0. 前言
本部分爲爬蟲自學教程
1. 代碼部分
1、爬取信息(學習)
import requests(模塊)
import bs4(未安裝模塊)
res=requests.get("https://movie.douban.com/top250")
soup=bs4.BeautifulSoup(res.text,"html.parser")
targets=soup.find_all("div",class_="hd")
for each in targets:
print(each.a.span.text)
結果未出來
2、參考網站 https://ilovefishc.com/dvd/
3、學習爬取豆瓣電影信息
import requests
from bs4 import BeautifulSoup
for i in range (0,10):
url = "https://movie.douban.com/top250?start="+(str(i*25))
#獲取網頁
response = requests.get(url)
#解析網頁
soup = BeautifulSoup(response.text,"html.parser")
movie_list = soup.find_all(name='div',attrs={'class':'info'})
#print(movie_list)
print("\n"+str(i+1)+" 頁:\n")
#遍歷網頁信息
for movie_information in movie_list:
m_name = movie_information.find(name = 'span',class_ = 'title').text
m_score = movie_information.find(name = 'span',class_='rating_num').text
print(m_name+" "+m_score)