一、使用 BeautifulSoup抓取网页信息信息

from bs4 import  BeautifulSoup

with open(‘C:/Users/michael/Desktop/Plan-for-combating-master/week1/1_2/1_2code_of_video/web/new_index.html‘,‘r‘) as web_data:
    Soup = BeautifulSoup(web_data,‘lxml‘)
    print(Soup)

  """
    body > div.main-content > ul > li:nth-child(1) > div.article-info > h3 > a
    body > div.main-content > ul > li:nth-child(1) > div.article-info > p.meta-info > span:nth-child(2)
    body > div.main-content > ul > li:nth-child(1) > div.article-info > p.description
    body > div.main-content > ul > li:nth-child(1) > div.rate > span
    body > div.main-content > ul > li:nth-child(1) > img
    """

  images = Soup.select(‘body > div.main-content > ul > li:nth-child(1) > img‘)
    print(images)

  images = Soup.select(‘body > div.main-content > ul > li:nth-of-type(1) > img‘)
    print(images)

    images = Soup.select(‘body > div.main-content > ul > li > img‘)
    print(images)

    titles = Soup.select(‘body > div.main-content > ul > li > div.article-info > h3 > a‘)
    descs = Soup.select(‘body > div.main-content > ul > li > div.article-info > p.description‘)
    rates = Soup.select(‘ body > div.main-content > ul > li > div.rate > span‘)
    cates = Soup.select(‘ body > div.main-content > ul > li > div.article-info > p.meta-info > span‘)
    print(images,titles,descs,rates,cates,sep=‘\n-----------\n‘)

for title in titles:
        print(title.get_text())

for title,image,desc,rate,cate in zip(titles,images,descs,rates,cates):
        data = {
            ‘title‘:title.get_text(),
            ‘rate‘:rate.get_text(),
            ‘desc‘:desc.get_text(),
            ‘cate‘:cate.get_text(),
            ‘image‘:image.get(‘src‘)
        }
        print(data)

cates = Soup.select(‘ body > div.main-content > ul > li > div.article-info > p.meta-info‘)

for title,image,desc,rate,cate in zip(titles,images,descs,rates,cates):
        data = {
            ‘title‘:title.get_text(),
            ‘rate‘:rate.get_text(),
            ‘desc‘:desc.get_text(),
            ‘cate‘:list(cate.stripped_strings),
            ‘image‘:image.get(‘src‘)
        }
        print(data)

#找到评分大于3的文章
for i in info:
    if float(i[‘rate‘])>3:
        print(i[‘title‘],i[‘cate‘])

from bs4 import  BeautifulSoup
info =[]
with open(‘C:/Users/michael/Desktop/Plan-for-combating-master/week1/1_2/1_2code_of_video/web/new_index.html‘,‘r‘) as web_data:
    Soup = BeautifulSoup(web_data,‘lxml‘)
    # print(Soup)
    """
    body > div.main-content > ul > li:nth-child(1) > div.article-info > h3 > a
    body > div.main-content > ul > li:nth-child(1) > div.article-info > p.meta-info > span:nth-child(2)
    body > div.main-content > ul > li:nth-child(1) > div.article-info > p.description
    body > div.main-content > ul > li:nth-child(1) > div.rate > span
    body > div.main-content > ul > li:nth-child(1) > img
    """
    images = Soup.select(‘body > div.main-content > ul > li > img‘)

    titles = Soup.select(‘body > div.main-content > ul > li > div.article-info > h3 > a‘)
    descs = Soup.select(‘body > div.main-content > ul > li > div.article-info > p.description‘)
    rates = Soup.select(‘ body > div.main-content > ul > li > div.rate > span‘)
    cates = Soup.select(‘ body > div.main-content > ul > li > div.article-info > p.meta-info‘)
    # print(images,titles,descs,rates,cates,sep=‘\n-----------\n‘)

for title,image,desc,rate,cate in zip(titles,images,descs,rates,cates):
        data = {
            ‘title‘:title.get_text(),
            ‘rate‘:rate.get_text(),
            ‘desc‘:desc.get_text(),
            ‘cate‘:list(cate.stripped_strings),
            ‘image‘:image.get(‘src‘)
        }
        #添加到列表中
        info.append(data)
#找到评分大于3的文章
for i in info:
    if float(i[‘rate‘])>3:
        print(i[‘title‘],i[‘cate‘])