Home > Net >  Extract POST request from website not working anymore
Extract POST request from website not working anymore

Time:06-16

This question follows an issue I had a few years ago which I posted here Send SQL string through POST with httr package in R.

The basic idea is to use R to download a zip file generated here https://www.transtats.bts.gov/DL_SelectFields.aspx?gnoyr_VQ=FIL&QO_fu146_anzr=Nv4 Pn44vr45.

When accessing the website above, we can select from a table, the variables we want, the year, and month (or all months), and press download. Before, when I right-clicked on the POST line and choose "Copy as cURL", I would get a really nice set of code which I could translate into this:

httr::POST(
  url = "https://www.transtats.bts.gov/DownLoad_Table.asp",
  httr::add_headers(
    Referer = "https://www.transtats.bts.gov/DL_SelectFields.asp?Table_ID=289"
  ),
  body = list(
    UserTableName = "DB1BCoupon",
    DBShortName = "", 
    RawDataTable = "T_DB1B_COUPON",
    sqlstr = " SELECT ORIGIN_AIRPORT_ID,ORIGIN_AIRPORT_SEQ_ID,ORIGIN_CITY_MARKET_ID,DEST_AIRPORT_ID,DEST_AIRPORT_SEQ_ID,DEST_CITY_MARKET_ID FROM T_DB1B_COUPON WHERE Quarter=1 AND YEAR=2018",
    varlist = "ORIGIN_AIRPORT_ID,ORIGIN_AIRPORT_SEQ_ID,ORIGIN_CITY_MARKET_ID,DEST_AIRPORT_ID,DEST_AIRPORT_SEQ_ID,DEST_CITY_MARKET_ID",
    grouplist = "", suml = "",
    sumRegion = "", filter1 = "title=",
    filter2 = "title=", geo = "All\xa0",
    time = "Q 1", timename = "Quarter",
    GEOGRAPHY = "All", XYEAR = "2018",
    FREQUENCY = "1", 
    VarDesc = "ItinID", VarType = "Num", 
    VarDesc = "MktID", VarType = "Num", 
    VarDesc = "SeqNum", VarType = "Num", 
    VarDesc = "Coupons", VarType = "Num", 
    VarDesc = "Year", VarType = "Num", VarName = "ORIGIN_AIRPORT_ID", 
    VarDesc = "OriginAirportID", VarType = "Num", VarName = "ORIGIN_AIRPORT_SEQ_ID", 
    VarDesc = "OriginAirportSeqID", VarType = "Num", VarName = "ORIGIN_CITY_MARKET_ID", 
    VarDesc = "OriginCityMarketID", VarType = "Num", 
    VarDesc = "Quarter", VarType = "Num", 
    VarDesc = "Origin", VarType = "Char", 
    VarDesc = "OriginCountry", VarType = "Char", 
    VarDesc = "OriginStateFips", VarType = "Char", 
    VarDesc = "OriginState", VarType = "Char", 
    VarDesc = "OriginStateName", VarType = "Char", 
    VarDesc = "OriginWac", VarType = "Num", VarName = "DEST_AIRPORT_ID", 
    VarDesc = "DestAirportID", VarType = "Num", VarName = "DEST_AIRPORT_SEQ_ID", 
    VarDesc = "DestAirportSeqID", VarType = "Num", VarName = "DEST_CITY_MARKET_ID", 
    VarDesc = "DestCityMarketID", VarType = "Num", 
    VarDesc = "Dest", VarType = "Char", 
    VarDesc = "DestCountry", VarType = "Char", 
    VarDesc = "DestStateFips", VarType = "Char", 
    VarDesc = "DestState", VarType = "Char", 
    VarDesc = "DestStateName", VarType = "Char", 
    VarDesc = "DestWac", VarType = "Num", 
    VarDesc = "Break", VarType = "Char", 
    VarDesc = "CouponType", VarType = "Char", 
    VarDesc = "TkCarrier", VarType = "Char", 
    VarDesc = "OpCarrier", VarType = "Char", 
    VarDesc = "RPCarrier", VarType = "Char", 
    VarDesc = "Passengers", VarType = "Num", 
    VarDesc = "FareClass", VarType = "Char", 
    VarDesc = "Distance", VarType = "Num", 
    VarDesc = "DistanceGroup", VarType = "Num", 
    VarDesc = "Gateway", VarType = "Num", 
    VarDesc = "ItinGeoType", VarType = "Num", 
    VarDesc = "CouponGeoType", VarType = "Num"
  ), 
  encode = "form",
  query = list(
    Table_ID = "289",
    Has_Group = "0", 
    Is_Zipped = "0"
  )
) -> res

The code used to extract the cURL was this:

library(curlconverter)

straighten() %>% make_req() -> tmp

The new saved res, had binary data which I could easily use to download the zip file generated by the POST.

res
## Response [https://transtats.bts.gov/ftproot/TranStatsData/351117019_T_DB1B_COUPON.zip]
##   Date: 2018-10-14 02:18
##   Status: 200
##   Content-Type: application/x-zip-compressed
##   Size: 14.6 MB
## <BINARY BODY>

However, when I do the same now it's a mess and I can't get anything from it.

httr::VERB(
  verb = "GET", url = "https://www.transtats.bts.gov/DL_SelectFields.aspx",
  query = list(
    gnoyr_VQ = "FIL",
    QO_fu146_anzr = "Nv4 Pn44vr45' -X 'POST' -H 'Accept: text/html,application/xhtml xml,application/xml;q=0.9,*/*;q=0.8' -H 'Content-Type: application/x-www-form-urlencoded' -H 'Origin: https://www.transtats.bts.gov' -H 'Cookie: _ga=GA1.2.279767402.1654087030; _ga_NQ5ZN114SB=GS1.1.1654601577.6.1.1654602173.0; _gat_gtag_UA_18660041_1=1; _gid=GA1.2.975702239.1654601578; f5avr1969959209aaaaaaaaaaaaaaaa_cspm_=DKBJFJCFEDEGJMPHAKDLLGKAOMIGFJJBLFKJJFLCOKMFKOPOIBLJNFBDAENMKNMNNBNCKLDMCJCFKOMIFAFAGDCBBEIKHALBFLPDDHNGGPNBOHCDHALHLHAFCPDCECCK; _gat=1; __utma=261918792.279767402.1654087030.1654149013.1654601578.6; __utmb=261918792.6.10.1654601578; __utmc=261918792; __utmz=261918792.1654087030.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); _ga=GA1.3.279767402.1654087030; _gat_b=1; _gid=GA1.3.975702239.1654601578; has_js=1; QSI_SI_e8TSnTOxZxScWdT_intercept=true; QSI_HistorySession=https://www.transtats.bts.gov/DL_SelectFields.aspx?gnoyr_VQ=GEE&QO_fu146_anzr=Nv4 Pn44vr45~1653914765211|https://www.transtats.bts.gov/DL_SelectFields.aspx?gnoyr_VQ=GEE&QO_fu146_anzr=Nv4 Pn44vr45~1653918802064|https://www.transtats.bts.gov/DL_SelectFields.aspx?gnoyr_VQ=FIL&QO_fu146_anzr=Nv4 Pn44vr45~1653926488227|https://www.transtats.bts.gov/DL_SelectFields.aspx?gnoyr_VQ=FIL&QO_fu146_anzr=Nv4 Pn44vr45~1653933301130|https://www.transtats.bts.gov/DL_SelectFields.aspx?gnoyr_VQ=FJE&QO_fu146_anzr=Nv4Pn44vr45~1653943359984|https://www.transtats.bts.gov/DL_SelectFields.aspx?gnoyr_VQ=FIL&QO_fu146_anzr=Nv4 Pn44vr45~1654090368888|https://www.transtats.bts.gov/DL_SelectFields.aspx?gnoyr_VQ=FIL&QO_fu146_anzr=Nv4 Pn44vr45~1654092812643|https://www.transtats.bts.gov/DL_SelectFields.aspx?gnoyr_VQ=FLM&QO_fu146_anzr=b4vtv0 n0q Qr56v0n6v10 f748rB~1654094623107|https://www.transtats.bts.gov/DL_SelectFields.aspx?gnoyr_VQ=FIL&QO_fu146_anzr=Nv4%Pn44vr45~1654102786829|https://www.transtats.bts.gov/DL_SelectFields.aspx?gnoyr_VQ=FIL&QO_fu146_anzr=Nv4 Pn44vr45~1654601914519; f5avraaaaaaaaaaaaaaaa_session_=PBGOPMEEHCNFKKAPFNCACAKCCBFOPNPHICHCBEFGHCMKMLBFFNNFBOCOFLEKPFCNHNLDMANNOIAOFKNKGMJADPMKGDFMDGGEFHKCCGNOLACEFOLDEKIKCIOLAIIANEKM; ASPSESSIONIDQCQCSDSA=JPCOCLGDHAIJOKGLBBJNAKCN; _ga_TS9639848Y=GS1.1.1654095826.2.0.1654095826.0; ASPSESSIONIDQCSATBTA=PFAPIPGDONFFBLDGBBMOOAJO; ASP.NET_SessionId=wr043omrzfn1emifxmj1wadr; ASPSESSIONIDQCSASBTB=BMMLLHNBPOKMOHFPOHEOJOOB' -H 'Content-Length: 8825' -H 'Accept-Language: en-us' -H 'Host: www.transtats.bts.gov' -H 'User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.2 Safari/605.1.15' -H 'Referer: https://www.transtats.bts.gov/DL_SelectFields.aspx?gnoyr_VQ=FIL",
    QO_fu146_anzr = "Nv4 Pn44vr45' -H 'Accept-Encoding: gzip, deflate, br' -H 'Connection: keep-alive' --data '__EVENTTARGET=chkAllVars",
    `__EVENTARGUMENT` = "",
    `__LASTFOCUS` = "", `__VIEWSTATE` = "s5lt5rBqZX9v/JLyUuO6kxf qIUW68llMVM3sydtYijhto3Fidu3O/WGJ1VjJcRr1BeRbJcXFN89qYPysApyatjfXjGvzeBGgpTbMcIpSxztQwdL/cWbPv4txnZ dOJQer1kYzuvfBl08iyWWck97yWXFANUe7FQ8cv7aw8Wm/8E 7GR9RcvXPAx0sZVlUem/s36TXoDlcTU1PWWNrbpwsQKOlzxG7ZWAfsCwv6/Pdygh0lPmkOBvD UkYBu 2jCGKht/PlZPFap6F2SeORYjnAiXG62IMWa amyOMJZrcWoiGXjooSPdlLgHOGL29OrIBilrLeGMjMAO64FgU1T1L13E0Vwomn1OIpyeAEMZHcVm0DF9ERh5RY3V1IDeUtlmdXKqy3c1GzA2Dkdg PlB4k0gTKgLc9tp82GfwaxgtDuCsDNtwmMcibObF0KPMeCNRov 97YEUY0SJ 6mvPT5XNLYHwO9jEd y3l5TE6qUKKaxv CufxMlTUGyY7ASU3MxC2XvzuwfeudWGUfKmAFC/43fhCpus2s1Ly0yL6bfjhO2S71k2f0KyINFg6aTcMxuL9vwgvNIlGWClZAmk6fmnimNp4GhzsCTUkmVBPckug8P1HG6HEWCin/AG5WXpGBlAl4/UqfTAwh/kO2MJzyrOSySRgo77LfDI87OUSZ9TEd8ZPRIvSROsZLT4h2wG4Hzhkqxrl4WIw3rt8xryG9kjoIpKd5FhjNnhZpVTLKfzuvkc3tcZfmLiy1FY49EwoudWiaNPZsIcz51Ws8ldNi4o EyXkVCZJJFcq3mFAg7iJeKZx6m5tGbAgE5kc1sVbqWvJoQVuz6qKpGbeK jZetVD34aBOKvmOn8FKTIN/n48aeIygD/946cgNI92r2bCU5Wjb0sE4kRWpqQvdPOtLQStK7WqHhAOZhew2oLSuAG44le 03knVl433U4IZq7dJcgkxv uqHK0pCzVf6lAxwhhGEqSQlByAgkXiNSGImxkDASB7uOAbk6Nt9x3CVozQrzSFrTpLE/d9X34qPJMfR67NrriUvAEN0V3DDxIcTFkg0QYskF3DZLRP7zwj9h4Sj tKixAf/jrfP0jE848t1DTiBxgAwS1CkcoBW18M7W9kDtMQzQYKstMNWdpAWvy2qoj6KbbRxFloDrR6OAZuMZphHmZhttHAxqRWwvy9AKfg QAwdKb0ZQUx97AFAonY8Q9nvWx74ww9lzJoHBaz52JxULgBryILXXHDMY68hG3XgmUnrY8mMpZLT42QR4IiLrifRi/AhEpFQ3SELS4w6CIs6V972hOKnfbL2JvPt8K93yuTR2Oz9rG2YbGBf4jIOIj4PvjgJ7uw4B9Fx XGAeM9Y3s5SaQh5jCNmWHa2aUieQV30gFiiT2LXTIi25SL97GIoSiJoqsMzCdk30y77vhIH7b6gKP053PRohNgP3r4WhwOzn6GAA E WyMoz25MJNNk3 4Z8nV4h58jeZb0CGkNvz ORNDYEh3BTtKuqJG1TFvEWIANM U2mLlrxZ8QmBHcadGshIH4OtXBnqThr9KDHCj0KeeET8QsvL/ofQKJkqaChrM3WLBf3LUEpA FmAJIwk27rwz9gArBY/B MwvPEq8Yz cKZhE8Sa7yBCFz7wXIkqdg0szO2ZaFVv2DAPOc7c0gpbVGQPJq64d4IGZ/qbqyf63IreCeh5kClA/ZBzlR5/JsWa9tQ036 kyeptLvxaJpXP78Bm ailFHEmvZmBtnCTDP 1jTi239XRhhg0kBvVTYHn1rLMPz4UZkYtOpUg/lxUGB lunCNo2uaZOe2BGDD3L hcZ4J/ToWY t6/G8lK8LkdkPdn2xSLXSWbbVHv2PbvlxwLmmvvHmA9rsoeQg3LXnEuSvmZhmdv3mFxwA/K/xz5sa  sjeY17pwab84w9ibZ8Bs8k4LrGISybuWHNA7V2VzrcISPHGpE jDN1623cLHCYCKUIbSuIu24zigeE3 FtSwZ9Usjp/40s39UiAJxFfYPBZZvW8BUF2JOY1kVeQ3/PSpGsaM5o8QNl02O/5lUqRNfzubcATxGuBu6AH Dj1nfWwebh5aFwRwo7ZfRWc4SQ6LKUCc/6XZJSSlLL7uAk2laCZ ryvxNqI5Vd1DPNI78JD9IUf0qADvzsiG8eSieCBjf5Um47fq3k19RfGW96ufeO8FOoVNaYjhdaodwTd1BWJAzl/JqBO41LTS8fIzt YkMnjzF1U/gUTN5 Tpx1GS4fuBrNHhbi0lGXbLDTqYkL lx2RoPmLKzKIwGw4r8fjF46SCLewQxv/hkW8d3ClcyrbFDvXWZirfNAIssf1HjF11jfdneyRfa5PDkaR6NhhByL/gBwZim6Jz bFoCORwIeUVFfCP1GmsCFBAPbU3NzDn30GDrfxn8o8LYXmRzRHc32PUDnAkHr/AdOUKzbddptM5oalj1wvuTOLmawT8RrbZUqQptqvmq01MNA3X9EwMFxWfwjsCWrPLXgwioo1NGp5xTheU3tMp/5KY5mus4aHEsPmgeEWByGmJCfoMp /KTtFGhiEvi/jZeo7VEBVfJiaZM4yK uLph6oWbMDLjK7AC1bV1bkdXsW3T700gkr/EpLId2aJ3xVVywDHq4Vl GJNtjaQSNc2UiIrEhAwSLmwxXJxK16fKD7cRwPxy4i X2j8w3oSUnyeepP58OFtpHAMzTfnl6PreLB7Qv0iBIEB7PjT38PDqMiBK5RGbHs MSfaqITFsB/BolvoGsMzCMY/aWdsEu6Kse9Pz UU8bKJda/h K4DTO7dy2OyXJG 4S/MLeYvaGQN 7BXyBY/ECdO7tGsUhtE5PbaPy/bnwg9oRSjPlGuLaC46Y2SmxuE8NtFs6ZK1I1MoLjPzGGf70u3Eou6G9n7spW9fZb2wWgsfjaBqdQLpcgIpBHwjFZCKe6R6wRsTKzAHL9EPQ04WSCr9yHJFOHeQWt7hd3Ba06bN1LkwqSyUISRcWkVKoRvImre7R9arEjRjaB1cQwA3b0ocVlGL81iwSdhrUaat0AkMo8NZst4CMzi6SrIj7yNw3HquMFp97ZHtleKp Ap2TWEwyZYhycS0aaoLqkIYijVP/l0I1 tCQ7jvb9zq1z JJNcnTVIuHu2W/V1fO/vloJ/L4fWMQ9 gEMcgRPwLKrdmJTCFuVUZFREAkxmjJkzkxmcQiZbIlP1ws89CCaEr7PUy93BZNxSpS4aKHRxQiy3LSpkibaZeVaxiJ4xQo7hmG6tPd1uoGkDTbn1Qkav75DiHxUkTfsLNGZkopMrWZnqP9vur qf2DUljUbYg0q1Vw7WpImiaXP3u7UPB9/CKUENV8yNdxZaz7wvyzrdaO71r8CiipXddoJl3VydnAJj11yR26hms/68M/n/BHSGx06xiSENKW 4LiiucR4uEd8a3sxWR wefSaWPXL7j0aDktHrJ O0NwJoTaBL8kitE0jkULTQY0poGPkr/YPbMHCklryFlFBbDPXUZD2sWqTsvYbDw 13m1vzL2QrFSBBY95OwjEnTfRycvC8amXGs32yD6mx6CTPTnS65OTIdNxes69/lJWlbRY9zZHUaKM3OVxPhAdpQb0syL2manh8qongwLD1IFYg72ijzX5xZB/NfSupvDq3jdmzm/hN/vZhUhi8oM4DgAS7U5W2PgQh43bc vJLylzUrRLi3u2p qgyuZobE5LsgpJULC85wjyJnVDAHCSMSIOxammFJApQY6ZNlV aPXM52D5rKOC WAAD4D0PABGn8e zIV3rvZy2Scv8BqbVtVrBWNT4OmR52/z4a8EixCU6a2SS2OZvw5Mnmow9fnooodw261ff58NX64MLuzo082u7VaGCTGMpMePjB1JqdhFq5iUdmt1nWRa74kdnzM Sw8NZ2yfDdXN9sXTshz9fCYO9w/sfXxHMYUoytcPE4D6/Bu17eqrJv4c0BBwDjkpXAW4KMemKCE1Cph0VeaiQkaFKhxoYCyo3ATHO6B2Neck8r11QbHZes/UfNuIv4XVkI5pJQo74KwezFh1gYyrKd4TJXpFpP eH3QY1GcxAJ6ZIf/Rj7CUU2e1 PUPNROpZpElnkavU/7ezbBwGPhDYEVALA/jFiPW0qChhlhlo7PJeJIzeXXIgBH G7DF9Y827mE8Ifl42cd2AxZiYqKa3f0/vTcqoFLEN4gSkHwkXJeNpQHu0wuzWbLzrkPXk7sz1VAR9cgFDIouWuBcD1ru5aMbQX4yN NDqQw0V3f0eCybatrxa2LKoR/L3wI4KxfPTspQUzEBTy9yX7bPnTMWUPxJAkAFjM/iIcrycYkgpgDpuY1ZBlOezTZm2RvM77WvolD qceeawfy/k9M8CMPpDh4JOnoyJF/W3cG54zcqj jVpfuhUTwfJeS14M9 ECEG eAbOwhYZIfE6pxgl7iIu7ydy6xnUdtKr7e92BxIcV848pu6yOyDpU3ovikh5rzJScih hXoukbkvi2azQWr9/NBP g13GAnNCu8kuTdvI29t358QwW7XAXFZvpu/jT33bEbF5lAjfgzSmC8EW1KpVvvrecpQG8jY/40Vcrg1HKEI2v/wgRFJHMCSE5ndjWXb0O8Km3KEbethBIQ73kqH8T7SowC9YEzqb4X5p5wcRj K9h7F XDgAP/c4sMQoowu3AINx7nwwM7e/52To9zP/Rv3lNMOPJDMheqx3Oh0TCNFU81zNYTXq6JbQoWd5Xn7kdnITrrvMr4aKDNNqOjr1YGWEfc1avlZ1Q3BI9skychiDGQrXH6wF5Q 3maWT4XIb5RBJV9Q556qqKm2OM1sDFjWWAJMz5oaBlZx8yybn2EFsSeVxLnnkEs2I3",
    `__VIEWSTATEGENERATOR` = "82CE8F70",
    `__EVENTVALIDATION` = "P8zqeK87DbezpJjSLiKpZ8OpZeoEr3iYiM856mfjXSxKDLh9yCTKYoB6C1bfipflE3CAUBAz/vHfCJcTC6wWr6PWoOLYqs1r9V75cs/zMS68Wc0O/5tYdH3Yi 56B0ZU/sb4qkLi0uIts16qnMye/H74uOplOooYSraTsfw3cG7/ysjjPjPqZbBVtL8sKbZcVXAvO2F6wg5dcpaiONg8RB6qhSodJHULBb9LLfi3UMpRtrN1hi/1I27XJ2MDZWajQdnQcvgqFga S14Y4uNU86BuzdasoyCMTc5SZ7nynyM0NE6xemPHyF9yyf2w7nTap46hmYWxn4SYEsor3Hclu5Tge9zrJPrABjIOh/q19dHwwe/9LZ4SGVelAqxRkZCuTAwuiqi2xLqty3m71EPGEbXKqDYG/ghH6HzXBAC2CFJNvoOiDaQBc kt1gBGHrv6KIMGL3Morbo4hDkaZA2BqeZFQvw63mVAcXfNyimBMCiVC t2y2BN o69EPsIQufSA k8W4lu0WgR2c8FdUBnD8gs//JsaYBTjj XDGuY2q4rYSuJNVkg/dwjjrz6rieOIsyzUBlbSUX8n msll32 VE2Cxn4G36m4YO Fn4gKyije2trLx2im4wgW2zbtCGbIt1L/jRW7U6ZAEiCHBU1tiIi52BD2mqOuxabo  /ua PdOz1PxUOAQY2Rw pqmZTLdJPY2Yu2lEU2Lp5I9lEyI09IXW6cQpqqo1DyoadurgTVpdao9oCIQBwueyWjgdpK9K7ygOA2rNteAwd1U6SXQVRuqOeGbTuh lZWxCdLwen16bibjrlzB5HMNHOnf7DfQqJsgmuAZFKriFR4CX08DBjNK9MVEVzx6a Lzm6t8W3y8xpU31wmf ZakgJ4WFz05WPdhnM9aUcCjBZUozO1RCA9QDrp6lCGGTdjK3D975reuwN Lax1aryT/DjCIYs/yHk7qIAmJ4mEjQfhJQgADxOZcM7qGNHCV 9lT 5hKY8xtosIdt/8/DFRGuZlhyvL4mxrrcmMb3aaDqnbFXiPTqAMseN3Tp39yxpEBuJhlwnF9M1bGMJsTccCrPj/1zN7xrVsmCr4ie7WOSwj1Egeop/mZv2KKIEskQhvul7 z7rcZLgGOhpzFpAr3xLpdkSLi0Ktg6fFd3g6KihofBmaktDlqSYnsOYyRphl4N QqDI5l3WOp3xDrD9jfP7 hNn2TwNsm/MdaI8hm0pthQ4YnLlj2gbtw H9IduHlwrmpl4mp5EoeG44OCSS7kvMtWmmwIKVZf/ZnViNRNvpEkeBlMIlYi5zCdKBD4WinvIWXZIKCrug07apQ55x NyS/ei0s8XHGOGFMulyXHPESsEbOQdSeSxZggCGusE4FtvyVZ9XbRvS5yrdmz2XXZgkUQIVLyxG0tWeJIp45qnEMuJfRvYDVRVAW7HuMfZ4hWF6Rs9sT03ijh8tXEX0CQNLWI5iHxHOj3R8uZ4RBj3yRsKHWNBpiJXDsUYbZEg2wVUzc0d7ErJUwlJ5MbEubCRxO8hE7JX29OKymmC9FjrImmNkM75Hyg5QEyVQUMe9MKi6Li4MNDDueYvPVRzs 7MoDineqHaZSBbw1MZ7ur6 QnbERBWd9lXrzxmZ2d2bsISHZieG49Y6yr38wSIX8Kdftl2CiA7zNvaWcxs0AnKYRsWLp2okRr4lA8qVp07wOiX4H2vH5wy494cY49jE8AA1Aqtg76WwIZeLFaFAxjnNXasGBWZSpbEky1H957jcYHSTiG5u3o7kwKANnWgiR9SbOvdfrsYOUxjEysFHaf4j7CVeyF1TiQrZsDb 9nQtTbVFkmimgYy/zm2sSZSqc1DaYMIfq1rykRljKkJbfsFY2JnneCQYjK4gIYzj4fw2Gzpum5Jhg1tj8W8GqMpwOpks4jAggjAIFWHNiO4z9IhBl7B1/4QmV97xn7oncH1n5py2fyf46dafVGO9LWoyujRot0Ndab6P3M9TJpPdhzaKuzpT2M4jROFllyy8EtBaBjFZeEcU8zb7YR1nebNl2Jr3LETibV2vjmcfs/dvU4XqvX9cjG8K7rVp1sX51f7nD2aOLsysHowxC27Lg1FMXY7b7irdYRONeoa4ecWNop75j/FOLmFza4 4HQUxXQf8b5JBhzEswdTX JIgAIJTx7YmZOs30G8Ffu9fdN4ne0Wu6tdLRLhaUOaNJ69H77Eq3VvMVfU4FJKU6he fRqIwHUMMD196d3/h2P EG5nps9heqmlXwnG9zyYG4767E84Qm 5mNq/XOMaVoyB v3FcFjGmNQ8MGUKnahH8dORAkOuw 17wZW4RI6JsuDxIoGbkuwwsOnK7SgXs34QWbORSbFDs0HImlEADpzIS2aGVvTQJgVKCQYiKvWXU10 Jd1ZUiMy0yHcihFRkgnpL F nVeJSfW/AuyHUVuj7H3ueMoGUy86NDc5Cb6FrWVsjnsIOjI 61E5t9O4okI3AwwmxdA5x4lVYJBxlyXMzprZCgaHowTK4JCQvwbAnuzAsYss/W0xXtmFNVVZCEYhGnRhi7ZiHTIuDlAi4puVYi1gfsU JPcyAVDej13CSrSZGE8fhwhQwNb/YMobr2tDA0MiJR7VXPRbfksbbLYkA8/ukFvYzokU7fQWzcIImYdN4hUEUoSEq/d1BC4UxKFph UCXz/guz6lFJy4m0s7SGp5Rt3XDSHZEV/flFjSWK0QsJ NLOQ cUmbP1Ftp1kzc7Qk4c3mWflvun H8Y98mJqntquxAMrCbyQENnFcEMhR7hq5fA5VkEwO2Ks3JKdwR690C9E6dSeYl1Z5IlK4SzYpsCU/mv2iZ5Mv/ALdOX3t2vLTedH4pAqbO1 x8HQP0IOxJOpxpQiv8CbBpkCRNvQGhESuWGgloGXag0GRnJd1LqLak1aowvcGEJmVI3Z01Kg9OJwFyaLamVWZx9t4GfCBPkXK3Ep8sW8uvARqxolVuuK1fNeJwFAD05a8VqKnD30Fe7Bn5oI0CLwiIsB8Ou7W5yExnBHmBTyeNzMP/0qeo6PTCbH88UrD9DPPXWMFXWvR7cXpAeSRsAHjtbVPwFq3bNxEunExbP54adWifEPsQs7zmBf8xQV2W1F2Rd1wmJ7DvfhwyVyITcUGig4/WcBHkEFHtCHuQvNzWTePbP5osJgeM pTDU=",
    txtSearch = "", cboGeography = "All",
    cboYear = "2022", cboPeriod = "All",
    chkAllVars = "on", UNIQUE_CARRIER = "on",
    UNIQUE_CARRIER_NAME = "on",
    ORIGIN_AIRPORT_ID = "on",
    ORIGIN = "on", DEST_AIRPORT_ID = "on",
    DEST = "on", MONTH = "on"
  )
) -> res

In fact, when trying to run that res, it won't get any zip file anymore, and I suspect that it's due to this __EVENTVALIDATION and/or the __VIEWSTATE. I've been reading a lot about it, but I still can't figure out how to get around it so I can download the zip file from R.

CodePudding user response:

Fixed by doing this. I'm not sure why is it that I need a second request. One with GET and one with getURL. It seems that not having the GET request doesn't create a cookie for some reason. However, it works. But if someone could explain why, this would be amazing.

curl <- getCurlHandle()
    curlSetOpt(cookiejar = paste(tempdir(), "/", "cookies.txt", sep = ""),
               followlocation = TRUE, autoreferer = TRUE, curl = curl)

    message("Connecting to T100")
    html <- getURL("https://www.transtats.bts.gov/DL_SelectFields.aspx?gnoyr_VQ=FIM&QO_fu146_anzr=Nv4%Pn44vr45", curl = curl)
    temp <- GET("https://www.transtats.bts.gov/DL_SelectFields.aspx?gnoyr_VQ=FIM&QO_fu146_anzr=Nv4%Pn44vr45", curl = curl)
    message("Done")

    viewstate <- as.character(sub('.*id="__VIEWSTATE" value="([0-9a-zA-Z /=]*).*', '\\1', html))
    viewstategenerator <- as.character(sub('.*id="__VIEWSTATEGENERATOR" value="([0-9a-zA-Z /=]*).*', '\\1', html))

    eventvalidation <- as.character(sub('.*id="__EVENTVALIDATION" value="([0-9a-zA-Z /=]*).*', '\\1', html))

    message("Downloading file")

    httr::POST(
      config = progress(),
      url = "https://www.transtats.bts.gov/DL_SelectFields.aspx?gnoyr_VQ=FIM&QO_fu146_anzr=Nv4 Pn44vr45",
      httr::add_headers(
        Referer = "https://www.transtats.bts.gov/DL_SelectFields.aspx?gnoyr_VQ=FIM&QO_fu146_anzr=Nv4%Pn44vr45"
      ),
      body = list(
        '__EVENTARGUMENT' = "",
        '__LASTFOCUS' = "",
        "__VIEWSTATE" = viewstate,
        '__VIEWSTATEGENERATOR' = viewstategenerator,
        '__EVENTVALIDATION' = eventvalidation,
        txtSearch = "",
        btnDownload = "Download",
        cboGeography = "All",
        cboYear = y,
        cboPeriod = "All",
        chkAllVars = "on",
        UNIQUE_CARRIER = "on",
        UNIQUE_CARRIER_NAME = "on",
        ORIGIN_AIRPORT_ID = "on",
        ORIGIN = "on",
        DEST_AIRPORT_ID = "on",
        DEST = "on",
        MONTH = "on"

      ),
      encode = "form", query = list(
        gnoyr_VQ = "FIM",
        QO_fu146_anzr = "Nv4 Pn44vr45"
      ),
      postData = list(
        text = paste("__EVENTTARGET=&__EVENTARGUMENT=&__LASTFOCUS=&__VIEWSTATE=", viewstate,
                     "&__VIEWSTATEGENERATOR=", viewstategenerator,
                     "&__EVENTVALIDATION=", eventvalidation,
                     "&txtSearch=&cboGeography=All&cboYear=",y,"&cboPeriod=All&btnDownload=Download&UNIQUE_CARRIER=on&UNIQUE_CARRIER_NAME=on&ORIGIN_AIRPORT_ID=on&ORIGIN=on&DEST_AIRPORT_ID=on&DEST=on&MONTH=on",
                     sep = "")
      )
    )
  • Related