{"id":1108530,"date":"2025-01-08T17:01:09","date_gmt":"2025-01-08T09:01:09","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1108530.html"},"modified":"2025-01-08T17:01:12","modified_gmt":"2025-01-08T09:01:12","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e7%88%ac%e5%8f%96%e8%b1%86%e7%93%a3top250","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1108530.html","title":{"rendered":"\u5982\u4f55\u7528python\u722c\u53d6\u8c46\u74e3top250"},"content":{"rendered":"

\"\u5982\u4f55\u7528python\u722c\u53d6\u8c46\u74e3top250\"<\/p>\n

\u4f7f\u7528Python\u722c\u53d6\u8c46\u74e3Top250\u7684\u65b9\u6cd5\u5305\u62ec\uff1a\u4f7f\u7528requests\u5e93\u8fdb\u884c\u7f51\u9875\u8bf7\u6c42\u3001\u4f7f\u7528BeautifulSoup\u5e93\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u3001\u63d0\u53d6\u7535\u5f71\u4fe1\u606f\u5e76\u4fdd\u5b58\u6570\u636e<\/strong>\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u5c06\u8be6\u7ec6\u5c55\u5f00\u5176\u4e2d\u4e00\u4e2a\u6b65\u9aa4\uff1a\u4f7f\u7528BeautifulSoup\u89e3\u6790\u7f51\u9875\u5185\u5bb9<\/strong>\u3002<\/p>\n<\/p>\n

\u4f7f\u7528BeautifulSoup\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u6d89\u53ca\u521b\u5efaBeautifulSoup\u5bf9\u8c61\u5e76\u4f7f\u7528\u5176\u65b9\u6cd5\u6765\u67e5\u627e\u548c\u63d0\u53d6\u7279\u5b9a\u7684HTML\u5143\u7d20\u3002\u5177\u4f53\u6765\u8bf4\uff0c\u9996\u5148\u8981\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\uff0c\u7136\u540e\u5229\u7528BeautifulSoup\u8fdb\u884c\u89e3\u6790\u3002\u901a\u8fc7\u5206\u6790\u7f51\u9875\u7ed3\u6784\uff0c\u53ef\u4ee5\u5b9a\u4f4d\u5230\u9700\u8981\u63d0\u53d6\u7684\u4fe1\u606f\uff0c\u5982\u7535\u5f71\u540d\u79f0\u3001\u8bc4\u5206\u3001\u8bc4\u8bba\u7b49\u3002<\/p>\n<\/p>\n

\u4e0b\u9762\u662f\u8be6\u7ec6\u7684\u5b9e\u73b0\u6b65\u9aa4\uff1a<\/p>\n<\/p>\n

\u4e00\u3001\u5b89\u88c5\u6240\u9700\u5e93<\/h3>\n<\/p>\n

\u9996\u5148\uff0c\u786e\u4fdd\u5b89\u88c5\u4e86requests\u548cBeautifulSoup\u5e93\u3002\u5982\u679c\u6ca1\u6709\u5b89\u88c5\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n

pip install requests<\/p>\n
pip install beautifulsoup4<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/h3>\n<\/p>\n
\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
url = "https:\/\/movie.douban.com\/top250"<\/p>\n
headers = {<\/p>\n
    "User-Agent": "Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.110 Safari\/537.3"<\/p>\n
}<\/p>\n
response = requests.get(url, headers=headers)<\/p>\n
html_content = response.text<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u89e3\u6790\u7f51\u9875\u5185\u5bb9<\/h3>\n<\/p>\n
\u4f7f\u7528BeautifulSoup\u89e3\u6790\u7f51\u9875\u5185\u5bb9\uff0c\u63d0\u53d6\u7535\u5f71\u4fe1\u606f\uff1a<\/p>\n<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
soup = BeautifulSoup(html_content, 'html.parser')<\/p>\n
movies = soup.find_all('div', class_='item')<\/p>\n
for movie in movies:<\/p>\n
    title = movie.find('span', class_='title').text<\/p>\n
    rating = movie.find('span', class_='rating_num').text<\/p>\n
    quote = movie.find('span', class_='inq').text if movie.find('span', class_='inq') else ""<\/p>\n
    print(f"Title: {title}, Rating: {rating}, Quote: {quote}")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u5904\u7406\u5206\u9875<\/h3>\n<\/p>\n
\u8c46\u74e3Top250\u6709\u591a\u9875\u5185\u5bb9\uff0c\u9700\u8981\u5904\u7406\u5206\u9875\u6765\u83b7\u53d6\u6240\u6709\u6570\u636e\uff1a<\/p>\n<\/p>\n
import time<\/p>\n
all_movies = []<\/p>\n
for i in range(0, 250, 25):<\/p>\n
    url = f"https:\/\/movie.douban.com\/top250?start={i}"<\/p>\n
    response = requests.get(url, headers=headers)<\/p>\n
    soup = BeautifulSoup(response.text, 'html.parser')<\/p>\n
    movies = soup.find_all('div', class_='item')<\/p>\n
    for movie in movies:<\/p>\n
        title = movie.find('span', class_='title').text<\/p>\n
        rating = movie.find('span', class_='rating_num').text<\/p>\n
        quote = movie.find('span', class_='inq').text if movie.find('span', class_='inq') else ""<\/p>\n
        all_movies.append({<\/p>\n
            "title": title,<\/p>\n
            "rating": rating,<\/p>\n
            "quote": quote<\/p>\n
        })<\/p>\n
    time.sleep(1)  # \u907f\u514d\u8fc7\u4e8e\u9891\u7e41\u7684\u8bf7\u6c42\u5bfc\u81f4\u88ab\u5c01\u7981<\/p>\n
\u6253\u5370\u6240\u6709\u7535\u5f71\u4fe1\u606f<\/strong><\/h2>\n
for movie in all_movies:<\/p>\n
    print(movie)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u4fdd\u5b58\u6570\u636e<\/h3>\n<\/p>\n
\u5c06\u63d0\u53d6\u5230\u7684\u6570\u636e\u4fdd\u5b58\u5230CSV\u6587\u4ef6\uff1a<\/p>\n<\/p>\n
import csv<\/p>\n
with open('douban_top250.csv', 'w', newline='', encoding='utf-8') as csvfile:<\/p>\n
    fieldnames = ['Title', 'Rating', 'Quote']<\/p>\n
    writer = csv.DictWriter(csvfile, fieldnames=fieldnames)<\/p>\n
    writer.writeheader()<\/p>\n
    for movie in all_movies:<\/p>\n
        writer.writerow({'Title': movie['title'], 'Rating': movie['rating'], 'Quote': movie['quote']})<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516d\u3001\u4ee3\u7801\u5b8c\u6574\u6027\u4e0e\u5f02\u5e38\u5904\u7406<\/h3>\n<\/p>\n
\u4e3a\u4e86\u786e\u4fdd\u4ee3\u7801\u7684\u5065\u58ee\u6027\uff0c\u6dfb\u52a0\u5f02\u5e38\u5904\u7406\uff1a<\/p>\n<\/p>\n
import requests<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
import csv<\/p>\n
import time<\/p>\n
def get_html(url, headers):<\/p>\n
    try:<\/p>\n
        response = requests.get(url, headers=headers)<\/p>\n
        response.rAI<\/a>se_for_status()<\/p>\n
        return response.text<\/p>\n
    except requests.RequestException as e:<\/p>\n
        print(f"Error fetching {url}: {e}")<\/p>\n
        return None<\/p>\n
def parse_html(html):<\/p>\n
    soup = BeautifulSoup(html, 'html.parser')<\/p>\n
    movies = soup.find_all('div', class_='item')<\/p>\n
    movie_list = []<\/p>\n
    for movie in movies:<\/p>\n
        title = movie.find('span', class_='title').text<\/p>\n
        rating = movie.find('span', class_='rating_num').text<\/p>\n
        quote = movie.find('span', class_='inq').text if movie.find('span', class_='inq') else ""<\/p>\n
        movie_list.append({<\/p>\n
            "title": title,<\/p>\n
            "rating": rating,<\/p>\n
            "quote": quote<\/p>\n
        })<\/p>\n
    return movie_list<\/p>\n
def save_to_csv(movies, filename):<\/p>\n
    with open(filename, 'w', newline='', encoding='utf-8') as csvfile:<\/p>\n
        fieldnames = ['Title', 'Rating', 'Quote']<\/p>\n
        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)<\/p>\n
        writer.writeheader()<\/p>\n
        for movie in movies:<\/p>\n
            writer.writerow({'Title': movie['title'], 'Rating': movie['rating'], 'Quote': movie['quote']})<\/p>\n
def main():<\/p>\n
    url_template = "https:\/\/movie.douban.com\/top250?start={}"<\/p>\n
    headers = {<\/p>\n
        "User-Agent": "Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.110 Safari\/537.3"<\/p>\n
    }<\/p>\n
    all_movies = []<\/p>\n
    for i in range(0, 250, 25):<\/p>\n
        url = url_template.format(i)<\/p>\n
        html = get_html(url, headers)<\/p>\n
        if html:<\/p>\n
            movies = parse_html(html)<\/p>\n
            all_movies.extend(movies)<\/p>\n
        time.sleep(1)  # \u907f\u514d\u8fc7\u4e8e\u9891\u7e41\u7684\u8bf7\u6c42\u5bfc\u81f4\u88ab\u5c01\u7981<\/p>\n
    save_to_csv(all_movies, 'douban_top250.csv')<\/p>\n
if __name__ == "__main__":<\/p>\n
    main()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e03\u3001\u603b\u7ed3<\/h3>\n<\/p>\n
\u4e0a\u8ff0\u65b9\u6cd5\u8be6\u7ec6\u4ecb\u7ecd\u4e86\u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u8c46\u74e3Top250\u7535\u5f71\u4fe1\u606f\uff0c\u6db5\u76d6\u4e86HTTP\u8bf7\u6c42\u3001HTML\u89e3\u6790\u3001\u6570\u636e\u63d0\u53d6\u3001\u5206\u9875\u5904\u7406\u548c\u6570\u636e\u4fdd\u5b58\u7b49\u6b65\u9aa4\u3002\u901a\u8fc7\u4f7f\u7528requests\u5e93\u53d1\u9001\u8bf7\u6c42\u3001BeautifulSoup\u5e93\u89e3\u6790HTML\u5185\u5bb9\uff0c\u53ef\u4ee5\u8f7b\u677e\u5730\u4ece\u8c46\u74e3\u7535\u5f71\u9875\u9762\u4e2d\u63d0\u53d6\u6240\u9700\u4fe1\u606f\uff0c\u5e76\u5c06\u5176\u4fdd\u5b58\u5230CSV\u6587\u4ef6\u4e2d<\/strong>\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u8c46\u74e3Top250\u7684\u7535\u5f71\u4fe1\u606f\uff1f<\/strong>
\u8981\u7528Python\u722c\u53d6\u8c46\u74e3Top250\uff0c\u53ef\u4ee5\u4f7f\u7528\u7b2c\u4e09\u65b9\u5e93\u5982Requests\u548cBeautifulSoup\u3002\u9996\u5148\uff0c\u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u7136\u540e\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\uff0c\u63d0\u53d6\u7535\u5f71\u540d\u79f0\u3001\u8bc4\u5206\u3001\u94fe\u63a5\u7b49\u4fe1\u606f\u3002\u786e\u4fdd\u9075\u5faa\u8c46\u74e3\u7684\u722c\u53d6\u89c4\u5219\uff0c\u907f\u514d\u9891\u7e41\u8bf7\u6c42\u5bfc\u81f4IP\u88ab\u5c01\u3002<\/p>\n
\u5728\u722c\u53d6\u8c46\u74e3Top250\u65f6\u9700\u8981\u6ce8\u610f\u54ea\u4e9b\u6cd5\u5f8b\u548c\u9053\u5fb7\u95ee\u9898\uff1f<\/strong>
\u5728\u8fdb\u884c\u722c\u866b\u65f6\uff0c\u9700\u8981\u5c0a\u91cd\u7f51\u7ad9\u7684robots.txt\u534f\u8bae\uff0c\u786e\u4fdd\u4e0d\u8fdd\u53cd\u7f51\u7ad9\u7684\u4f7f\u7528\u6761\u6b3e\u3002\u540c\u65f6\uff0c\u907f\u514d\u5bf9\u7f51\u7ad9\u9020\u6210\u8d1f\u62c5\uff0c\u4e0d\u8981\u9891\u7e41\u8bf7\u6c42\u540c\u4e00\u9875\u9762\u3002\u5982\u679c\u9700\u8981\u5927\u89c4\u6a21\u6570\u636e\uff0c\u8003\u8651\u4f7f\u7528\u8c46\u74e3\u7684API\uff08\u5982\u679c\u6709\u63d0\u4f9b\uff09\u6216\u8005\u83b7\u53d6\u6570\u636e\u8bb8\u53ef\u3002<\/p>\n
\u5982\u4f55\u5904\u7406\u8c46\u74e3Top250\u9875\u9762\u4e2d\u7684\u52a8\u6001\u5185\u5bb9\uff1f<\/strong>
\u8c46\u74e3Top250\u9875\u9762\u90e8\u5206\u5185\u5bb9\u53ef\u80fd\u901a\u8fc7JavaScript\u52a8\u6001\u52a0\u8f7d\uff0c\u8fd9\u610f\u5473\u7740\u76f4\u63a5\u8bf7\u6c42HTML\u53ef\u80fd\u65e0\u6cd5\u83b7\u53d6\u6240\u6709\u6570\u636e\u3002\u53ef\u4ee5\u4f7f\u7528Selenium\u7b49\u5de5\u5177\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u6216\u901a\u8fc7\u5206\u6790\u7f51\u7edc\u8bf7\u6c42\u627e\u5230API\u63a5\u53e3\uff0c\u83b7\u53d6\u6240\u9700\u7684\u52a8\u6001\u6570\u636e\u3002<\/p>\n
\u5982\u679c\u722c\u53d6\u65f6\u9047\u5230\u53cd\u722c\u866b\u673a\u5236\uff0c\u5e94\u8be5\u5982\u4f55\u5e94\u5bf9\uff1f<\/strong>
\u9047\u5230\u53cd\u722c\u866b\u673a\u5236\u65f6\uff0c\u53ef\u4ee5\u5c1d\u8bd5\u8bbe\u7f6e\u8bf7\u6c42\u5934\u4f2a\u88c5\u6210\u771f\u5b9e\u7528\u6237\uff0c\u4f7f\u7528\u968f\u673a\u7684User-Agent\uff0c\u6216\u8005\u5f15\u5165\u4ee3\u7406IP\u8f6e\u6362\u673a\u5236\u3002\u540c\u65f6\uff0c\u63a7\u5236\u8bf7\u6c42\u9891\u7387\uff0c\u907f\u514d\u77ed\u65f6\u95f4\u5185\u53d1\u9001\u5927\u91cf\u8bf7\u6c42\uff0c\u4ee5\u51cf\u5c11\u88ab\u68c0\u6d4b\u7684\u98ce\u9669\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u4f7f\u7528Python\u722c\u53d6\u8c46\u74e3Top250\u7684\u65b9\u6cd5\u5305\u62ec\uff1a\u4f7f\u7528requests\u5e93\u8fdb\u884c\u7f51\u9875\u8bf7\u6c42\u3001\u4f7f\u7528BeautifulSo […]","protected":false},"author":3,"featured_media":1108539,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1108530"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1108530"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1108530\/revisions"}],"predecessor-version":[{"id":1108542,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1108530\/revisions\/1108542"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1108539"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1108530"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1108530"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1108530"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}