實現(xiàn)了用python代碼讀取本地網(wǎng)頁的并解析出其中的內(nèi)容
需要解析的網(wǎng)頁
實現(xiàn)代碼
from bs4 import BeautifulSoup
info = []
starslist = []
with open('/Users/Trudy/Desktop/plan-for-combating/week1/1_2/1_2answer_of_homework/index.html', 'r') as wb_data:
soup = BeautifulSoup(wb_data, 'lxml')
images = soup.select(
"body > div > div > div.col-md-9 > div > div > div > img")
prices = soup.select(
"body > div > div > div.col-md-9 > div > div > div > div.caption > h4.pull-right")
titles = soup.select(
"body > div > div > div.col-md-9 > div > div > div > div.caption > h4 > a")
stars = soup.select(
"body > div > div > div.col-md-9 > div > div > div > div.ratings > p:nth-of-type(2)")
reviews = soup.select(
"body > div > div > div.col-md-9 > div > div > div > div.ratings > p.pull-right")
for image,price,title,star,review in zip(images,prices,titles,stars,reviews):
data={
'image':image.get_text(),
'price':price.get_text(),
'title':title.get_text(),
'star':len(star.find_all("span","glyphicon glyphicon-star")),
'review':review.get_text()
}
info.append(data)
for i in info:
print(i['title'],i['price'],i['image'],i['review'],i['star'])
總結(jié)：
- nth-of-type（2）父元素的第二個 p 元素的每個 p
- find_all() 方法搜索當前tag的所有tag子節(jié)點,并判斷是否符合過濾器的條件.這里有幾個例子:
soup.find_all("title")
#[<title>The Dormouse's story</title>]
soup.find_all("p", "title"
[<p class="title"><b>The Dormouse's story</b></p>]
soup.find_all("a")
#[<a class="sister" id="link1">Elsie</a>,
#<a class="sister" id="link2">Lacie</a>,
#<a class="sister" id="link3">Tillie</a>]
soup.find_all(id="link2")
#[<a class="sister" id="link2">Lacie</a>]
import re
soup.find(string=re.compile("sisters"))
# u'Once upon a time there were three little sisters; and their names were\n'
