一.下厨房爬最受欢迎菜谱实例
1.#####方法1 : 先去爬取所有的最小父级标签<div class="info pure-u">，然后针对每一个父级标签，想办法提取里面的菜名、URL、食材。
import requests
# 引用requests库
from bs4 import BeautifulSoup
# 引用BeautifulSoup库
res_foods = requests.get('http://www.xiachufang.com/explore/')
# 获取数据
bs_foods = BeautifulSoup(res_foods.text,'html.parser')
# 解析数据
list_foods = bs_foods.find_all('div',class_='info pure-u')
# 查找最小父级标签
list_all = []
# 创建一个空列表，用于存储信息
for food in list_foods:
tag_a = food.find('a')
# 提取第0个父级标签中的<a>标签
name = tag_a.text[17:-13]
# 菜名，使用[17:-13]切掉了多余的信息
URL = 'http://www.xiachufang.com'+tag_a['href']
# 获取URL
tag_p = food.find('p',class_='ing ellipsis')
# 提取第0个父级标签中的<p>标签
ingredients = tag_p.text[1:-1]
# 食材，使用[1:-1]切掉了多余的信息
list_all.append([name,URL,ingredients])
# 将菜名、URL、食材，封装为列表，添加进list_all
print(list_all)
# 打印
2.方法二 : 分别提取所有的菜名、所有的URL、所有的食材。然后让菜名、URL、食材给一一对应起来（这并不复杂，第0个菜名，对应第0个URL，对应第0组食材，按顺序走即可）
import requests
# 引用requests库
from bs4 import BeautifulSoup
# 引用BeautifulSoup库
res_foods = requests.get('http://www.xiachufang.com/explore/')
# 获取数据
bs_foods = BeautifulSoup(res_foods.text,'html.parser')
# 解析数据
tag_name = bs_foods.find_all('p',class_='name')
# 查找包含菜名和URL的<p>标签
tag_ingredients = bs_foods.find_all('p',class_='ing ellipsis')
# 查找包含食材的<p>标签
list_all = []
# 创建一个空列表，用于存储信息
for x in range(len(tag_name)):
# 启动一个循环，次数等于菜名的数量
list_food = [tag_name[x].text[18:-14],tag_name[x].find('a')['href'],tag_ingredients[x].text[1:-1]]
# 提取信息，封装为列表。注意此处[18:-14]切片和之前不同，是因为此处使用的是<p>标签，而之前是<a>
list_all.append(list_food)
# 将信息添加进list_all
print(list_all)
# 打印
二.豆瓣爬前250电影
1.先爬取最小共同父级标签，然后针对每一个父级标签，提取里面的序号/电影名/评分/推荐语/链接。
import requests
from bs4 import BeautifulSoup
Url = 'https://movie.douban.com/top250?start='
startIndex = 0
trail = '&filter='
def GetNeedURL():
return Url + str(startIndex)+trail;
movies = []
for i in range(10):
startIndex = i * 25
res = requests.get(GetNeedURL())
soup = BeautifulSoup(res.text,'html.parser')
oneMovies = soup.find_all('div',class_ = 'item')
for item in oneMovies:
index = item.find('em').text
name = item.find('img')['alt'];
URL = item.find('div',class_ = 'hd').find('a')['href']
grade = item.find('span',class_ = 'rating_num').text
if item.find('p',class_ = 'quote'):
Recommendations = item.find('p',class_ = 'quote').text
Recommendation = Recommendations[1 : len(Recommendations)-1]
movies.append([index,name,URL,grade,Recommendation])
print(movies)
2.分别提取所有的序号/所有的电影名/所有的评分/所有的推荐语/所有的链接，然后再按顺序一一对应起来。
import requests
from bs4 import BeautifulSoup
Url = 'https://movie.douban.com/top250?start='
startIndex = 0
trail = '&filter='
def GetNeedURL():
return Url + str(startIndex)+trail;
movies = []
for i in range(10):
startIndex = i * 25
res = requests.get(GetNeedURL())
soup = BeautifulSoup(res.text,'html.parser')
movielist = soup.find('ol',class_ = 'grid_view')
indexs = movielist.find_all('em')
images = movielist.find_all('img')
hd = movielist.find_all('div',class_ = 'hd')
grades = movielist.find_all('span',class_ = 'rating_num')
Recommendations = movielist.find_all('div',class_ = 'bd')
for i in range(len(indexs)):
if Recommendations[i].find('p',class_ = 'quote'):
aa = Recommendations[i].find('p', class_='quote').text
Recommendation = aa[1 : len(aa)-1]
movies.append([indexs[i].text, images[i]['alt'], hd[i].find('a')['href'], grades[i].text, Recommendation])
