利用python實現查看溧陽的攝影圈

http://www.jsly001.com/thread-htm-fid-45-page-{頁碼}.html

import random
import threading
import logging
from bs4 import BeautifulSoup
import requests
import lxml
logging.basicConfig(level=logging.NOTSET) # 設置日志輸出級別
# 聲明一個 LiYang 類，其繼承自 threading.Thread
class LiYangThread(threading.Thread):
    def __init__(self):
        threading.Thread.__init__(self) # 實例化多線程對象
        self._headers = self._get_headers() # 隨機獲取 ua
        self._timeout = 5 # 設置超時時間

    # 每個線程都去獲取全局資源
    def run(self):
        # while True: # 此處為多線程開啟位置
        try:
            res = requests.get(url="http://www.jsly001.com/thread-htm-fid-45-page-1.html", headers=self._headers,
                               timeout=self._timeout) # 測試獲取第一頁數據
        except Exception as e:
            logging.error(e)
        if res is not None:
            html_text = res.text
            self._format_html(html_text) # 調用html解析函數

    def _format_html(self, html):
        # 使用 lxml 進行解析
        soup = BeautifulSoup(html, 'lxml')

        # 獲取板塊主題分割區域，主要為防止獲取置頂的主題
        part_tr = soup.find(attrs={'class': 'bbs_tr4'})

        if part_tr is not None:
            items = part_tr.find_all_next(attrs={"name": "readlink"}) # 獲取詳情頁地址
        else:
            items = soup.find_all(attrs={"name": "readlink"})
        # 解析出標題與數據
        data = [(item.text, f'http://www.jsly001.com/{item["href"]}') for item in items]
        # 進入標題內頁
        for name, url in data:
            self._get_imgs(name, url)

    def _get_imgs(self, name, url):
        """解析圖片地址"""
        try:
            res = requests.get(url=url, headers=self._headers, timeout=self._timeout)
        except Exception as e:
            logging.error(e)
		# 圖片提取邏輯
        if res is not None:
            soup = BeautifulSoup(res.text, 'lxml')
            origin_div1 = soup.find(attrs={'class': 'tpc_content'})
            origin_div2 = soup.find(attrs={'class': 'imgList'})
            content = origin_div2 if origin_div2 else origin_div1

            if content is not None:
                imgs = content.find_all('img')

                # print([img.get("src") for img in imgs])
                self._save_img(name, imgs) # 保存圖片
    def _save_img(self, name, imgs):
        """保存圖片"""
        for img in imgs:
            url = img.get("src")
            if url.find('http') < 0:
                continue
            # 尋找父標簽中的 id 屬性
            id_ = img.find_parent('span').get("id")

            try:
                res = requests.get(url=url, headers=self._headers, timeout=self._timeout)
            except Exception as e:
                logging.error(e)

            if res is not None:
                name = name.replace("/", "_")
                with open(f'./imgs/{name}_{id_}.jpg', "wb+") as f: # 註意在 python 運行時目錄提前創建 imgs 文件夾
                    f.write(res.content)
    def _get_headers(self):
        uas = [
            "Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)",
        ]
        ua = random.choice(uas)
        headers = {
            "user-agent": ua
        }
        return headers
if __name__ == '__main__':
    my_thread = LiYangThread()
    my_thread.run()

# 尋找父標簽中的 id 屬性
id_ = img.find_parent('span').get("id")