Python实战3

Python实战3
1.小demo ：爬取豆瓣电影前几名

import requests
import bs4

res=requests.get("https://movie.douban.com/top250") //获得网址
soup=bs4.BeautifulSoup(res.text,"html.parser")     //“熬汤”解析网页内容
targets=soup.find_all("div",class_="hd")        //找到目标
for each in targets:                                            //输出目标
    print(each.a.span.text)

备注：尤其注意“找到目标“”时要加下划线 class_
2.可以实现翻页爬取

import requests
import bs4
import re


def open_url(url):
    # 使用代理
    # proxies = {"http": "127.0.0.1:1080", "https": "127.0.0.1:1080"}
    headers = {
        'user-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, proxies=proxies)
    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(length):
        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://movie.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()

备注：运行结果就是生成一个.txt文档