bs4抓取糗事百科

抓取糗事百科内容及评论，不包含图片信息。user-agent填入浏览器的即可。user-agent对应的value，360极速浏览器的话，可以在地址栏输入about:version，回车，用户代理后面的一长串就是需要填入''里面的内容。其他的可以自行百度

import urllib.request
import re
from urllib import request
from bs4 import BeautifulSoup

#1.获取网页源代码
def get_html(url):
    headers = {
        'User-Agent': '',
    }
    req = request.Request(headers=headers,url=url)
    response = urllib.request.urlopen(req)
    content = response.read().decode('utf-8')
    return content

#获取评论链接
def get_comment_link(content,comment_url_base):
    soup = BeautifulSoup(content,'html.parser')
    articleFloor = 1
    for string in soup.find_all(attrs=re.compile(r"article block untagged mb15.*?")):
        comment = str(string.get('id')).strip().split("_")[2]
        comment_url = comment_url_base % comment#评论链接
        get_comment_content(comment_url,articleFloor)#获取评论内容
        articleFloor += 1

#获取糗事内容及评论内容
def get_comment_content(comment_url,articleFloor):
    commentPage = get_html(comment_url)
    commentFloor = 1
    soupComment = BeautifulSoup(commentPage,'html.parser')
    for item in soupComment.find_all('div',class_='content'):
        print(articleFloor,".",item.get_text().strip())#获取糗事内容
    for comment in soupComment.find_all(attrs="body"):
        print("      ",commentFloor,"楼回复：",comment.get_text())#获取评论内容
        commentFloor += 1

def command():
    while True:
        raw = input("点击enter查看或者输入exit退出，请输入你的选择：")
        if raw=='enter':
            main()
            break
        else:
            break


def main():
    article_url_base = 'https://www.qiushibaike.com/8hr/page/%d/'#文章地址
    comment_url_base = 'https://www.qiushibaike.com/article/%s'#评论地址
    article_url = article_url_base % 2
    content = get_html(article_url)
    get_comment_link(content,comment_url_base)

if __name__ == '__main__':
    command()

View Code

 

转载于:https://www.cnblogs.com/smart-zihan/p/9615915.html