網絡爬蟲練習

1.利用requests.get(url)獲取網頁頁面的html文件

import requests
newsurl='http://news.gzcc.cn/html/xiaoyuanxinwen/'
res = requests.get(newsurl) #返回response對象
res.encoding='utf-8'
print(res.text)

?

2.利用BeautifulSoup的HTML解析器，生成結構樹

import requests
from bs4 import BeautifulSoup
newsurl='http://news.gzcc.cn/html/xiaoyuanxinwen/'
res = requests.get(newsurl) #返回response對象
res.encoding='utf-8'
print(BeautifulSoup(res.text,'html.parser'))

3.找出特定標簽的html元素

soup.p #標簽名，返回第一個

soup.head

soup.p.name #字符串

soup.p. attrs #字典，標簽的所有屬性

soup.p. contents # 列表，所有子標簽

soup.p.text #字符串

soup.p.string

soup.select(‘li')

?

4.取得含有特定CSS屬性的元素

soup.select('#p1Node')

soup.select('.news-list-title')

?

5.練習：

取出h1標簽的文本

import requests
from bs4 import BeautifulSoup
url = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
res = requests.get(url)
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text,'html.parser')
#取h4標簽的文本
print(soup.select('h4')[0].text)

?

取出a標簽的鏈接

import requests
from bs4 import BeautifulSoup
url = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
res = requests.get(url)
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text,'html.parser')
#取a標簽的鏈接
for i in soup.select('a'):print(i.get('href'))

?

取出所有li標簽的所有內容

import requests
from bs4 import BeautifulSoup
url = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
res = requests.get(url)
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text,'html.parser')
#取li標簽的所有內容
for i in soup.select('li'):print(i)

?

取出一條新聞的標題、鏈接、發布時間、來源

import requests
from bs4 import BeautifulSoup
url = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
res = requests.get(url)
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text,'html.parser')# 取出一條新聞的標題、鏈接、發布時間、來源
print(soup.select('.news-list-title')[0].text)
print(soup.select('li')[1].a.attrs['href'])
print(soup.select('.news-list-info')[0].contents[0].text)
print(soup.select('.news-list-info')[0].contents[1].text)

?