xml_parsing_via_api
Differences
This shows you the differences between two versions of the page.
| Next revision | Previous revision | ||
| xml_parsing_via_api [2024/11/28 01:30] – created hkimscil | xml_parsing_via_api [2024/12/03 22:20] (current) – hkimscil | ||
|---|---|---|---|
| Line 1: | Line 1: | ||
| < | < | ||
| + | library(XML) | ||
| + | library(httr) | ||
| + | library(tidyr) | ||
| + | library(tidyverse) | ||
| + | |||
| searchPeople <- " | searchPeople <- " | ||
| KEY <- ' | KEY <- ' | ||
| Line 9: | Line 14: | ||
| spRes <- GET(url, query= list(" | spRes <- GET(url, query= list(" | ||
| spRes | spRes | ||
| - | spParsed <- xmlParse(sres) | + | spParsed <- xmlParse(spRes) |
| spParsed | spParsed | ||
| xmlPeople <- getNodeSet(spParsed, | xmlPeople <- getNodeSet(spParsed, | ||
| Line 17: | Line 22: | ||
| filmCh <- xmlToDataFrame(xmlFilm, | filmCh <- xmlToDataFrame(xmlFilm, | ||
| filmCh | filmCh | ||
| + | View(filmCh) | ||
| + | |||
| - | library(tidyr) | ||
| films <- filmCh | films <- filmCh | ||
| films %> | films %> | ||
| mutate(text = strsplit(as.character(text), | mutate(text = strsplit(as.character(text), | ||
| unnest(text) | unnest(text) | ||
| + | |||
| fs <- mutate(films, | fs <- mutate(films, | ||
| fs <- unnest(fs, text) | fs <- unnest(fs, text) | ||
| Line 30: | Line 37: | ||
| fs[1,] | fs[1,] | ||
| + | ################################## | ||
| sFilms <- " | sFilms <- " | ||
| Line 47: | Line 55: | ||
| xmlF | xmlF | ||
| filmId <- xmlToDataFrame(xmlId, | filmId <- xmlToDataFrame(xmlId, | ||
| + | filmId | ||
| + | colnames(filmId) <- " | ||
| filmId | filmId | ||
| filmN <- xmlToDataFrame(xmlF, | filmN <- xmlToDataFrame(xmlF, | ||
| + | colnames(filmN) <- " | ||
| filmN | filmN | ||
| str(filmN) | str(filmN) | ||
| - | fg <- data.frame(filmId, filmN) | + | fg <- cbind(filmId, filmN) |
| fg | fg | ||
| - | fg <- unnest(fg, | + | fg <- unnest(fg, |
| fg | fg | ||
| + | |||
| + | ############### | ||
| sFd <- " | sFd <- " | ||
| KEY <- ' | KEY <- ' | ||
| filmId[1,] | filmId[1,] | ||
| - | name <- fg$text[1] | + | fg$filmId[1] |
| - | name | + | fg$film[1] |
| - | # name <- iconv(name, to=" | + | id <- fg$filmId[1] |
| + | id | ||
| url < | url < | ||
| url | url | ||
| - | sfdr <- GET(url, query= list(" | + | sfdr <- GET(url, query= list(" |
| sfdr | sfdr | ||
| sfdrP <- xmlParse(sfdr) | sfdrP <- xmlParse(sfdr) | ||
| Line 71: | Line 85: | ||
| xmlA <- getNodeSet(sfdrP, | xmlA <- getNodeSet(sfdrP, | ||
| xmlA | xmlA | ||
| + | |||
| actor <- xmlToDataFrame(xmlA, | actor <- xmlToDataFrame(xmlA, | ||
| actor | actor | ||
| + | colnames(actor) <- " | ||
| + | actor | ||
| + | |||
| + | |||
| dir | dir | ||
| - | mv <- fg$text.1[1] | + | mv <- fg$film[1] |
| - | dtoa <- data.frame(dir, | + | mv |
| + | dtoa <- data.frame(dir, | ||
| dtoa | dtoa | ||
| write.csv(dtoa, | write.csv(dtoa, | ||
| - | |||
| </ | </ | ||
xml_parsing_via_api.1732757423.txt.gz · Last modified: by hkimscil
