def get_single_item_data(item_url):
source_code = requests.get(item_url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text)
for item_name in soup.findAll('div', {'class': 'i-name'}):
print(item_name.string)
for link in soup.findAll('a'):
href = "https://buckysroom.org" + link.get('href')
print(href)
def get_single_item_data(item_url):
source_code = requests.get(item_url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text)
for item_name in soup.findAll('div', {'class': 'i-name'}):
print(item_name.string)
for link in soup.findAll('a'):
href = "https://buckysroom.org" + link.get('href')
print(href)
def trade_spider(max_pages):
page = 1
while page <= max_pages:
url = 'https://buckysroom.org/trade/search.php?page=' + str(page)
source_code = requests.get(url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text)
for link in soup.findAll('a', {'class': 'item-name'}):
href = "https://buckysroom.org" + link.get('href')
title = link.string
print(href)
print(title)
page += 1
def trade_spider(max_pages):
page = 1
while page <= max_pages:
url = 'DESIRED WEBSITE' + str(page)
source_code = requests.get(url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text)
for link in soup.findAll('a', {'class': 'item-name'}):
href = "DESIRED WEBSITE" + link.get('href')
title = link.string
get_single_item_data(href)
page += 1
def trade_spider(max_pages):
page = 1
while page <= max_page:
url = 'https://buckysroom.org/trade/search.php?page=' + str(page)
source_code = requests.get(url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text)
for link in soup.findAll('a', {'class': 'item-name'}):
href = "https://buckysroom.org" + link.get('href')
title = link.string
print(href)
print(title)
page += 1
def get_composer(number):
wiki_composer_page = requests.get(
"https://en.wikipedia.org/wiki/List_of_classical_music_composers_by_era"
)
if not wiki_composer_page.ok:
print("Failed to download list of composers")
raise SystemExit(1)
composer_soup = BeautifulSoup(wiki_composer_page.text, "html.parser")
timelines = composer_soup.find_all("div", class_="timeline-wrapper")
composer_elements = []
for item in timelines:
composer_elements.extend(item.find_all("area"))
composers = [comp['title'] for comp in composer_elements]
choices = random.choices(composers, k=number)
for item in choices:
print(item)
# -*- coding: utf-8 -*-
from b4 import BeautifulSoup
#from b4 import BeautifulSoup
import urllib2
#import os, re, urlparse
#Site = 'https://www.google.co.jp'
Site = 'http://www.yahoo.co.jp/'
soup = BeautifulSoup(urllib2.urlopen(Site), "lxml")
#res = soup.find_all("a")
#res = soup.a.get("href")
res = soup.select('a[href^="http://"]')
for one in res:
print one
#from pprint import pprint
#pprint(txt)
print 'Finish'
import requests
from b4 import BeautifulSoup
url = "http://kurstenge.kz"
r = requests.get(url)
html = r.text
soup = BeautifulSoup(html, "html.parser")
rows = soup.select("#content table table tr")
for tr in rows:
print(tr.text)