1 #3、書店尋寶（二）
 2 #    題目要求：你需要爬取的是網上書店Books to ScrapeTravel這類書中，所有書的書名、評分、價格三種信息，並且打印提取到的信息。
 3 #    網頁URL:http://books.toscrape.com/catalogue/category/books/travel_2/index.html
 

 4 
 5 import requests
 6 from bs4 import BeautifulSoup
 7 res = requests.get(‘http://books.toscrape.com/catalogue/category/books/travel_2/index.html‘)
 8 html = res.text
 9 soup = BeautifulSoup(html,‘html.parser‘)
10 items = soup.find_all(‘article‘,class_=‘product_pod‘)
11 for item in items:
12     print
 
(item.find(‘h3‘).find(‘a‘)[‘title‘]+‘\t‘+item.find(‘p‘)[‘class‘][1],‘\t‘,item.find(‘p‘,class_=‘price_color‘).text)
13 #    print(item.find(‘h3‘).find(‘a‘)[‘title‘])
14 #    print(item.find(‘p‘)[‘class‘][1])
15 #    print(item.find(‘p‘,class_=‘price_color‘).text)
16 
17 
18 ‘‘‘
19 執行結果如下：
20 It‘s Only the Himalayas Two      £45.17
 
21 Full Moon over Noahâs Ark: An Odyssey to Mount Ararat and Beyond    Four     £49.43
22 See America: A Celebration of Our National Parks & Treasured Sites      Three    £48.87
23 Vagabonding: An Uncommon Guide to the Art of Long-Term World Travel     Two      £36.94
24 Under the Tuscan Sun    Three    £37.33
25 A Summer In Europe      Two      £44.34
26 The Great Railway Bazaar        One      £30.54
27 A Year in Provence (Provence #1)        Four     £56.88
28 The Road to Little Dribbling: Adventures of an American in Britain (Notes From a Small Island #2)   One          £23.21
29 Neither Here nor There: Travels in Europe       Three    £38.95
30 1,000 Places to See Before You Die      Five     £26.08
31 ‘‘‘
32 
33 ‘‘‘
34 老師的代碼
35 
36 import requests
37 from bs4 import BeautifulSoup
38 
39 res_bookstore = requests.get(‘http://books.toscrape.com/catalogue/category/books/travel_2/index.html‘)
40 bs_bookstore = BeautifulSoup(res_bookstore.text,‘html.parser‘)
41 list_books = bs_bookstore.find_all(class_=‘product_pod‘)
42 for tag_books in list_books:
43 # 找到a標簽需要提取兩次
44     tag_name = tag_books.find(‘h3‘).find(‘a‘)
45 # 這個p標簽的class屬性有兩種："star-rating"，以及具體的幾星比如"Two"。我們選擇所有書都有的class屬性："star-rating"
46     list_star = tag_books.find(‘p‘,class_="star-rating")
47 # 價格比較好找，根據屬性提取，或者標簽與屬性一起都可以
48     tag_price = tag_books.find(‘p‘,class_="price_color")
49 # 這裏用到了tag[‘屬性名‘]提取屬性值
50     print(tag_name[‘title‘])
51 # 同樣是用屬性名提取屬性值
52     print(‘star-rating:‘,list_star[‘class‘][1])
53 # 用list_star[‘class‘]提取出來之後是一個由兩個值組成的列表，如："[‘star-rating‘, ‘Two‘]"，我們最終要提取的是這個列表的第1個值："Two"。
54 # 為什麽是列表呢？因為這裏的class屬性有兩個值。其實，在這個過程中，我們是使用class屬性的第一個值提取出了第二個值。
55 # 打印的時候，我加上了換行，為了讓數據更加清晰地分隔開，當然你也可以不加。</code></pre>
56     print(‘Price:‘,tag_price.text, end=‘\n‘+‘------‘+‘\n‘)
57 ‘‘‘

 1 <article class="product_pod">
 2     <div class="image_container">
 3         <a href="../../../its-only-the-himalayas_981/index.html"><img alt="It‘s Only the Himalayas" class="thumbnail"
 4                 src="../../../../media/cache/27/a5/27a53d0bb95bdd88288eaf66c9230d7e.jpg" /></a>
 5     </div>
 6     <p class="star-rating Two">
 7         <i class="icon-star"></i>
 8         <i class="icon-star"></i>
 9         <i class="icon-star"></i>
10         <i class="icon-star"></i>
11         <i class="icon-star"></i>
12     </p>
13     <h3><a href="../../../its-only-the-himalayas_981/index.html" title="It‘s Only the Himalayas">It‘s Only the
14             Himalayas</a></h3>
15     <div class="product_price">
16         <p class="price_color">£45.17</p>
17         <p class="instock availability">
18             <i class="icon-ok"></i>
19 
20 
21             In stock
22 
23 
24         </p>
25         <form>
26             <button class="btn btn-primary btn-block" data-loading-text="Adding..." type="submit">Add to basket</button>
27         </form>
28     </div>
29 </article>

03、書店尋寶（二）