python网络爬虫，对小甲鱼课程的复现练习

豆瓣top250排行1.1

import requests
import bs4
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)

导入requests 和BeautifulSoup4

获取目标网址

将res获取的文本内容导入soup,启用默认解析器“html.parser”

将所有查找到的“div”（class_="hd"）放进targets中

利用for循环将targets中的内容输出。

豆瓣top250排行1.2

import requests
import bs4
import re

def open_url(url):
    #使用代理
    headers = {'uer-agent': 'Mozilla/5.0(windows NT 10.0;WOW64) Applewebkit/537.36(KHTML,like Gecko) Chrome/57.0.2987.98 Safari/537.36'}
    res =requests.get(url,headers=headers)

    return res

def find_movies(res):
    soup = bs4.BeautifulSoup(res.text, 'html.parser')
    #电影名
    movies =[]
    targets = soup.find_all("div",class_="hd")
    for each in targets:
        movies.append(each.a.span.text)
    #评分
    ranks =[]
    targets = soup.find_all("span",class_="rating_num")
    for each in targets:
        ranks.append('评分：%s' % each.text)
    #资料
    messages =[]
    targets = soup.find_all("div",class_="bd")
    for each in targets:
        try:
            messages.append(each.p.text.split('\n')[1].strip()+each.p.text.split('\n')[2].strip())
        except:
            continue

    result =[]
    length = len(movies)
    for i in range(movies):
        result.append(movies[i]+ranks[i]+messages[i]+'\n')
    return result
#找出一共有多少个页面
def find_depth(res):
    soup = bs4.BeautifulSoup(res.text,'html.parser')
    depth = soup.find('span',class_='next').previous_sibling.previous.sibling.text

    return int (depth)

def main():
    host = "https://moive.douban.com/top250"
    res = open_url(host)
    depth = find_depth(res)

    result = []
    for i in range(depth):
        url = host +'/?start='+str(25*i)
        res = open_url(url)
        result.extend(find_movies(res))

        with open("豆瓣TOP250电影.txt","w",encoding="utf-8") as f:
            for each in result:
                f.write(each)

if __name__=="__main__" :
    main()