网络爬虫抓取某年份腾讯新闻内容

Posted 2021-03-04 laiqunshi

首先要获取网页的代码，先将其装成一个函数

def gethtmlText(url):
    try:
        r = requests.get(url, timeout = 30)
        r.raise_for_status()
        #r.encoding = ‘utf-8‘
        return r.text
    except:
        return ""

在chrome浏览器下，直接进去新闻之后，右键题目检查就可以定位到题目所在的html代码，如下图

 

 然后会看到<h1>标签内，它的上一级标签是div，并且class="hd"，BeautifulSoup提供了一个CSS选择器，直接调用select方法即可

所以代码可以写成

def getContent(url):
    html = getHTMLText(url)
    # print(html)
    soup = BeautifulSoup(html, "html.parser")
    title = soup.select("div.hd > h1")
    print(title[0].get_text())
    time = soup.select("div.a_Info > span.a_time")
    print(time[0].string)
    author = soup.select("div.qq_articleFt > div.qq_toolWrap > div.qq_editor")
    print(author[0].get_text())
    paras = soup.select("div.Cnt-Main-Article-QQ > p.text")
    for para in paras:
        if len(para) > 0:
            print(para.get_text())
            print()

完整源代码

#此代码主要是从给定腾讯新闻网页中爬取新闻的题目，时间，正文，作者
import requests
from bs4 import BeautifulSoup
def getHTMLText(url):
    try:
        r = requests.get(url, timeout = 30)
        r.raise_for_status()
        #r.encoding = ‘utf-8‘
        return r.text
    except:
        return ""
def getContent(url):
    html = getHTMLText(url)
    # print(html)
    soup = BeautifulSoup(html, "html.parser")
    title = soup.select("div.hd > h1")
    print(title[0].get_text())
    time = soup.select("div.a_Info > span.a_time")
    print(time[0].string)
    author = soup.select("div.qq_articleFt > div.qq_toolWrap > div.qq_editor")
    print(author[0].get_text())
    paras = soup.select("div.Cnt-Main-Article-QQ > p.text")
    for para in paras:
        if len(para) > 0:
            print(para.get_text())
            print()
    #写入文件
    fo = open("text.txt", "w+")
    fo.writelines(title[0].get_text() + "
")
    fo.writelines(time[0].get_text() + "
")
    for para in paras:
        if len(para) > 0:
            fo.writelines(para.get_text() + "

")
    fo.writelines(author[0].get_text() + ‘
‘)
    fo.close()
    #将爬取到的文章用字典格式来存
    article = {
        ‘Title‘ : title[0].get_text(),
        ‘Time‘ : time[0].get_text(),
        ‘Paragraph‘ : paras,
        ‘Author‘ : author[0].get_text()
    }
    print(article)
def main():
    url = "http://news.qq.com/a/20170504/012032.htm"
    getContent(url);
main()