python爬虫

拼搏现实的明天。 2022-02-21 09:14 339阅读 0赞

# from bs4 import  BeautifulSoup
    # import requests
    # url="https://www.tripadvisor.cn/Attractions-g60763-Activities-oa30-New_York_City_New_York.html#FILTERED_LIST"
    # headers={
    #  'user-agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Mobile Safari/537.36',
    #  'cookie':'ServerPool=R; TART=%1%enc%3ApZKvMxq7NP0fj9JmIgXfSgresnokkPS4mgblLnmeTjpoxuvGONo7PehLpsjT0J1ztkxpre72JQY%3D; TAUnique=%1%enc%3Ak51%2FDnpdhzZvh5GqlfOESeNS7yPl3EufT0qz%2Blgg1PtZDUlyGj4a2Q%3D%3D; TASSK=enc%3AAEbWWzwAqWLup%2BU8JJUsm7R4U5raO%2Br63n9nsCJ0sufWoBiVKLKbDMJOATMGuF1AX0jOaXsYcSymuRzme25iTMXe0T%2BytJ4eZ2d3CB1FQcVkMlga1ReTRm3qYRV%2BQv87%2Bw%3D%3D; _gcl_au=1.1.292633309.1554780156; _ga=GA1.2.862947117.1554780156; _gid=GA1.2.1218858504.1554780156; _smt_uid=5cac0ffd.bd1386a; __gads=ID=08f38286e6c31954:T=1554780155:S=ALNI_MZhKY7-6Xp5bPCZ4Waa75KWTXKSwg; TAReturnTo=%1%%2FAttractions-g60763-Activities-oa30-New_York_City_New_York.html; CM=%1%PremiumMobSess%2C%2C-1%7Ct4b-pc%2C%2C-1%7CRestAds%2FRPers%2C%2C-1%7CRCPers%2C%2C-1%7CWShadeSeen%2C%2C-1%7CTheForkMCCPers%2C%2C-1%7CHomeASess%2C1%2C-1%7CPremiumSURPers%2C%2C-1%7CPremiumMCSess%2C%2C-1%7CRestPartSess%2C%2C-1%7CUVOwnersSess%2C%2C-1%7CCCUVOwnPers%2C%2C-1%7CRestPremRSess%2C%2C-1%7CCCSess%2C%2C-1%7CCYLSess%2C%2C-1%7CPremRetPers%2C%2C-1%7CViatorMCPers%2C%2C-1%7Csesssticker%2C%2C-1%7C%24%2C%2C-1%7CPremiumORSess%2C%2C-1%7Ct4b-sc%2C%2C-1%7CRestAdsPers%2C%2C-1%7CMC_IB_UPSELL_IB_LOGOS2%2C%2C-1%7Cb2bmcpers%2C%2C-1%7CPremMCBtmSess%2C%2C-1%7CPremiumSURSess%2C%2C-1%7CMC_IB_UPSELL_IB_LOGOS%2C%2C-1%7CLaFourchette+Banners%2C%2C-1%7Csess_rev%2C%2C-1%7Csessamex%2C%2C-1%7CPremiumRRSess%2C%2C-1%7CTADORSess%2C%2C-1%7CAdsRetPers%2C%2C-1%7CTARSWBPers%2C%2C-1%7CSPMCSess%2C%2C-1%7CTheForkORSess%2C%2C-1%7CTheForkRRSess%2C%2C-1%7Cpers_rev%2C%2C-1%7Cmds%2C%2C-1%7CSPMCWBPers%2C%2C-1%7CRBAPers%2C%2C-1%7CRestAds%2FRSess%2C%2C-1%7CHomeAPers%2C%2C-1%7CPremiumMobPers%2C%2C-1%7CRCSess%2C%2C-1%7CLaFourchette+MC+Banners%2C%2C-1%7CRestAdsCCSess%2C%2C-1%7CRestPartPers%2C%2C-1%7CRestPremRPers%2C%2C-1%7CCCUVOwnSess%2C%2C-1%7CUVOwnersPers%2C%2C-1%7Csh%2C%2C-1%7Cpssamex%2C%2C-1%7CTheForkMCCSess%2C%2C-1%7CCYLPers%2C%2C-1%7CCCPers%2C%2C-1%7Cb2bmcsess%2C%2C-1%7CSPMCPers%2C%2C-1%7CPremRetSess%2C%2C-1%7CViatorMCSess%2C%2C-1%7CPremiumMCPers%2C%2C-1%7CAdsRetSess%2C%2C-1%7CPremiumRRPers%2C%2C-1%7CRestAdsCCPers%2C%2C-1%7CTADORPers%2C%2C-1%7CTheForkORPers%2C%2C-1%7CPremMCBtmPers%2C%2C-1%7CTheForkRRPers%2C%2C-1%7CTARSWBSess%2C%2C-1%7CPremiumORPers%2C%2C-1%7CRestAdsSess%2C%2C-1%7CRBASess%2C%2C-1%7CSPORPers%2C%2C-1%7Cperssticker%2C%2C-1%7CSPMCWBSess%2C%2C-1%7C; MobileLastViewedList=%1%%2FAttractions-g60763-Activities-oa30-New_York_City_New_York.html; VRMCID=%1%V1*id.12019*llp.%2FAppLink-a_source%5C.android-a_url%5C.__2F__Attractions__2D__g60763__2D__Activities__2D__oa30__2D__New__5F__York__5F__City__5F__New__5F__York__2E__html-m12019*e.1555398729910; interstitialCounter=-1; _gat_UA-79743238-4=1; TASession=%1%V2ID.E825B3497E68A74689C607C851CA4029*SQ.64*MC.12019*LR.https%3A%2F%2Fwww%5C.tripadvisor%5C.cn%2FAttractions-g60763-Activities-oa30-New_York_City_New_York%5C.html*LP.%2FAppLink-a_source%5C.android-a_url%5C.__2F__Attractions__2D__g60763__2D__Activities__2D__oa30__2D__New__5F__York__5F__City__5F__New__5F__York__2E__html-m12019*LS.MobileAttractions*GR.22*TCPAR.22*TBR.46*EXEX.60*ABTR.27*PHTB.74*FS.13*CPU.35*HS.recommended*ES.popularity*DS.5*SAS.popularity*FPS.oldFirst*LF.zhCN*FA.1*DF.0*RT.0*FLO.60763*TRA.false*LD.60763; TATravelInfo=V2*A.-1*MG.-1*HP.2*FL.3; TAUD=LA-1554780153284-1*RDD-1-2019_04_08*LD-13999636-.....*LG-13999639-0.0.F.; roybatty=TNI1625!AP5Y%2Fs2WogWAuJ6bxCYafswveOkZdVLiVVE1IykAdQm7JYc7EFXooQLVvlIFOdTZEKyKMDR2wqNoaXKNAwcMmrAr3rgIdTqlM5hL0XuCTiXoh0S7NXDnjRrsSVILcQDvu7mxL6secHb%2FgXChYpKjgDFf%2BgIVk8qhaijk%2B2t3oOie%2C1; NPID=0'
    #  }
    # wb_data=requests.get(url,headers)
    # soup=BeautifulSoup(wb_data.text, 'html.parser')
    # print(soup)
    # # select = soup.select('div.centering_wrapper > img')
    # imgs = soup.select('div.thumb thumbLLR soThumb > img')
    # for img in imgs:
    #     print(img)