Let's scrape the names, addresses and public health units of pharmacies in Ontario offering the COVID-19 vaccine from the provincial website.
# load packages
library(rvest)
library(stringr)
# load webpage and list pharmacy cards
webpage <- read_html("https://covid-19.ontario.ca/vaccine-locations") %>%
html_nodes(xpath = '//*[@class="ontario-assessment-centre-card__wrapper"]')
# number of pharmacies
n_pharms <- length(webpage)
# create table
pharms <- data.frame(
name = character(n_pharms),
address_street = character(n_pharms),
address_city = character(n_pharms),
address_province = character(n_pharms),
address_postal_code = character(n_pharms),
address_country = character(n_pharms),
phu = character(n_pharms)
)
# extract name, address and PHU from each each pharmacy card
for (i in 1:length(webpage)) {
# ## print progress
# cat(i, fill = TRUE)
## extract data
dat <- webpage[i] %>%
html_elements("p")
## fill in table
pharms[i, "name"] <- dat[1] %>% html_text
pharms[i, "address_street"] <- dat[2] %>% html_text
pharms[i, "address_city"] <- dat[3] %>% html_text %>% str_sub(0, -5)
pharms[i, "address_province"] <- "Ontario"
pharms[i, "address_postal_code"] <- dat[4] %>% html_text
pharms[i, "address_country"] <- "Canada"
pharms[i, "phu"] <- dat[length(dat)] %>% html_text
}
# write table
write.csv(pharms, "pharms.csv", row.names = FALSE)Previewing the results:
head(pharms)## name address_street address_city address_province
## 1 Costco Pharmacy 150 Kingston Road East Ajax Ontario
## 2 Health-Rite Pharmacy 75 Bayly Street West Ajax Ontario
## 3 Loblaw Pharmacy 30 Kingston Road West Ajax Ontario
## 4 Rexall 955 Westney Road South Unit 7 Ajax Ontario
## 5 Shoppers Drug Mart 15 Westney Road North Ajax Ontario
## 6 Rexall 149 Young Street Alliston Ontario
## address_postal_code address_country phu
## 1 L1Z 1E5 Canada Durham Region Health Department
## 2 L1S 7K7 Canada Durham Region Health Department
## 3 L1T 4K8 Canada Durham Region Health Department
## 4 L1S 3K7 Canada Durham Region Health Department
## 5 L1T 1P4 Canada Durham Region Health Department
## 6 L9R 2A9 Canada Simcoe Muskoka District Health Unit
The number of pharmacies by Public Health Unit:
table(pharms$phu) %>%
as.data.frame## Var1 Freq
## 1 Algoma Public Health Unit 3
## 2 Brant County Health Unit 3
## 3 Chatham-Kent Health Unit 3
## 4 Durham Region Health Department 25
## 5 Eastern Ontario Health Unit 3
## 6 Grey-Bruce Health Unit 3
## 7 Haldimand-Norfolk Health Unit 3
## 8 Haliburton, Kawartha, Pine Ridge District Health Unit 5
## 9 Halton Region Health Department 19
## 10 Hamilton Public Health Services 21
## 11 Hastings and Prince Edward Counties Health Unit 3
## 12 Huron Perth Health Unit 3
## 13 Kingston, Frontenac and Lennox & Addington Health Unit 46
## 14 Lambton Health Unit 3
## 15 Leeds,Grenville, and Lanark District Health Unit 2
## 16 Middlesex-London Health Unit 2
## 17 Niagara Region Public Health Department 22
## 18 North Bay-Parry Sound District Health Unit 4
## 19 Northwestern Health Unit 3
## 20 Ottawa Public Health 34
## 21 Peel Public Health 42
## 22 Peterborough Public Health 3
## 23 Porcupine Health Unit 3
## 24 Region of Waterloo, Public Health 19
## 25 Renfrew County and District Health Unit 3
## 26 Simcoe Muskoka District Health Unit 25
## 27 Southwestern Public Health 5
## 28 Sudbury 3
## 29 Thunder Bay 3
## 30 Timiskaming 3
## 31 Toronto Public Health 275
## 32 Wellington-Dufferin-Guelph Health Unit 10
## 33 Windsor-Essex County Health Unit 57
## 34 York Region Public Health Services 38