web scrapping code example
Example 1: web scraping
import os
import requests
from bs4 import BeautifulSoup
url = "https://www.google.com/"
reponse = requests.get(url)
if reponse.ok:
soup = BeautifulSoup(reponse.text, "lxml")
title = str(soup.find("title"))
title = title.replace("<title>", "")
title = title.replace("</title>", "")
print("The title is : " + str(title))
os.system("pause")
Example 2: My Web Scrapping Code
u <- "http://stackoverflow.com/questions/tagged?tagnames=r"
doc.raw <- getURL(u)
doc <- tidyHTML(doc.raw)
html <- htmlTreeParse(doc, useInternal = TRUE)
txt <- xpathApply(html, "//body//text()[not(ancestor::script)][not(ancestor::style)][not(ancestor::noscript)]", xmlValue)
cat(unlist(txt))