We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 3dc9856 commit 573368bCopy full SHA for 573368b
scraper.py
@@ -0,0 +1,30 @@
1
+import requests
2
+from bs4 import BeautifulSoup
3
+
4
+proxy = {'http': 'http://SPusername:SPpassword@gate.smartproxy.com:7000'}
5
+url = 'http://books.toscrape.com/catalogue/page-1.html'
6
7
+r = requests.get(url, proxies=proxy)
8
+html = BeautifulSoup(r.content, 'html.parser')
9
10
+all_books = html.find_all('article', class_='product_pod')
11
12
+for book in all_books:
13
+ title = book.h3.a['title']
14
+ price = book.find('p', class_='price_color').text
15
+ availability = book.find('p', class_ ='instock availability').text.strip()
16
+ link_to_book = book.h3.a['href']
17
18
+ link = "http://books.toscrape.com/catalogue/{0}".format(link_to_book)
19
20
+ r2 = requests.get(link)
21
+ html2 = BeautifulSoup(r2.content, 'html.parser')
22
23
+ description = html2.find('p', class_='').text
24
25
+ print(title)
26
+ print(price)
27
+ print(availability)
28
+ print("{0}...".format(description[:150]))
29
+ print(link)
30
+ print()
AltStyle によって変換されたページ (->オリジナル) / アドレス: モード: デフォルト 音声ブラウザ ルビ付き 配色反転 文字拡大 モバイル
0 commit comments