爬取知乎问题下的各种图片

源码分享

import json
import os.path
import time
 
import jsonpath
import requests
 
headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.5060.114 Safari/537.36',
        'referer': 'https://www.zhihu.com/question/26297181',
        'cookie': ''
}
 
 
# 发送请求获取json数据
def get_data(url):
        # 发送请求获取json数据
        resp = requests.get(url=url, headers=headers)
        content = resp.content
        # 返回json数据
        return content
 
 
# 解析json数据
def parse_data(content):
        # 加载json数据
        data = json.loads(content)
        # 解析获取回答数据
        answer_list = jsonpath.jsonpath(data, '$..data')
        # 解析获取下一页请求地址
        answer_next = jsonpath.jsonpath(data, '$..paging..next')[0]
        # 定义一个字典存放答主名称和src列表
        answer_dict = {}
        # 遍历获取每个回答的内容
        for answer in answer_list[0]:
                # 解析获取答主名称
                answer_name = jsonpath.jsonpath(answer, '$..author..name')[0]
                # 解析获取回答内容
                answer_content = str(jsonpath.jsonpath(answer, '$..target..content'))
                # 定义列表存放src路径
                src_list = []
                # 遍历获取内容中所有图片
                while True:
                        # 图片src起始位置
                        start_index = answer_content.find('data-actualsrc=\"') + 16
                        # 图片src结束位置
                        end_index = answer_content.find('?source=1940ef5c')
                        # 如果能查到结束位置标记则获取src路径避免返回值为-1时的无效查找
                        if end_index != -1:
                                # 真实图片src路径
                                src = answer_content[start_index:end_index]
                                # 如果src在列表中不存在且不包含_r则添加到列表中
                                if src not in src_list and '_r' not in src and len(src) < 100 and len(src) != 0:
                                        src = src.replace('_720w', '')
                                        src_list.append(src)
                                # 更新截取后的内容
                                answer_content = answer_content[end_index + 17:-1]
                        # 如果查不到src结束索引则跳出循环
                        else:
                                break
                answer_dict[answer_name] = src_list
        # 将存放src的列表和下一页api返回
        return answer_dict, answer_next
 
 
def download_img(answer_dict, save_path):
        # 遍历字典获取名称\src列表
        for name, src_list in answer_dict.items():
                # 遍历src列表获取src
                for src in src_list:
                        # 发送请求获取图片
                        img_resp = requests.get(src, headers=headers)
                        # 设置保存路径
                        path = save_path + f'{name}'
                        # 判断路径是否存在,不存在就创建
                        if not os.path.exists(path):
                                os.makedirs(path)
                        # 保存图片
                        with open(f'{path}/{int(time.time())}.jpg', 'wb') as img_f:
                                img_f.write(img_resp.content)
 
 
if __name__ == '__main__':
        # 设置起始api
        url = 'https://www.zhihu.com/api/v4/questions/26297181/feeds?cursor=e9d89ca6466891518544484e84026815&include=data%5B%2A%5D.is_normal%2Cadmin_closed_comment%2Creward_info%2Cis_collapsed%2Cannotation_action%2Cannotation_detail%2Ccollapse_reason%2Cis_sticky%2Ccollapsed_by%2Csuggest_edit%2Ccomment_count%2Ccan_comment%2Ccontent%2Ceditable_content%2Cattachment%2Cvoteup_count%2Creshipment_settings%2Ccomment_permission%2Ccreated_time%2Cupdated_time%2Creview_info%2Crelevant_info%2Cquestion%2Cexcerpt%2Cis_labeled%2Cpaid_info%2Cpaid_info_content%2Creaction_instruction%2Crelationship.is_authorized%2Cis_author%2Cvoting%2Cis_thanked%2Cis_nothelp%2Cis_recognized%3Bdata%5B%2A%5D.mark_infos%5B%2A%5D.url%3Bdata%5B%2A%5D.author.follower_count%2Cvip_info%2Cbadge%5B%2A%5D.topics%3Bdata%5B%2A%5D.settings.table_of_content.enabled&limit=5&offset=0&order=default&platform=desktop&session_id=1657444499711409954'
        save_path = input('请输入要保存的路径,以/结尾:')
        if save_path[-1] != '/':
                save_path = input('没有以/结尾,请重新输入保存路径:')
        while True:
                try:
                        # 调用方法获取数据
                        content = get_data(url=url)
                except Exception:
                        break
                # 调用方法解析图片地址
                answer_dict, url = parse_data(content=content)
                # 调用方法下载图片
                download_img(answer_dict, save_path)

实现一个知乎下的简单爬行图，虽然简单，但基本涵盖了所有爬虫的基础知识，小白可以学习，毕竟简单爬图还是没有问题的。