HTMLを読み込む

import urllib.request

url = “http://www.customslegaloffice.com/fta”

 

# urlopenを使う
html = urllib.request.urlopen(url)
#readの引数に文字数を指定.decode(“utf=8#))
print(html.read(500).decode(“utf-8”))

 

 

例1:yahooニュースからスクレイピング

 

import urllib.request
from bs4 import BeautifulSoup

url = "https://news.yahoo.co.jp"
html = urllib.request.urlopen(url)

soup = BeautifulSoup(html, 'lxml')

topics = soup.find_all("p",class_="ttl")

for topic in topics:
print(topic.text)

 

例:2　ビットコイン価格の取得

import urllib.request
from bs4 import BeautifulSoup
import csv
import time
from datetime import datetime

url = "https://coinmarketcap.com/currencies/bitcoin-cash/"

 

f = open("bitcoin.csv", "w")
writer = csv.writer(f, lineterminator="\n")

html = urllib.request.urlopen(url)
soup = BeautifulSoup(html, 'lxml')

for i in range(15):

# リスト形式で格納し、csvに書き込む
price = soup.find_all("span", class_="text-large2", id="quote_price")
value = price[0].text
writer.writerow([datetime.now(),value])

# 240秒処理を休止します
time.sleep(2)

f.close()

 

 

 

 

 

 

 

例:1で取得したyahooのスクレイピングの対象タグ

 

<li>
	<div>
	<p class=”ttl“><a href=”https://news.yahoo.co.jp/pickup/6263011” onmousedown=”this.href=’https://rdsig.yahoo.co.jp/_ylt=A2Rifg0JaR9aimsAUHAEnf57/RV=2/RE=1512094345/RH=cmRzaWcueWFob28uY28uanA-/RB=tJQRd1AC72Lz8jGDGZOagZ_Lbl0-/RU=aHR0cHM6Ly9uZXdzLnlhaG9vLmNvLmpwL3BpY2t1cC82MjYzMDExAA–/RK=0/RS=8TztB1eAvSrIMPzmJpmHQep2GB8-‘“>海底に人 墜落空自ヘリ乗員か<span class=”icPhoto“>写真</span></a></p>
	</div>
	</li>
	<li>
	<div>
	<p class=”ttl“><a href=”https://news.yahoo.co.jp/pickup/6263008” onmousedown=”this.href=’https://rdsig.yahoo.co.jp/_ylt=A2Rifg0JaR9aimsAUXAEnf57/RV=2/RE=1512094345/RH=cmRzaWcueWFob28uY28uanA-/RB=tJQRd1AC72Lz8jGDGZOagZ_Lbl0-/RU=aHR0cHM6Ly9uZXdzLnlhaG9vLmNvLmpwL3BpY2t1cC82MjYzMDA4AA–/RK=0/RS=9uov33ITmDdzaj9DqnJQ7RhyFBE-‘“>火星15 米攻撃能力なお疑問<span class=”icPhoto“>写真</span></a></p>
	</div>
	</li>
	<li>
	<div>
	<p class=”ttl“><a href=”https://news.yahoo.co.jp/pickup/6263017” onmousedown=”this.href=’https://rdsig.yahoo.co.jp/_ylt=A2Rifg0JaR9aimsAUnAEnf57/RV=2/RE=1512094345/RH=cmRzaWcueWFob28uY28uanA-/RB=tJQRd1AC72Lz8jGDGZOagZ_Lbl0-/RU=aHR0cHM6Ly9uZXdzLnlhaG9vLmNvLmpwL3BpY2t1cC82MjYzMDE3AA–/RK=0/RS=hpkwmxO3YnpTdJcl8hgYbThc.vI-‘“>賃金より給食高く 障害者訴え<span class=”icPhoto“>写真</span><span class=”icNew“>new</span></a></p>
	</div>
	</li>