通过rvest获取web抓取中的电子邮件地址

这里需要一个javascript引擎来处理js代码。幸运的是,R得到了 V8 .

安装后修改代码 包裹:

library(rvest)
library(V8)

link <- 'https://food.list.co.uk/place/22191-brewhemia-edinburgh/'
page <- read_html(link)
name_html <- html_nodes(page,'.placeHeading')
business_adr <- html_text(adr_html)
tel_html <- html_nodes(page,'.value')
business_tel <- html_text(tel_html)

emailjs <- page %>% html_nodes('li') %>% html_nodes('script') %>% html_text()
ct <- v8()

read_html(ct$eval(gsub('document.write','',emailjs))) %>% html_text()

> read_html(ct$eval(gsub('document.write','',emailjs))) %>% html_text()
[1] "info@brewhemia.co.uk"