library(httr)
library(stringi)
res <- httr::GET("https://water.ca.gov/-/media/DWR-Website/Web-Pages/Programs/State-Water-Project/Operations-And-Maintenance/Files/Operations-Control-Office/Project-Wide-Operations/Dispatchers-Monday-Water-Report.txt?la=en&hash=B8C874426999D484F7CF1E9821EE9D8C6896CF1E")
l <- stri_split_lines(content(res))[[1]]
page_breaks <- which(stri_detect_fixed(l, "SUMMARY OF SWP"))
# target page 1
page_one <- l[1:(page_breaks[2]-1)]
# find all the records on the page
recs <- paste0(page_one[stri_detect_regex(page_one, "^[[:alpha:]].*[[:digit:]]\\.")], collapse="\n")
# read it in as a fixed-width text file (b/c it really kinda is)
read.fwf(
textConnection(recs),
widths = c(10, 7, 8, 7, 7, 8, 8, 5, 7, 6, 7),
stringsAsFactors = FALSE
) -> xdf
# clean up the columns
xdf[] <- lapply(xdf, stri_trim_both)
xdf[] <- lapply(xdf, function(x) ifelse(grepl("\\.\\.|DCTOT", x), "NA", x)) # replace "....."s and the "DCTOT" string with "NA" so we can do the type conversion
xdf <- type.convert(xdf)
colnames(xdf) <- c("reservoir", "abs_max_elev", "abs_max_stor", "norm_min_elev", "norm_min_stor", "elev", "stor", "evap", "chng", "net_rel", "inflow")
xdf$reservoir <- as.character(xdf$reservoir)
Что дает нам:
xdf
## reservoir abs_max_elev abs_max_stor norm_min_elev norm_min_stor elev stor evap chng net_rel inflow
## 1 FRENCHMN 5588.0 55475 5560.00 21472 5578.67 41922 NA -53 NA NA
## 2 ANTELOPE 5002.0 22564 4990.00 12971 4994.64 16306 NA -46 NA NA
## 3 DAVIS 5775.0 84371 5760.00 35675 5770.22 66299 NA -106 NA NA
## 4 OROVILLE 901.0 3553405 640.00 852196 702.69 1275280 249 -4792 6018 1475
## 5 F/B 225.0 11768 221.00 9350 224.52 11467 NA -106 NA NA
## 6 DIV 225.0 13353 221.00 12091 224.58 13217 NA -48 NA NA
## 7 F/B+DIV 225.0 25120 221.00 21441 NA 24684 NA -154 NA NA
## 8 AFTERBAY 136.0 54906 124.00 15156 132.73 41822 NA -263 5372 NA
## 9 CLIF CT 5.0 29082 -2.00 13965 -0.72 16714 NA 194 NA 5943
## 10 BETHANY 243.5 4894 241.50 4545 243.00 4806 NA 0 NA NA
## 11 DYER 806.0 545 785.00 90 795.40 299 NA -21 NA NA
## 12 DEL VALLE 703.0 39914 678.00 24777 690.22 31514 NA -122 97 0
## 13 TEHACHAPI 3101.0 545 3097.00 388 3098.22 434 NA -25 NA NA
## 14 TEHAC EAB 3101.0 1232 3085.00 254 3096.64 941 NA -39 NA NA
## 15 QUAIL+LQC 3324.5 8612 3306.50 3564 3318.18 6551 NA -10 0 NA
## 16 PYRAMID 2578.0 169901 2560.00 147680 2574.72 165701 25 -1056 881 0
## 17 ELDRBERRY 1530.0 27681 1490.00 12228 1510.74 19470 NA 805 0 0
## 18 CASTAIC 1513.0 319247 1310.00 33482 1491.48 273616 36 -1520 1432 0
## 19 SILVRWOOD 3355.0 74970 3312.00 39211 3351.41 71511 10 276 1582 107
## 20 DC AFBY 1 1933.0 50 1922.00 18 1932.64 49 NA 0 NA NA
## 21 DC AFBY 2 1930.0 967 1904.50 198 1922.01 696 NA 37 1690 NA
## 22 CRAFTON H 2925.0 292 2905.00 70 2923.60 274 NA -2 NA NA
## 23 PERRIS 1588.0 126841 1555.30 60633 1577.96 104620 21 85 8 NA
## 24 SAN LUIS 543.0 2027835 326.00 79231 470.16 1178789 238 3273 -4099 0
## 25 O'NEILL 224.5 55076 217.50 36843 222.50 49713 NA 2325 NA NA
## 26 LOS BANOS 353.5 34562 296.00 8315 322.87 18331 NA -5 0 0
## 27 L.PANOCHE 670.4 13233 590.00 308 599.60 664 NA 0 0 0
## 28 TRINITY 2370.0 2447656 2145.00 312631 2301.44 1479281 NA -1192 NA NA
## 29 SHASTA 1067.0 4552095 828.00 502004 974.01 2300953 NA -6238 NA NA
## 30 FOLSOM 466.0 976952 327.80 84649 408.50 438744 NA -2053 NA NA
## 31 MELONES 1088.0 2420000 808.00 300000 1031.66 1779744 NA -2370 NA NA
## 32 PINE FLT 951.5 1000000 712.58 100002 771.51 231361 NA 543 508 NA
## 33 MATHEWS 1390.0 182569 1253.80 3546 1352.17 94266 NA 522 NA NA
## 34 SKINNER 1479.0 44405 1393.00 0 1476.02 38485 NA 242 NA NA
## 35 BULLARDS 1956.0 966103 1730.00 230118 1869.01 604827 NA -1310 NA NA
Это было легко: -)
Большую часть страницы 2 можно выполнить довольно просто и просто:
page_two <- l[page_breaks[2]:length(l)]
do.call(
rbind.data.frame,
lapply(
stri_split_fixed(
stri_replace_all_regex(
stri_trim_both(page_two[stri_detect_regex(
stri_trim_both(page_two), # trim blanks
"^([^[:digit:]]+)([[:digit:]\\.]+)[[:space:]]+([^[:digit:]]+)([[:digit:]\\.]+)$" # find the release rows
)]),
"[[:space:]]{2,}", "\t" # make tab-separated fields wherever there are 2+ space breaks
), "\t"),
function(x) {
if (length(x) > 2) { # one of the lines will only have one record but most have 2
data.frame(
facility = c(x[1],x[3]),
amt = as.numeric(c(x[2], x[4])),
stringsAsFactors = FALSE
)
} else {
data.frame(
facility = x[1],
amt = as.numeric(x[2]),
stringsAsFactors = FALSE
)
}
})
) -> ydf
Что дает нам (без почти бесполезных TOTAL строк):
ydf[!grepl("TOTAL", ydf$facility),]
## facility amt
## 1 KESWICK RELEASE TO RIVER 15386.0
## 2 SHASTA STORAGE WITHDRAWAL 8067.0
## 3 SPRING CREEK RELEASE 0.0
## 4 WHISKYTOWN STORAGE WITHDRAWAL 46.0
## 6 OROVILLE STORAGE WITHDRAWL 5237.0
## 7 CDWR YUBA RIVER @ MARYSVILLE 0.0
## 8 FOLSOM STORAGE WITHDRAWAL 1386.0
## 9 LAKE OROVILLE 20.2
## 10 BYRON BETHANY I.D. 32.0
## 11 POWER CANAL 0.0
## 12 SAN LUIS TO SAN FELIPE 465.0
## 13 SUTTER BUTTE 922.0
## 14 O'NEILL FOREBAY 2.0
## 15 LATERAL 0.0
## 16 CASTAIC LAKE 1432.0
## 17 RICHVALE 589.0
## 18 SILVERWOOD LAKE TO CLAWA 7.0
## 19 WESTERN 787.0
## 20 LAKE PERRIS 0.0
## 23 D/S FEATHER R. DIVERSIONS 0.0
## 24 FISH REQUIREMENT 1230.0
## 25 FLOOD CONTROL RELEASE 0.0
## 26 DELTA REQUIREMENT 3629.0
## 27 FEATHER R. RELEASE @ RIVER OUTLET 3074.0
## 28 OTHER RELEASE 0.0
Но, если вам нужны дельты или данные о работе установки, вы сами.