作业笔记03_request&bs4
2017-02-07 本文已影响45人
ChZ_CC
-
http://www.pythonscraping.com/pages/warandpeace.html
- 提取以上网页中所有的对话(显示为红色字体)
-
http://www.pythonscraping.com/pages/page3.html
- 提取以上网页中礼物标题(title)和礼物花费(cost)
- 查询礼物“Dead Parrot” 的花费(cost)
import requests
from bs4 import BeautifulSoup
url_1 = 'http://www.pythonscraping.com/pages/warandpeace.html'
url_2 = 'http://www.pythonscraping.com/pages/page3.html'
r1 = requests.get(url_1)
r2 = requests.get(url_2)
soup1 = BeautifulSoup(r1.content, 'html.parser')
soup2 = BeautifulSoup(r2.content, 'html.parser')
# 1)提取以上网页中所有的对话(显示为红色字体)
redText = soup1.find_all("span", {"class":"red"})
for item in redText:
print(item.text)
# 2)提取以上网页中礼物标题(title)和礼物花费(cost)
# title
items = soup2.find_all('tr',{"class":"gift"})
for item in items:
print(item.td.text)
#cost
for item in items:
print(item.contents[2].text)