I want to scrape the player data table from the following URL:
https://www.transfermarkt.de/mamadou-doucoure/profil/spieler/340480
Here's what I coded:
x <- read_html(url) %>%
html_node(xpath = '//div[@class="row collapse"]') %>%
html_table(fill = TRUE) %>%
as.data.frame() %>%
set_names(.,letters[1:ncol(.)])
As far as I understand, the player data isn't classed as a table, and I don't know how to edit the code. Also, I want to have the output in a data frame.
Dataframe could have many forms, having that player table in dataframe as-is might not be the most practical way, though here are a few examples. Some parts are bit tricky and solving those correctly depends on context and objective (e.g. multiple nationalities that currently end up as a single collapsed value)
library(rvest)
library(dplyr, warn.conflicts = F)
library(tidyr)
library(stringr)
url <- "https://www.transfermarkt.de/mamadou-doucoure/profil/spieler/340480"
html <- read_html(url)
# most basic aproach to extract just what's in the table + player name:
df_01 <- tibble(
feature = html_elements(html, "div.info-table > span.info-table__content--regular") %>% html_text() %>% str_squish(),
text = html_elements(html, "div.info-table > span.info-table__content--bold") %>% html_text() %>% str_squish()
) %>%
# player name is not included in div.info-table, add it separately
add_row(.before = 1,
feature = "Player:",
text = html_elements(html, "header > div.data-header__headline-container > h1") %>% html_text() %>% str_squish())
df_01
#> # A tibble: 15 × 2
#> feature text
#> <chr> <chr>
#> 1 Player: "#4 Mamadou Doucouré"
#> 2 Geburtsdatum: "21.05.1998"
#> 3 Geburtsort: "Dakar"
#> 4 Alter: "24"
#> 5 Größe: "1,83 m"
#> 6 Nationalität: "Frankreich Senegal"
#> 7 Position: "Abwehr - Innenverteidiger"
#> 8 Fuß: "links"
#> 9 Spielerberater: "Sport Avenir Management International"
#> 10 Aktueller Verein: "Borussia Mönchengladbach"
#> 11 Im Team seit: "01.07.2016"
#> 12 Vertrag bis: "30.06.2024"
#> 13 Letzte Verlängerung: "14.02.2020"
#> 14 2. Verein: "Borussia Mönchengladbach II (#3)"
#> 15 Social Media: ""
To include URLs we handle the first info-table column as before but processes 2nd one through map - not all entries have URLs and we don't want to end up with misaligned columns with different lengths:
df_02 <- tibble(
feature = html_elements(html, "div.info-table > span.info-table__content--regular") %>% html_text() %>% str_squish(),
) %>% bind_cols(
purrr::map_df(
html_elements(html, "div.info-table > span.info-table__content--bold"),
~ list(
html_text(.x) %>% stringr::str_squish() %>% na_if(""),
html_element(.x, "a") %>% html_attr("href")
) %>% setNames(c("text", "url"))
)
) %>% add_row(.before = 1,
feature = "Player:",
text = html_elements(html, "header > div.data-header__headline-container > h1") %>% html_text() %>% stringr::str_squish())
df_02
#> # A tibble: 15 × 3
#> feature text url
#> <chr> <chr> <chr>
#> 1 Player: #4 Mamadou Doucouré <NA>
#> 2 Geburtsdatum: 21.05.1998 /aktuell/waspassi…
#> 3 Geburtsort: Dakar <NA>
#> 4 Alter: 24 <NA>
#> 5 Größe: 1,83 m <NA>
#> 6 Nationalität: Frankreich Senegal <NA>
#> 7 Position: Abwehr - Innenverteidiger <NA>
#> 8 Fuß: links <NA>
#> 9 Spielerberater: Sport Avenir Management International /sport-avenir-man…
#> 10 Aktueller Verein: Borussia Mönchengladbach /borussia-monchen…
#> 11 Im Team seit: 01.07.2016 <NA>
#> 12 Vertrag bis: 30.06.2024 <NA>
#> 13 Letzte Verlängerung: 14.02.2020 <NA>
#> 14 2. Verein: Borussia Mönchengladbach II (#3) /borussia-monchen…
#> 15 Social Media: <NA> http://www.instag…
To have a tidy dataframe that could potentially take more players, missing text values are replaced by URLs and separate URL column is dropped:
df_03 <- df_02 %>%
mutate(feature = janitor::make_clean_names(feature),
`text` = coalesce(`text`,url)) %>%
select(-url) %>%
pivot_wider(names_from = feature, values_from = text) %>%
extract(player, into = c("number", "player"), "^#(\\d+) (.*)")
glimpse(df_03)
#> Rows: 1
#> Columns: 16
#> $ number <chr> "4"
#> $ player <chr> "Mamadou Doucouré"
#> $ geburtsdatum <chr> "21.05.1998"
#> $ geburtsort <chr> "Dakar"
#> $ alter <chr> "24"
#> $ grosse <chr> "1,83 m"
#> $ nationalitat <chr> "Frankreich Senegal"
#> $ position <chr> "Abwehr - Innenverteidiger"
#> $ fuss <chr> "links"
#> $ spielerberater <chr> "Sport Avenir Management International"
#> $ aktueller_verein <chr> "Borussia Mönchengladbach"
#> $ im_team_seit <chr> "01.07.2016"
#> $ vertrag_bis <chr> "30.06.2024"
#> $ letzte_verlangerung <chr> "14.02.2020"
#> $ x2_verein <chr> "Borussia Mönchengladbach II (#3)"
#> $ social_media <chr> "http://www.instagram.com/mams_dcr/"