[ Python ] 爬虫类库学习之 requests，爬取豆瓣喜剧电影排行榜

requests

文档：http://cn.python-requests.org/zh_CN/latest/

安装：pip --timeout=100 install requests

[ python ] pip 配置国内镜像源（亲测有效）

---

百度搜索

• 一个简单地小例子
• 基于requests模块的get请求
• 爬取百度搜索首页

import requests

if __name__ == "__main__":
    url = "https://www.baidu.com"
    response = requests.get(url)
    response.encoding = 'utf-8'
    print("状态码：" + str(response.status_code))

    page_text = response.text
    print("页面内容：" + page_text)
    with open('./baidu.html', 'w', encoding='utf-8') as fp:
        fp.write(page_text)

    print('爬取数据结束！')

搜狗搜索

• 基于requests模块的get请求
• 爬取搜狗指定词条对应的搜索结果页面

import requests

if __name__ == '__main__':
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'
    }
    url = 'https://www.sogou.com/web'
    kw = input('输入查询关键字：')
    param = {
        'query': kw
    }
    response = requests.get(url, param, headers=headers)

    page_text = response.text
    fileName = kw + '.html'
    with open(fileName, 'w', encoding='utf-8') as fp:
        fp.write(page_text)

    print('数据爬取结束！')

百度翻译

• 基于requests模块的post请求
• 破解百度翻译

import requests
import json

if __name__ == '__main__':
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'
    }
    post_url = 'https://fanyi.baidu.com/sug'
    word = input('输入查询关键字：')
    data = {
        'kw': word
    }
    response = requests.post(post_url, data, headers=headers)
    dic_obj = response.json()
    print(dic_obj)
    fileName = word + '.json'
    fp = open(fileName, 'w', encoding='utf-8')
    json.dump(dic_obj, fp, ensure_ascii=False)
    print('数据爬取结束！')

豆瓣喜剧电影排行榜

• 基于requests模块ajax的get请求
• 爬取链接：https://movie.douban.com/
• 爬取豆瓣电影分类排行榜 - 喜剧片

import requests
import json

if __name__ == '__main__':
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'
    }
    param = {
        "type": "24",
        "interval_id": "100:90",
        "action": "",
        "start": "0",
        "limit": "20",
    }
    url = 'https://movie.douban.com/j/chart/top_list'
    response = requests.get(url, param, headers=headers)
    dic_obj = response.json()
    print(dic_obj)
    fileName = '豆瓣电影排行榜.json'
    fp = open(fileName, 'w', encoding='utf-8')
    json.dump(dic_obj, fp, ensure_ascii=False)
    print('数据爬取结束！')

企业信息爬取

• 爬取链接：http://125.35.6.84:81/xk/
• 爬取企业化妆品生产许可证信息

import requests
import json
if __name__ == '__main__':
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) '
                      'Chrome/78.0.3904.108 Safari/537.36 '
    }
    url = 'http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsList'
    # 企业 id 列表
    id_list = []
    detail_list = []
    
    # 获取前两页企业 id，30 条id
    for page in range(1, 3):
        page = str(page)
        param = {
            "on": "true",
            "page": page,
            "pageSize": "15",
            "productName": "",
            "conditionType": "1",
            "applyname": "",
            "applysn": "",
        }
        response = requests.post(url, param, headers=headers)
        json_ids = response.json()
        for dic in json_ids['list']:
            id_list.append(dic['ID'])

    post_url = 'http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsById'
    for id in id_list:
        data = {
            'id': id
        }
        res = requests.post(post_url, data, headers=headers)
        detail_json = res.json()
        detail_list.append(detail_json)

    fileName = '企业信息.json'
    fp = open(fileName, 'w', encoding='utf-8')
    json.dump(detail_list, fp, ensure_ascii=False)
    print('数据爬取结束！')

来源：爬虫开发入门丨老男孩IT教育

---