源碼分享

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': ''
}
 
 
# 發(fā)送請求獲取json數(shù)據(jù)
def get_data(url):
        # 發(fā)送請求獲取json數(shù)據(jù)
        resp = requests.get(url=url, headers=headers)
        content = resp.content
        # 返回json數(shù)據(jù)
        return content
 
 
# 解析json數(shù)據(jù)
def parse_data(content):
        # 加載json數(shù)據(jù)
        data = json.loads(content)
        # 解析獲取回答數(shù)據(jù)
        answer_list = jsonpath.jsonpath(data, '$..data')
        # 解析獲取下一頁請求地址
        answer_next = jsonpath.jsonpath(data, '$..paging..next')[0]
        # 定義一個字典存放答主名稱和src列表
        answer_dict = {}
        # 遍歷獲取每個回答的內(nèi)容
        for answer in answer_list[0]:
                # 解析獲取答主名稱
                answer_name = jsonpath.jsonpath(answer, '$..author..name')[0]
                # 解析獲取回答內(nèi)容
                answer_content = str(jsonpath.jsonpath(answer, '$..target..content'))
                # 定義列表存放src路徑
                src_list = []
                # 遍歷獲取內(nèi)容中所有圖片
                while True:
                        # 圖片src起始位置
                        start_index = answer_content.find('data-actualsrc=\"') + 16
                        # 圖片src結(jié)束位置
                        end_index = answer_content.find('?source=1940ef5c')
                        # 如果能查到結(jié)束位置標記則獲取src路徑避免返回值為-1時的無效查找
                        if end_index != -1:
                                # 真實圖片src路徑
                                src = answer_content[start_index:end_index]
                                # 如果src在列表中不存在且不包含_r則添加到列表中
                                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)
                                # 更新截取后的內(nèi)容
                                answer_content = answer_content[end_index + 17:-1]
                        # 如果查不到src結(jié)束索引則跳出循環(huán)
                        else:
                                break
                answer_dict[answer_name] = src_list
        # 將存放src的列表和下一頁api返回
        return answer_dict, answer_next
 
 
def download_img(answer_dict, save_path):
        # 遍歷字典獲取名稱\src列表
        for name, src_list in answer_dict.items():
                # 遍歷src列表獲取src
                for src in src_list:
                        # 發(fā)送請求獲取圖片
                        img_resp = requests.get(src, headers=headers)
                        # 設(shè)置保存路徑
                        path = save_path + f'{name}'
                        # 判斷路徑是否存在,不存在就創(chuàng)建
                        if not os.path.exists(path):
                                os.makedirs(path)
                        # 保存圖片
                        with open(f'{path}/{int(time.time())}.jpg', 'wb') as img_f:
                                img_f.write(img_resp.content)
 
 
if __name__ == '__main__':
        # 設(shè)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('請輸入要保存的路徑,以/結(jié)尾:')
        if save_path[-1] != '/':
                save_path = input('沒有以/結(jié)尾,請重新輸入保存路徑:')
        while True:
                try:
                        # 調(diào)用方法獲取數(shù)據(jù)
                        content = get_data(url=url)
                except Exception:
                        break
                # 調(diào)用方法解析圖片地址
                answer_dict, url = parse_data(content=content)
                # 調(diào)用方法下載圖片
                download_img(answer_dict, save_path)

實現(xiàn)一個知乎下的簡單爬行圖，雖然簡單，但基本涵蓋了所有爬蟲的基礎(chǔ)知識，小白可以學(xué)習(xí)，畢竟簡單爬圖還是沒有問題的。

相關(guān)圖片爬取文章：

免費創(chuàng)意音樂設(shè)計QQ資料背景圖PSD源碼

3年前

01.6W+624