoc) yearName = eachHatADoc.text() print("yearName=%s" % yearName) yearId = eachHatADoc.attr["data-yearid"] print("yearId=%s" % yearId) # getHaltSpecUrl = "https://www.autohome.com.cn/ashx/car/Spec_ListByYearId.ashx?seriesid=%s&syearid=%s&levelid=%s" % (carModelDict["carSeriesId"], yearId, carModelDict["carSeriesLevelId"]) if carSeriesId and carSeriesLevelId: getHaltSpecUrl = "https://www.autohome.com.cn/ashx/car/Spec_ListByYearId.ashx?seriesid=%s&syearid=%s&levelid=%s" % (carSeriesId, yearId, carSeriesLevelId) # https://www.autohome.com.cn/ashx/car/Spec_ListByYearId.ashx?seriesid=2123&syearid=10379&levelid=17 print("getHaltSpecUrl=%s" % getHaltSpecUrl) self.crawl(getHaltSpecUrl, callback=self.haltCarSpecCallback, save=carModelDict, ) # """ # <div class="information-summary"> # <dl class="information-price"> # ... # <dd class="type"> # <span class="type__item">紧凑型车</span> # """ # carLevelDoc = response.doc("div[class='information-summary'] dl[class='information-price'] dd[class='type'] span[class='type__item']").eq(0) # print("carLevelDoc=%s" % carLevelDoc) # carSeriesLevelName = carLevelDoc.text() # print("carSeriesLevelName=%s" % carSeriesLevelName) # carModelDict["carSeriesLevelName"] = carSeriesLevelName carSeriesContentDoc = response.doc("div[class='series-content']") print("carSeriesContentDoc=%s" % carSeriesContentDoc) # carSpecWrapDoc = carSeriesContentDoc.find("div[class^='spec-wrap']") # carSpecWrapDoc = carSeriesContentDoc.find("div[class^='spec-wrap active']") carSpecWrapListDoc = carSeriesContentDoc.items("div[class^='spec-wrap']") print("carSpecWrapListDoc=%s" % carSpecWrapListDoc) for curSpecWrapIdx, eachSpecWrapDoc in enumerate(carSpecWrapListDoc): print("%s [%d] %s" % ('#'*30, curSpecWrapIdx, '#'*30)) print("eachSpecWrapDoc=%s" % eachSpecWrapDoc) """ <!--即将上市 start--> <div class="spec-wrap active" id="specWrap-1"> <dl class="halt-spec"> <dt> <div class="spec-name"> <span>参数配置未公布</span> </div> <dl class="halt-spec"> <dt> <div class="spec-name"> <span>1.5升 涡轮增压 169马力 国VI</span> </div> """ # dlDoc = eachSpecWrapDoc.find("dl[class='']") # dlDoc = eachSpecWrapDoc.find("dl") dlListDoc = eachSpecWrapDoc.items("dl") print("dlListDoc=%s" % dlListDoc) for curDlIdx, eachDlDoc in enumerate(dlListDoc): print("%s [%d] %s" % ('='*30, curDlIdx, '='*30)) print("eachDlDoc=%s" % eachDlDoc) """ <dt> <div class="spec-name"> <span>1.5升 涡轮增压 169马力 国VI</span> """ dtDoc = eachDlDoc.find("dt") print("dtDoc=%s" % dtDoc) groupSpecNameSpanDoc = dtDoc.find("div[class='spec-name'] span") print("groupSpecNameSpanDoc=%s" % groupSpecNameSpanDoc) carModelGroupName = "" if groupSpecNameSpanDoc: carModelGroupName = groupSpecNameSpanDoc.text() print("carModelGroupName=%s" % carModelGroupName) carModelDict["carModelGroupName"] = carModelGroupName # <dd data-sift1="2020款" data-sift2="国VI" data-sift3="1.5T" data-sift4="7挡双离合" class=""> ddListDoc = eachDlDoc.items("dd") print("ddListDoc=%s" % ddListDoc) for curDdIdx, eachDdDoc in enumerate(ddListDoc): print("%s [%d] %s" % ('-'*30, curDdIdx, '-'*30)) curDdAttr = eachDdDoc.attr # print("curDdAttr=%s" % curDdAttr) carModelYear = curDdAttr["data-sift1"] print("carModelYear=%s" % carModelYear) carModelEmissionStandards = curDdAttr["data-sift2"] print("carModelEmissionStandards=%s" % carModelEmissionStandards) carModelPower = curDdAttr["data-sift3"] print("carModelPower=%s" % carModelPower) carModelGearBox = curDdAttr["data-sift4"] print("carModelGearBox=%s" % carModelGearBox) carModelDict["carModelYear"] = carModelYear carModelDict["carModelEmissionStandards"] = carModelEmissionStandards carModelDict["carModelPower"] = carModelPower carModelDict["carModelGearBox"] = carModelGearBox """ <div class="spec-name"> <div class="name-param"> <p data-gcjid="41511" id="spec_41511"> <a href="/spec/41511/#pvareaid=3454492" class="name">2020款 1.5GDIT 自动铂金舒适版</a> <span class="athm-badge athm-badge--grey is-plain">停产在售</span> <span class="athm-badge athm-badge--orange">特惠</span></p> <p><span class="type-default">前置前驱</span><span class="type-default">7挡双离合</span></p> </div> </div> """ specNameDoc = eachDdDoc.find("div[class='spec-name']") # print("specNameDoc=%s" % specNameDoc) specADoc = specNameDoc.find("p a[class='name']") # print("specADoc=%s" % specADoc) carModelName = specADoc.text() print("carModelName=%s" % carModelName) # 2020款 1.5GDIT 自动铂金舒适版 carModelSpecUrl = specADoc.attr["href"] print("carModelSpecUrl=%s" % carModelSpecUrl) # https://www.autohome.com.cn/spec/41511/#pvareaid=3454492 typeDefaultListDoc = specNameDoc.items("p span[class='type-default']") print("typeDefaultListDoc=%s" % typeDefaultListDoc) typeDefaultList = list(typeDefaultListDoc) print("typeDefaultList=%s" % typeDefaultList) carModelDriveType = "" carModelGearBox = "" if typeDefaultList: spanTypeDefault0 = typeDefaultList[0] print("spanTypeDefault0=%s" % spanTypeDefault0) carModelDriveType = spanTypeDefault0.text() print("carModelDriveType=%s" % carModelDriveType) spanTypeDefault1 = typeDefaultList[1] print("spanTypeDefault1=%s" % spanTypeDefault1) carModelGearBox = spanTypeDefault1.text() print("carModelGearBox=%s" % carModelGearBox) carModelDict["carModelName"] = carModelName carModelDict["carModelSpecUrl"] = carModelSpecUrl carModelDict["carModelDriveType"] = carModelDriveType # 前置前驱 carModelDict["carModelGearBox"] = carModelGearBox # 7挡双离合 """ <div class="spec-guidance"> <p class="guidance-price"> <span>10.40万</span> <a href="//j.autohome.com.cn/pc/carcounter?type=1&specId=41511&pvareaid=3454617"><i class="athm-iconpng athm-iconpng-calculator"></i></a> </p> </div> <div class="spec-guidance"> <p class="guidance-price"> <span><span>暂无</span></span> """ specGuidanceDoc = eachDdDoc.find("div[class='spec-guidance']") # print("specGuidanceDoc=%s" % specGuidanceDoc) guidancePriceSpanDoc = specGuidanceDoc.find("p[class='guidance-price'] span") # print("guidancePriceSpanDoc=%s" % guidancePriceSpanDoc) carModelMsrp = guidancePriceSpanDoc.text() print("carModelMsrp=%s" % carModelMsrp) if "暂无" in carModelMsrp: carModelMsrp = "" print("carModelMsrp=%s" % carModelMsrp) carModelDict["carModelMsrp"] = carModelMsrp self.send_message(self.project_name, carModelDict, url=carModelSpecUrl) @catch_status_code_error def haltCarSpecCallback(self, response): carModelDict = response.save carModelDict = copy.deepcopy(carModelDict) print("carModelDict=%s" % carModelDict) respJson = response.json print("respJson=%s" % respJson) """ [ { "name": "1.5升 涡轮增压 169马力", "speclist": [ { "specid": 36955, "specname": "2019款 红标 1.5GDIT 自动舒适版", "specstate": 40, "minprice": 102000, "maxprice": 102000, "fueltype": 1, "fueltypedetail": 1, "driveform": "前置前驱", "drivetype": "前驱", "gearbox": "7挡双离合", "evflag": "", "newcarflag": "", "subsidy": "", "paramisshow": 1, "videoid": 0, "link2sc": "http://www.che168.com/china/hafu/hafuh6/7_8/", "price2sc": "7.58万", "price": "10.20万", "syear": 2019 }, { "specid": 36956, "specname": "2019款 红标 1.5GDIT 自动都市版", "specstate": 40, "minprice": 109000, "maxprice": 109000, "fueltype": 1, "fueltypedetail": 1, "driveform": "前置前驱", "drivetype": "前驱", "gearbox": "7挡双离合", "evflag": "", "newcarflag": "", "subsidy": "", "paramisshow": 1, "videoid": 0, "link2sc": "", "price2sc": "", "price": "10.90万", "syear": 2019 }, ... """ if respJson: for eachModelGroupDict in respJson: modelGroupName = eachModelGroupDict["name"] modelSpecList = eachModelGroupDict["speclist"] for eachModelDict in modelSpecList: curCarModelDict = copy.deepcopy(carModelDict) carModelYear = "%s款" % eachModelDict["syear"] # carModelSpecUrl = "%s/%s" % (CarSpecPrefix, eachModelDict["specid"]) carModelSpecUrl = self.genSpecUrl(eachModelDict["specid"]) curCarModelDict["carModelGroupName"] = modelGroupName curCarModelDict["carModelYear"] = carModelYear curCarModelDict["carModelEmissionStandards"] = "" curCarModelDict["carModelPower"] = "" curCarModelDict["carModelDriveType"] = eachModelDict["drivetype"] curCarModelDict["carModelGearBox"] = eachModelDict["gearbox"] curCarModelDict["carModelName"] = eachModelDict["specname"] curCarModelDict["carModelSpecUrl"] = carModelSpecUrl curCarModelDict["carModelMsrp"] = eachModelDict["price"] self.send_message(self.project_name, curCarModelDict, url=carModelSpecUrl) |
如此，去批量运行
（注意旧版车系页面不支持，可以自己加代码忽略，而不至于报错
比如：
1 2 3 4 5 6 | foundLevelId = re.search("var\s+levelid\s+=", carSeriesHtml) print("foundLevelId=%s" % foundLevelId) isNewLayoutHtml = bool(foundLevelId) if isNewLayoutHtml: # add above code |
）
最后即可抓包出
- PySpider总运行Url：9365个
- 车型数据总数：31287个
- excel文件：
- 效果截图
转载请注明：在路上 » 【已解决】汽车之家车型车系数据：支持新版车系页面