Loop with rvest - r

I'm very new to all this and am trying to work through some examples on stackoverflow to build up my confidence.
I found this answer by #RonakShah
Using rvest to scrape data that is not in table
and thought I'd use it because I'm familiar with HTML to build up my confidence with loops.
My issue is that I can't make the loop work.
Could someone please point out where I'm going wrong? It's bits and pieces of code I've found through the messageboards, but I'm not getting anywhere!
library(rvest)
page<- (0:2)
urls <- list()
for (i in 1:length(page)) {
url<- paste0("https://concreteplayground.com/sydney/bars?page=",page[i])
urls[[i]] <- url
}
tbl <- list()
j <- 1
for (j in seq_along(urls)) {
tbl[[j]] <- urls[[j]] %>% read_html()
name <- tbl[[j]] %>% html_nodes('p.name a') %>%html_text() %>% trimws()
address <- tbl[[j]] %>% html_nodes('p.address') %>% html_text() %>% trimws()
links <- tbl[[j]] %>% html_nodes('p.name a') %>% html_attr('href')
data.frame(name, address, links)
j <- j+1
}
#convert list to data frame
tbl <- do.call(rbind, tbl)

Create urls using paste0 directly, no need for a loop.
library(rvest)
pages <- 1:2
urls <- paste0("https://concreteplayground.com/sydney/bars?page=", pages)
If you put the code on that page in a function, you can use it with map_df to get combined dataframe directly. map_df does the job of for loop and do.call(rbind, tbl) together.
get_web_data <- function(url) {
webpage <- url %>% read_html()
name <- webpage %>% html_nodes('p.name a') %>%html_text() %>% trimws()
address <- webpage %>% html_nodes('p.address') %>% html_text() %>% trimws()
links <- webpage %>% html_nodes('p.name a') %>% html_attr('href')
data.frame(name, address, links)
}
purrr::map_df(urls, get_web_data)

Related

Web scraping in R: the same element gets scraped multiple times. How could I fix this?

I am trying to scrape some URLs from the dutch train disruptions website. The problem is that on every page the first URL gets scraped 7x times. The HTML only contains the URL once so I don't understand why it is scraped multiple times.
The problem occurs the same way on every page: Every time, the first URL is scraped 7 times and on the rest of the page just once.
I am using the following script:
library(tidyverse)
library(rvest)
scrape_css_attr <- function(css,group,attribute,html_page){
txt <- html_page %>%
html_nodes(group) %>%
lapply(.%>% html_nodes(css) %>% html_attr(attribute) %>% ifelse(identical(.,character(0)),NA,.)) %>%
unlist()
return(txt)
}
get_element_data <- function(link){
if(!is.na(link)){
html <- read_html(link)
Sys.sleep(2)
datum <- html %>%
html_node(".disruption-cause") %>%
html_text()
return(tibble(datum=datum))
}
}
get_elements_from_url <- function(url){
html_page <- read_html(url)
Sys.sleep(2)
element_urls <- scrape_css_attr(".resolved","div","href",html_page)
element_urls <- element_urls[!is.na(element_urls)]
element_urls <- paste0("https://www.rijdendetreinen.nl", element_urls)
element_data_detail <- element_urls %>%
map(get_element_data) %>%
bind_rows()
elements_data <- tibble(element_urls=element_urls)
elements_data_overview <- elements_data[complete.cases(elements_data[,1]), ]
return(bind_cols(elements_data_overview,element_data_detail))
}
scrape_write_table <- function(url){
list_of_pages <- str_c(url, 1)
list_of_pages %>%
map(get_elements_from_url) %>%
bind_rows()
}
trainDisruptions <- scrape_write_table("https://www.rijdendetreinen.nl/storingen?lines=&reasons=&date_before=31-12-2018&date_after=01-01-2018&page=")
View(trainDisruptions)

Looping through a list of webpages with rvest follow_link

I'm trying to webscrape the government release calendar: https://www.gov.uk/government/statistics and use the rvest follow_link functionality to go to each publication link and scrape text from the next page. I have this working for each single page of results (40 publications are displayed per page), but can't get a loop to work so that I can run the code over all publications listed.
This is the code I run first to get the list of publications (just from the first 10 pages of results):
#Loading the rvest package
library('rvest')
library('dplyr')
library('tm')
#######PUBLISHED RELEASES################
###function to add number after 'page=' in url to loop over all pages of published releases results (only 40 publications per page)
###check the site and see how many pages you want to scrape, to cover months of interest
##titles of publications - creates a list
publishedtitles <- lapply(paste0('https://www.gov.uk/government/statistics?page=', 1:10),
function(url_base){
url_base %>% read_html() %>%
html_nodes('h3 a') %>%
html_text()
})
##Dates of publications
publisheddates <- lapply(paste0('https://www.gov.uk/government/statistics?page=', 1:10),
function(url_base){
url_base %>% read_html() %>%
html_nodes('.public_timestamp') %>%
html_text()
})
##Organisations
publishedorgs <- lapply(paste0('https://www.gov.uk/government/statistics?page=', 1:10),
function(url_base){
url_base %>% read_html() %>%
html_nodes('.organisations') %>%
html_text()
})
##Links to publications
publishedpartial_links <- lapply(paste0('https://www.gov.uk/government/statistics?page=', 1:10),
function(url_base){
url_base %>% read_html() %>%
html_nodes('h3 a') %>%
html_attr('href')
})
#Check all lists are the same length - if not, have to deal with missings before next step
# length(publishedtitles)
# length(publisheddates)
# length(publishedorgs)
# length(publishedpartial_links)
#str(publishedorgs)
#Combining all the lists to form a data frame
published <-data.frame(Title = unlist(publishedtitles), Date = unlist(publisheddates), Organisation = unlist(publishedorgs), PartLinks = unlist(publishedpartial_links))
#adding prefix to partial links, to turn into full URLs
published$Links = paste("https://www.gov.uk", published$PartLinks, sep="")
#Drop partial links column
keeps <- c("Title", "Date", "Organisation", "Links")
published <- published[keeps]
Then I want to run something like the below, but over all pages of results. I've ran this code manually changing the parameters for each page, so know it works.
session1 <- html_session("https://www.gov.uk/government/statistics?page=1")
list1 <- list()
for(i in published$Title[1:40]){
nextpage1 <- session1 %>% follow_link(i) %>% read_html()
list1[[i]]<- nextpage1 %>%
html_nodes(".grid-row") %>% html_text()
df1 <- data.frame(text=list1)
df1 <-as.data.frame(t(df1))
}
So the above would need to change page=1 in the html_session, and also the publication$Title[1:40] - I'm struggling with creating a function or loop that includes both variables.
I think I should be able to do this using lapply:
df <- lapply(paste0('https://www.gov.uk/government/statistics?page=', 1:10),
function(url_base){
for(i in published$Title[1:40]){
nextpage1 <- url_base %>% follow_link(i) %>% read_html()
list1[[i]]<- nextpage1 %>%
html_nodes(".grid-row") %>% html_text()
}
}
)
But I get the error
Error in follow_link(., i) : is.session(x) is not TRUE
I've also tried other methods of looping and turning it into a function but didn't want to make this post too long!
Thanks in advance for any suggestions and guidance :)
It looks like you may have just need to start a session inside the lapply function. In the last chunk of code, url_base is simply a text string that gives the base URL. Would something like this work:
df <- lapply(paste0('https://www.gov.uk/government/statistics?page=', 1:10),
function(url_base){
for(i in published$Title[1:40]){
tmpSession <- html_session(url_base)
nextpage1 <- tmpSession %>% follow_link(i) %>% read_html()
list1[[i]]<- nextpage1 %>%
html_nodes(".grid-row") %>% html_text()
}
}
)
To change the published$Title[1:40] for each iteraction of the lapply function, you could make an object that holds the lower and upper bounds of the indices:
lowers <- cumsum(c(1, rep(40, 9)))
uppers <- cumsum(rep(40, 10))
Then, you could include those in the call to lapply
df <- lapply(1:10, function(j){
url_base <- paste0('https://www.gov.uk/government/statistics?page=', j)
for(i in published$Title[lowers[j]:uppers[j]]){
tmpSession <- html_session(url_base)
nextpage1 <- tmpSession %>% follow_link(i) %>% read_html()
list1[[i]]<- nextpage1 %>%
html_nodes(".grid-row") %>% html_text()
}
}
)
Not sure if this is what you want or not, I might have misunderstood the things that are supposed to be changing.

Follow links in a loop with rvest

I'm trying to learn the rvest package, but the documentation and the examples on the web are either very basic or very complex. I could not find how to use the follow_link function in a loop to browse some number of pages. Perhaps I did not understand its logic at all...
Here is a simplified example of my attempt:
library(rvest)
url <-
"https://www.wikidata.org/w/index.php?title=Special:WhatLinksHere/Q5&limit=500"
s <- html_session(url)
liste <- list()
for (i in 1:2) {
data <-
s %>%
read_html() %>%
html_nodes("#mw-whatlinkshere-list li")
result <- c(liste, data)
s <- s %>%
follow_link(xpath = "//a[text()='next 500']/#href")
}
I've also tried to avoid the jump_link, like this : it's better, but I'm not sure is the best and fastest solution :
liste <- c()
while (!is.na(url)) {
data <-
url %>%
read_html() %>%
html_nodes("#mw-whatlinkshere-list li")
liste <- c(liste, data)
url <- url %>%
read_html() %>%
html_node(xpath = "//a[text()='next 500']") %>%
html_attr("href") %>%
paste0("https://www.wikidata.org", .)
print(url)
}
Any advice is welcome and would be appreciated.
Try this:
library(rvest)
url <- "https://www.wikidata.org/w/index.php?title=Special:WhatLinksHere/Q5&limit=500"
s <- html_session(url)
liste <- list()
for (i in 1:2) {
data <-
s %>%
read_html() %>%
html_nodes("#mw-whatlinkshere-list li")
# There was a mistake here. You were overwriting your results
liste <- c(liste, data)
# Here you have to pass a 'a' tag, not a 'href' value. Besides,
# there is two 'next 500' tags. They are the same, but you have
# to pick one.
s <- s %>%
follow_link(xpath = "//a[text()='next 500'][1]")
}

Web scraping on multiple pages using R

I am trying to scrape the reviews for a product using the below url in R. When I run the below code, I am able to get a single review scraped.
comment<- read_html("https://www.influenster.com/reviews/chobani-greek-yogurt")
comment %>% html_node(".content-item-text") %>% html_text()
comment %>% html_node(".date") %>% html_text()
However, when I use the below code for scraping multiple comments on multiple pages, it returns NULL.
reviews <- lapply(paste0('https://www.influenster.com/reviews/chobani-greek-yogurt?review_page=2', 2:50),
function(url){
url %>% read_html() %>%
html_nodes(".content-item-text review-text") %>%
html_nodes(".date") %>%
html_text()
})
Does the following code achieve what you are looking for?
comment<- read_html("https://www.influenster.com/reviews/chobani-greek-yogurt")
reviews <- c()
dates <- c()
for(i in 1:10){
reviews <- c(reviews,
comment %>%
html_node(paste0(".review-item:nth-child(", i, ") .review-text")) %>%
html_text())
dates <- c(dates,
comment %>%
html_node(paste0(".review-item:nth-child(", i, ") .date")) %>%
html_text())
}
for(j in 2:50){
comment <- read_html(paste0("https://www.influenster.com/reviews/chobani-greek-yogurt?review_page=", j))
for(i in 1:10){
reviews <- c(reviews,
comment %>%
html_node(paste0(".review-item:nth-child(", i, ") .review-text")) %>%
html_text())
dates <- c(dates,
comment %>%
html_node(paste0(".review-item:nth-child(", i, ") .date")) %>%
html_text())
}
}
Just note that I am in the UK and the extracted dates seem to be corrected (- 6 hours what is stated on the site)
Furthermore, apologies for the multiple looping I am not yet very quick at translating loops to the apply functions :)

R return multiple nodes in 1 search using rvest (massive list of urls)

I am using rvest to scrape a website. It works, buy highly inefficient, and I can't figure out how to get it to work better.
in url is a list of over 10.000 url's.
number <- sapply(url, function(x)
read_html(x) %>%
html_nodes(".js-product-artnr") %>%
html_text())
price_new <- sapply(url, function(x)
read_html(x) %>%
html_nodes(".product-page__price__new") %>%
html_text())
price_old <- sapply(url, function(x)
read_html(x) %>%
html_nodes(".product-page__price__old") %>%
html_text())
The problem above is, rvest visits the 10.000 urls to get the first node in ".js-product-artnr", then visits the same 10.000 urls again for the second node and so on. In the end I expect to need about 10 different nodes from these 10.000 pages. getting them 1 by 1 and combining into a data frame later on takes way to long, there must be a better way.
I am looking for something like below, to get all information in 1 search
info <- sapply(url, function(x)
read_html(x) %>%
html_nodes(".js-product-artnr") %>%
html_nodes(".product-page__price__new") %>%
html_nodes(".product-page__price__old") %>%
html_text())
This works for me.
func <- function(url){
sample <- read_html(url) %>%
scrape1 <- html_nodes(sample, ".js-product-artnr")%>%
html_text()
scrape2 <- html_nodes(sample, ".product-page__price__new") %>%
html_text()
scrape3 <- html_nodes(sample,".product-page__price__old") %>%
html_text()
df <- cbind(scrape1, scrape2, scrape3)
final_df <- as.data.frame(df)
return(final_df)
}
data <- lapply(urls_all, func)

Resources