requests库和BeautifulSoup4库爬取新闻列表

Posted 2020-10-08 410陈锐锦

画图显示：

 

import jieba
from wordcloud import WordCloud
import matplotlib.pyplot as plt

txt = open("zuihou.txt","r",encoding=\'utf-8\').read()
wordlist = jieba.lcut(txt)

 

wl_split=" ".join(wordlist)
mywc = WordCloud().generate(wl_split)
plt.imshow(mywc)
plt.axis("off")
plt.show()

结果：

 

 用requests库和BeautifulSoup4库，爬取校园新闻列表的时间、标题、链接、来源、详细内容

爬虫，网页信息

import requests
from bs4 import BeautifulSoup

gzccurl = \'http://news.gzcc.cn/html/xiaoyuanxinwen/\'
res = requests.get(gzccurl)
res.encoding = \'utf-8\'

soup = BeautifulSoup(res.text,\'html.parser\')
for news in soup.select(\'li\'):
    if len(news.select(\'.news-list-title\'))>0:
        title = news.select(\'.news-list-title\')[0].text
        url = news.select(\'a\')[0][\'href\']
        print(title,url)

结果：

 加上时间：

for news in soup.select(\'li\'):
    if len(news.select(\'.news-list-title\'))>0:
        title = news.select(\'.news-list-title\')[0].text
        url = news.select(\'a\')[0][\'href\']
        time = news.select(\'.news-list-info\')[0].contents[0].text
        
        print(time,title,url)

效果：

• 将其中的时间str转换成datetime类型。
• 将取得详细内容的代码包装成函数。

import requests
from bs4 import BeautifulSoup
from datetime import datetime

gzccurl = \'http://news.gzcc.cn/html/xiaoyuanxinwen/\'
res = requests.get(gzccurl)
res.encoding = \'utf-8\'

soup = BeautifulSoup(res.text,\'html.parser\')
def getdetail(url):
    resd = requests.get(url)
    resd.encoding= \'utf-8\'
    soupd = BeautifulSoup(resd.text,\'html.parser\')
    return(soupd.select(\'.show-content\')[0].text)

for news in soup.select(\'li\'):
    if len(news.select(\'.news-list-title\'))>0:
        title = news.select(\'.news-list-title\')[0].text
        url = news.select(\'a\')[0][\'href\']
        time = news.select(\'.news-list-info\')[0].contents[0].text
        dt = datetime.strptime(time,\'%Y-%m-%d\')
        source = news.select(\'.news-list-info\')[0].contents[1].text
        detail = getdetail(url)
        print(dt,title,url,source,detail)

结果：

• 选一个自己感兴趣的主题，做类似的操作，为后面“爬取网络数据并进行文本分析”做准备。

import requests
from bs4 import BeautifulSoup
from datetime import datetime

gzccurl = \'http://www.lbldy.com/tag/gqdy/\'
res = requests.get(gzccurl)
res.encoding = \'utf-8\'

soup = BeautifulSoup(res.text,\'html.parser\')
def getdetail(url):
    resd = requests.get(url)
    resd.encoding= \'utf-8\'
    soupd = BeautifulSoup(resd.text,\'html.parser\')
    return(soupd.select(\'.show-content\')[0].text)

for news in soup.select(\'h4\'):
    
        print(news)

结果：