python爬虫爬取腾讯新闻

admin管理员组

文章数量:1130349

python爬虫爬取腾讯新闻

话不多说，直接上代码！

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()
    fo = open("text.txt", "w+")
    fo.writelines(title[0].get_text() + "\n")
    fo.writelines(time[0].get_text() + "\n")
    for para in paras:
        if len(para) > 0:
            fo.writelines(para.get_text() + "\n\n")
    fo.writelines(author[0].get_text() + '\n')
    fo.close()
    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/a/20170504/012032.htm"
    getContent(url);
main()

运行结果：

python爬虫爬取腾讯新闻

话不多说，直接上代码！

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()
    fo = open("text.txt", "w+")
    fo.writelines(title[0].get_text() + "\n")
    fo.writelines(time[0].get_text() + "\n")
    for para in paras:
        if len(para) > 0:
            fo.writelines(para.get_text() + "\n\n")
    fo.writelines(author[0].get_text() + '\n')
    fo.close()
    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/a/20170504/012032.htm"
    getContent(url);
main()

运行结果：

本文标签： 爬虫腾讯新闻python