こんにちは。YOSHITAKA（@YOSHITA19704216）です。
初心者
どうやってやるんですか？
よしたか
僕もYou Tube見てやりました。
今回は動画の通り、Pythonを打ち込んで、できたので足跡として残しておきます。
僕もまだまだ詳しくないので、詳しいことは言えませんが、コピペ程度に使ってください。
この記事を読むことで
- Pythonでダウンロードする実践的な方法が分かります。
Contents
必要な情報と記述例一式
内容を参考にしたサイト
この動画を参考にしました。
https://www.youtube.com/watch?v=GXBCPEBAlVk&t=1054s
from bs4 import BeautifulSoup
import lxml
import requests
headers = {"user-Agent": "hoge"}
URL = "https://search.yahoo.co.jp/image/search?p=%E3%81%8C%E3%81%A3%E3%81%8D%E3%83%BC&ei=UTF-8&save=0"
resp = requests.get(URL, timeout=1, headers=headers)
soup = BeautifulSoup(resp.text,"lxml")
print(soup.find("a")["href"])
———
from bs4 import BeautifulSoup
import lxml
import requests
headers = {"user-Agent": "hoge"}
URL = "https://search.yahoo.co.jp/image/search?p=%E3%81%8C%E3%81%A3%E3%81%8D%E3%83%BC&ei=UTF-8&save=0"
resp = requests.get(URL, timeout=1, headers=headers)
soup = BeautifulSoup(resp.text,"lxml")
print(soup.find_all("img")[0])
———
from bs4 import BeautifulSoup
import lxml
import requests
headers = {"user-Agent": "hoge"}
URL = "https://search.yahoo.co.jp/image/search?p=%E3%81%8C%E3%81%A3%E3%81%8D%E3%83%BC&ei=UTF-8&save=0"
resp = requests.get(URL, timeout=1, headers=headers)
soup = BeautifulSoup(resp.text,"lxml")
print(soup.find_all("img")[0]["src"])
———
ローカルにダウンロードする。 落とす
画像の個数を調べる
from bs4 import BeautifulSoup
import lxml
import requests
headers = {"user-Agent": "hoge"}
URL = "https://search.yahoo.co.jp/image/search?p=%E3%81%8C%E3%81%A3%E3%81%8D%E3%83%BC&ei=UTF-8&save=0"
resp = requests.get(URL, timeout=1, headers=headers)
soup = BeautifulSoup(resp.text,"lxml")
imgs = soup.find_all("img")
print(len(imgs))
エンコード＆デコードしました。
（Macだとアドレスバーが勝手に変化します）
https://search.yahoo.co.jp/image/search?p=%E3%82%AC%E3%83%83%E3%82%AD%E3%83%BC&oq=&ei=UTF-8&save=0
https://search.yahoo.co.jp/image/search?p=ガッキー&oq=&ei=UTF-8&save=0
———
from bs4 import BeautifulSoup
import lxml
import requests
headers = {"user-Agent": "hoge"}
URL = "https://search.yahoo.co.jp/image/search?p=ガッキー&oq=&ei=UTF-8&save=0"
resp = requests.get(URL, timeout=1, headers=headers)
soup = BeautifulSoup(resp.text,"lxml")
imgs = soup.find_all(alt="「ガッキー」の画像検索結果")
print(len(imgs))
———
URLを取得
from bs4 import BeautifulSoup
import lxml
import requests
headers = {"user-Agent": "hoge"}
URL = "https://search.yahoo.co.jp/image/search?p=ガッキー&oq=&ei=UTF-8&save=0"
resp = requests.get(URL, timeout=1, headers=headers)
soup = BeautifulSoup(resp.text,"lxml")
imgs = soup.find_all(alt="「ガッキー」の画像検索結果")
print(len(imgs))
for i in range(len(imgs)):
print(imgs[i]["src"])
———
ダウンロードする
from bs4 import BeautifulSoup
import lxml
import requests
import urllib.request
headers = {"user-Agent": "hoge"}
URL = "https://search.yahoo.co.jp/image/search?p=ガッキー&oq=&ei=UTF-8&b=1"
resp = requests.get(URL, timeout=1, headers=headers)
soup = BeautifulSoup(resp.text,"lxml")
imgs = soup.find_all(alt="「ガッキー」の画像検索結果")
print(len(imgs))
for i in range(len(imgs)):
filepath = "{}.jpg".format(i)
urllib.request.urlretrieve(imgs[i]["src"],filepath)
———
ページごとにダウンロード
from bs4 import BeautifulSoup
import lxml
import requests
import urllib.request
num = 0
headers = {"user-Agent": "hoge"}
URL = "https://search.yahoo.co.jp/image/search?p=ガッキー&oq=&ei=UTF-8&b={}".format(1+ 20*num)
resp = requests.get(URL, timeout=1, headers=headers)
soup = BeautifulSoup(resp.text,"lxml")
imgs = soup.find_all(alt="「ガッキー」の画像検索結果")
print(len(imgs))
for i in range(len(imgs)):
filepath = "{}.jpg".format(i)
urllib.request.urlretrieve(imgs[i]["src"],filepath)
from bs4 import BeautifulSoup
import lxml
import requests
import urllib.request
num = 0
for num in range(3):
headers = {"user-Agent": "hoge"}
URL = "https://search.yahoo.co.jp/image/search?p=ガッキー&oq=&ei=UTF-8&b={}".format(1+ 20*num)
resp = requests.get(URL, timeout=1, headers=headers)
soup = BeautifulSoup(resp.text,"lxml")
imgs = soup.find_all(alt="「ガッキー」の画像検索結果")
print(len(imgs))
for i in range(len(imgs)):
filepath = "{}.jpg".format(i)
urllib.request.urlretrieve(imgs[i]["src"],filepath)
from bs4 import BeautifulSoup
import lxml
import requests
import urllib.request
num = 0
for num in range(3):
headers = {"user-Agent": "hoge"}
URL = "https://search.yahoo.co.jp/image/search?p=ガッキー&oq=&ei=UTF-8&b={}".format(1+ 20*num)
resp = requests.get(URL, timeout=1, headers=headers)
soup = BeautifulSoup(resp.text,"lxml")
imgs = soup.find_all(alt="「ガッキー」の画像検索結果")
print(len(imgs))
for i in range(len(imgs)):
filepath = "./date/practice/{0}-{1}.jpg".format(num,i)
urllib.request.urlretrieve(imgs[i]["src"],filepath)
———
検索ワードを自分で入れる
from bs4 import BeautifulSoup
import lxml
import requests
import urllib.request
import sys
query_word = sys.argv[1]
num = 0
for num in range(3):
headers = {"user-Agent": "hoge"}
URL = "https://search.yahoo.co.jp/image/search?p={0}&oq=&ei=UTF-8&b={1}".format(query_word,1+ 20*num)
resp = requests.get(URL, timeout=1, headers=headers)
soup = BeautifulSoup(resp.text,"lxml")
imgs = soup.find_all(alt="「{}」の画像検索結果.format(query_word)")
print(len(imgs))
for i in range(len(imgs)):
filepath = "./date/practice/{0}-{1}.jpg".format(num,i)
urllib.request.urlretrieve(imgs[i]["src"],filepath)
———
from bs4 import BeautifulSoup
import lxml
import requests
import urllib.request
import sys
query_word = sys.argv[1]
num = 0
for num in range(3):
headers = {"user-Agent": "hoge"}
URL = "https://search.yahoo.co.jp/image/search?p={0}&oq=&ei=UTF-8&b={1}".format(query_word,1+ 20*num)
resp = requests.get(URL, timeout=1, headers=headers)
soup = BeautifulSoup(resp.text,"lxml")
imgs = soup.find_all(alt="「{}」の画像検索結果.format(query_word)")
print(len(imgs))
for i in range(len(imgs)):
filepath = "./date/{0}/{1}-{2}.jpg".format(query_word,num,i)
urllib.request.urlretrieve(imgs[i]["src"],filepath)
———
フォルダをなければ作る
from bs4 import BeautifulSoup
import lxml
import requests
import urllib.request
import sys
query_word = sys.argv[1]
num = 0
for num in range(3):
headers = {"user-Agent": "hoge"}
URL = "https://search.yahoo.co.jp/image/search?p={0}&oq=&ei=UTF-8&b={1}".format(query_word,1+ 20*num)
resp = requests.get(URL, timeout=1, headers=headers)
soup = BeautifulSoup(resp.text,"lxml")
imgs = soup.find_all(alt="「{}」の画像検索結果.format(query_word)")
print(len(imgs))
for i in range(len(imgs)):
dir_name ="./date/{0}"
filepath = "./date/{0}/{1}-{2}.jpg".format(query_word,num,i)
urllib.request.urlretrieve(imgs[i]["src"],filepath)
———
from bs4 import BeautifulSoup
import lxml
import requests
import urllib.request
import sys,os
query_word = sys.argv[1]
num = 0
for num in range(3):
headers = {"user-Agent": "hoge"}
URL = "https://search.yahoo.co.jp/image/search?p={0}&oq=&ei=UTF-8&b={1}".format(query_word,1+ 20*num)
resp = requests.get(URL, timeout=1, headers=headers)
soup = BeautifulSoup(resp.text,"lxml")
imgs = soup.find_all(alt="「{}」の画像検索結果.format(query_word)")
print(len(imgs))
for i in range(len(imgs)):
dir_name ="./date/{0}".format(query_word)
if not os.path.exists(dir_name):
os.makedirs(dir_name)
filepath = dir_name + "{0}-{1}.jpg".format(num,i)
urllib.request.urlretrieve(imgs[i]["src"],filepath)
———
from bs4 import BeautifulSoup
import lxml
import requests
import urllib.request
import sys, os
query_word = sys.argv[1]
for num in range(2):
headers = {"user-Agent": "hoge"}
URL = "https://search.yahoo.co.jp/image/search?p={0}&oq=&ei=UTF-8&b={1}".format(query_word, 1+ 20*num)
resp = requests.get(URL, timeout=1, headers=headers)
soup = BeautifulSoup(resp.text,"lxml")
imgs = soup.find_all(alt="「{}」の画像検索結果".format(query_word))
for i in range(len(imgs)):
dir_name ="./date/{0}".format(query_word)
if not os.path.exists(dir_name):
os.makedirs(dir_name)
filepath = dir_name + "/{0}-{1}.jpg".format(num, i)
urllib.request.urlretrieve(imgs[i]["src"], filepath)
———
完成
from bs4 import BeautifulSoup
import lxml
import requests
import urllib.request
import sys, os
query_word = sys.argv[1]
max_num = int(sys.argv[2])
for num in range(max_num):
headers = {"user-Agent": "hoge"}
URL = "https://search.yahoo.co.jp/image/search?p={0}&oq=&ei=UTF-8&b={1}".format(query_word, 1+ 20*num)
resp = requests.get(URL, timeout=1, headers=headers)
soup = BeautifulSoup(resp.text,"lxml")
imgs = soup.find_all(alt="「{}」の画像検索結果".format(query_word))
for i in range(len(imgs)):
dir_name ="./date/{0}".format(query_word)
if not os.path.exists(dir_name):
os.makedirs(dir_name)
filepath = dir_name + "/{0}-{1}.jpg".format(num, i)
urllib.request.urlretrieve(imgs[i]["src"], filepath)
まとめ
今回は、備忘録になりました。
僕も勉強中ですので、コピペで思い出せるようにしておきます。
この記事を読んでいるあなたも、パイソンを学ぶきっかけになってくれればと思います。
