学习重点：
Step 1 解析数据
Step 2 通过find_all便利标签
Step 3 通过.text [‘src’][‘href’]提取内容

# 引用requests库
import requests
# 引用BeautifulSoup库
from bs4 import BeautifulSoup

# 获取数据
res_foods = requests.get('http://lvnvl.cn')
# 解析数据
bs_foods = BeautifulSoup(res_foods.text , 'html.parser')


movieLists = bs_foods.find_all('div',class_='mi_btcon')
moviesList = []
def main():
    for lis in movieLists:
        li = lis.find_all('li')
        # 打印解析结果


        for i in li:
            href = i.find('a')['href']
        #   print(tag_a)
            img = i.find('img',class_='thumb')['data-original']
        #   print(img)
            tit = i.find('h3').text
        #   print(tit)
            movie = {}
            movie['href']=href
            movie['img'] = img
            movie['tit'] = tit
            moviesList.append(movie)
    return(moviesList)
main()
print(moviesList)

进阶用法，伪装浏览器分页爬取数据

import requests, bs4

# 为躲避反爬机制，伪装成浏览器的请求头
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'}

for x in range(10):
    url = 'https://movie.douban.com/top250?start=' + str(x*25) + '&filter='
    res = requests.get(url, headers=headers)
    bs = bs4.BeautifulSoup(res.text, 'html.parser')
    bs = bs.find('ol', class_="grid_view")
    for titles in bs.find_all('div',class_='item'):
        num = titles.find('em',class_="").text
        #查找序号
        title = titles.find('span', class_="title").text
        #查找电影名
        if titles.find('span',class_="inq"):
            tes = titles.find('span',class_="inq").text
        else:
            tes = '无推荐语'
        #查找推荐语
        comment = titles.find('span',class_="rating_num").text
        #查找评分
        url_movie = titles.find('a')['href']

        print(num + '.' + title + '——' + comment + '\n' + '推荐语：' + tes +'\n' + url_movie)

import requests, bs4

# 为躲避反爬机制，伪装成浏览器的请求头
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'}
# 引用requests库
import requests
# 引用BeautifulSoup库
from bs4 import BeautifulSoup

# 获取数据
res_foods = requests.get('http://www.xiachufang.com/explore/',headers=headers)
# 解析数据
bs_foods = BeautifulSoup(res_foods.text,'html.parser')

# 查找包含菜名和URL的<p>标签
tag_name = bs_foods.find_all('p',class_='name')
# 查找包含食材的<p>标签
tag_ingredients = bs_foods.find_all('p',class_='ing ellipsis')
# 创建一个空列表，用于存储信息
list_all = []
# 启动一个循环，次数等于菜名的数量
for x in range(len(tag_name)):
    # 提取信息，封装为列表。此处[18:-14]切片的主要功能是切掉空格
    list_food = [tag_name[x].text[18:-14],tag_name[x].find('a')['href'],tag_ingredients[x].text[1:-1]]
    # 将信息添加进list_all
    list_all.append(list_food)

# 打印
print(list_all)


# 以下是另外一种解法

# 查找最小父级标签
list_foods = bs_foods.find_all('div',class_='info pure-u')
# 创建一个空列表，用于存储信息
list_all = []

for food in list_foods:
    # 提取第0个父级标签中的<a>标签
    tag_a = food.find('a')
    # 菜名，使用[17:-13]切掉了多余的信息
    name = tag_a.text[17:-13]
    # 获取URL
    URL = 'http://www.xiachufang.com'+tag_a['href']
    # 提取第0个父级标签中的<p>标签
    tag_p = food.find('p',class_='ing ellipsis')
    # 食材，使用[1:-1]切掉了多余的信息
    ingredients = tag_p.text[1:-1]
    # 将菜名、URL、食材，封装为列表，添加进list_all
    list_all.append([name,URL,ingredients])

# 打印
print(list_all)

find(),find_all()的两种常用方法

# 第一种方法：在attrs属性用字典进行传递参数
css_class = soup.find(attrs={'class':'primaryconsumers'})
print(css_class) 

#第二种方法：BeautifulSoup中的特别关键字参数class_
css_class = soup.find(class_ = 'primaryconsumers')