python for web scraping code example
Example 1: python web scraping
import requests
from bs4 import BeautifulSoup
URL = 'https://www.monster.com/jobs/search/?q=Software-Developer&where=Australia'
page = requests.get(URL)
soup = BeautifulSoup(page.content, 'html.parser')
Example 2: web scraping python
#pip install beautifulsoup4
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")
#python (code name).py
Example 3: web scraping python
import scrapy
from ..items import SampletestItem #items class
class QuoteTestSpider(scrapy.Spider):
name = 'quote_test'
start_urls = ['https://quotes.toscrape.com/']
def parse(self, response):
items = SampletestItem() #items class
quotes = response.css("div.quote")
for quote in quotes:
items['title'] = quote.css("span.text::text").get()
items['author'] = quote.css(".author::text").get()
items['tags'] = quote.css(".tags .tag::text").getall()
yield items
next_page = response.css(".next a::attr(href)").get()
if next_page is not None:
next_url = response.urljoin(next_page)
yield scrapy.Request(next_url, callback=self.parse)
Example 4: web scraper python
def get_hits_on_name(name):
"""
Accepts a `name` of a mathematician and returns the number
of hits that mathematician's Wikipedia page received in the
last 60 days, as an `int`
"""
# url_root is a template string that is used to build a URL.
url_root = 'URL_REMOVED_SEE_NOTICE_AT_START_OF_ARTICLE'
response = simple_get(url_root.format(name))
if response is not None:
html = BeautifulSoup(response, 'html.parser')
hit_link = [a for a in html.select('a')
if a['href'].find('latest-60') > -1]
if len(hit_link) > 0:
# Strip commas
link_text = hit_link[0].text.replace(',', '')
try:
# Convert to integer
return int(link_text)
except:
log_error("couldn't parse {} as an `int`".format(link_text))
log_error('No pageviews found for {}'.format(name))
return None
Example 5: web scraper python
>>> raw_html = simple_get('http://www.fabpedigree.com/james/mathmen.htm')
>>> html = BeautifulSoup(raw_html, 'html.parser')
>>> for i, li in enumerate(html.select('li')):
print(i, li.text)
0 Isaac Newton
Archimedes
Carl F. Gauss
Leonhard Euler
Bernhard Riemann
1 Archimedes
Carl F. Gauss
Leonhard Euler
Bernhard Riemann
2 Carl F. Gauss
Leonhard Euler
Bernhard Riemann
3 Leonhard Euler
Bernhard Riemann
4 Bernhard Riemann
# 5 ... and many more...