Chapter complicated HTML parsing

bsObj.findAll(tagName, tagAttributes)

.get_text () will these hyperlinks, and paragraph tags are removed, leaving only the text string with no label.

findAll(tag, attributes, recursive, text, limit, keywords)

find(tag, attributes, recursive, text, keywords)

.findAll({"h1","h2","h3","h4","h5","h6"})

.findAll("span", {"class":{"green", "red"}})

nameList = bsObj.findAll(text="the prince") print(len(nameList))

from urllib.request import urlopen
from bs4 import BeautifulSoup

html = urlopen("http://www.pythonscraping.com/pages/warandpeace.html")
bsObj = BeautifulSoup(html, features="lxml")
namelist = bsObj.findAll("span", {"class": "green"})
for name in namelist:
    print(name.get_text())

output

Anna
Pavlovna Scherer
Empress Marya
Fedorovna
Prince Vasili Kuragin
Anna Pavlovna
St. Petersburg
the prince
Anna Pavlovna
Anna Pavlovna
the prince
the prince
the prince
Prince Vasili
Anna Pavlovna
Anna Pavlovna
the prince
Wintzingerode
King of Prussia
le Vicomte de Mortemart
Montmorencys
Rohans
Abbe Morio
the Emperor
the prince
Prince Vasili
Dowager Empress Marya Fedorovna
the baron
Anna Pavlovna
the Empress
the Empress
Anna Pavlovna's
Her Majesty
Baron
Funke
The prince
Anna
Pavlovna
the Empress
The prince
Anatole
the prince
The prince
Anna
Pavlovna
Anna Pavlovna

 

from urllib.request import urlopen
from bs4 import BeautifulSoup

html = urlopen("http://www.pythonscraping.com/pages/page3.html")
bsObj = BeautifulSoup(html, features="lxml")

for child in bsObj.find("table", {"id": "giftList"}).children:
    print(child)

output

<tr><th>
Item Title
</th><th>
Description
</th><th>
Cost
</th><th>
Image
</th></tr>


<tr class="gift" id="gift1"><td>
Vegetable Basket
</td><td>
This vegetable basket is the perfect gift for your health conscious (or overweight) friends!
<span class="excitingNote">Now with super-colorful bell peppers!</span>
</td><td>
$15.00
</td><td>
<img src="../img/gifts/img1.jpg"/>
</td></tr>


<tr class="gift" id="gift2"><td>
Russian Nesting Dolls
</td><td>
Hand-painted by trained monkeys, these exquisite dolls are priceless! And by "priceless," we mean "extremely expensive"! <span class="excitingNote">8 entire dolls per set! Octuple the presents!</span>
</td><td>
$10,000.52
</td><td>
<img src="../img/gifts/img2.jpg"/>
</td></tr>


<tr class="gift" id="gift3"><td>
Fish Painting
</td><td>
If something seems fishy about this painting, it's because it's a fish! <span class="excitingNote">Also hand-painted by trained monkeys!</span>
</td><td>
$10,005.00
</td><td>
<img src="../img/gifts/img3.jpg"/>
</td></tr>


<tr class="gift" id="gift4"><td>
Dead Parrot
</td><td>
This is an ex-parrot! <span class="excitingNote">Or maybe he's only resting?</span>
</td><td>
$0.50
</td><td>
<img src="../img/gifts/img4.jpg"/>
</td></tr>


<tr class="gift" id="gift5"><td>
Mystery Box
</td><td>
If you love suprises, this mystery box is for you! Do not place on light-colored surfaces. May cause oil staining. <span class="excitingNote">Keep your friends guessing!</span>
</td><td>
$1.50
</td><td>
<img src="../img/gifts/img6.jpg"/>
</td></tr>

处理兄弟标签

把bsObj.find("table", {"id": "giftList"}).children改为以下，可以跳过标题

for sibling in bsObj.find("table", {"id": "giftList"}).tr.next_siblings:
       print(sibling)

处理父标签

from urllib.request import urlopen
from bs4 import BeautifulSoup

html = urlopen("http://www.pythonscraping.com/pages/page3.html")
bsObj = BeautifulSoup(html, features="lxml")

print(bsObj.find("img", {"src": "../img/gifts/img1.jpg"
                            }).parent.previous_sibling.get_text())

正则表达式

from urllib.request import urlopen
from bs4 import BeautifulSoup
import re

html = urlopen("http://www.pythonscraping.com/pages/page3.html")
bsObj = BeautifulSoup(html, features='lxml')
images = bsObj.findAll("img", {"src": re.compile("\.\.\/img\/gifts\/img.*\.jpg")})
for image in images:
    print(image["src"])

output

../img/gifts/img1.jpg
../img/gifts/img2.jpg
../img/gifts/img3.jpg
../img/gifts/img4.jpg
../img/gifts/img6.jpg

 

2019-10-10

17:22:17