[Python知识库]python爬取豆瓣top250

直接上代码,爬虫这东西,话太多,审核过不了啊~

import requests
import re
import csv

for pages in range(0, 250, 25):
    douabntop50url = f'https://movie.douban.com/top250?start={pages}&filter='

    request_head = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
                      "Chrome/96.0.4664.93 Safari/537.36"
    }

    resp_source_code = requests.get(url=douabntop50url, headers=request_head)

    page_source_code = resp_source_code.text

    analysis = re.compile(r'<li>.*?<div class="item">.*?<span class="title">(?P<name>.*?)'
                          r'</span>.*?<div class="bd">.*?<br>(?P<year>.*?)&nbsp;.*?<div class="star">'
                          r'.*?<span class="rating_num" property="v:average">(?P<score>.*?)</span>'
                          r'.*?<span>(?P<evaluators_people>.*?)</span>', re.S)

    # '<br>'到年份有一大串空格,得用strip()清除,而其他标记,因为左右定位都是内容,所以没有空格
    # 另外csv文件的用gbk编码解,utf-8会乱码;

    match_result = analysis.finditer(page_source_code)

    top_250 = open("top_250.csv", "a")

    top_250csv = csv.writer(top_250)

    for i in match_result:
        # print(i.group("name").strip())

        # print(i.group("year").strip())

        # print(i.group("score").strip())

        # print(i.group("evaluators_people").strip())

        top = i.groupdict()

        top["year"] = top["year"].strip()
        top["year"] = top["year"] + "年"
        top["score"] = top["score"] + "分"
        top["name"] = "片名:" + top["name"]
        top_250csv.writerow(top.values())

    print(f"正在爬取排行耪{pages+1}-{pages+25}页")

top_250.close()

print(resp_source_code.apparent_encoding)

解释看我那个dytt文篇的那些,思路都差不多

结果:

?

后面还有好多好多~...