• 28 comments
• Andrew Coyne

3. CSS选择器强化练习

1. 爬取文章标题

import requests
from bs4 import BeautifulSoup

url = "http://www.shixiaolei.com/2022/3/7/1-pa-chong-ru-men/"
r = requests.get(url)
soup = BeautifulSoup(r.text,'lxml')
data = soup.select('ul.tabNav li a')
for i in data:
    print(i.get_text())

2. 爬取发布日期和作者

data = soup.select('p.date')
for i in data:
    print(i.get_text())

3. 爬取正文

data = soup.select('.post_text')
for i in data:
    print(i.get_text())

4. 爬取导航菜单

data = soup.select('ul.nav li a')
for i in data:
    print(i.get_text(strip=True))

5. 爬取底部文字

data = soup.select('ul.foot li p')
for i in data:
    print(i.get_text(strip=True))

6. 爬取科信新闻列表页标题

url = "http://www.hebkx.cn/jijiao/main/index.php"
r = requests.get(url)
soup = BeautifulSoup(r.text,'lxml')
data = soup.select('.mod_NewsList2 li a')
for i in data:
    print(i.get_text())

7. 爬取爬取科信新闻详情页标题和正文

url = "http://www.hebkx.cn/jijiao/html/?6173.html"
r = requests.get(url)
soup = BeautifulSoup(r.text,'lxml')
data = soup.select('.newstitle')
print(data[0].get_text())
data = soup.select('.detail')
print(data[0].get_text(strip=True))

8. 爬取菜单

url = "http://www.hebkx.cn/jijiao/html/?6173.html"
r = requests.get(url)
soup = BeautifulSoup(r.text,'lxml')
data = soup.select('.menu li a')
for i in data:
    print(i.get_text())