Python爬虫入门教程：蜂鸟网图片爬取

 1 from http_help import R  # 这个文件自己去上篇博客找，或者去github找
 2 import threading
 3 import time
 4 import json
 5 import re
 6 
 7 img_list = []
 8 imgs_lock = threading.Lock()  #图片操作锁
 9 
10 
11 # 生产者类
12 class Product(threading.Thread):
13 
14     def __init__(self):
15         threading.Thread.__init__(self)
16 
17         self.__headers = {"Referer":"http://image.fengniao.com/",
18                           "Host": "image.fengniao.com",
19                           "X-Requested-With":"XMLHttpRequest"
20                           }
21         #链接模板
22         self.__start = "http://image.fengniao.com/index.php?action=getList&class_id=192&sub_classid=0&page={}&not_in_id={}"
23         self.__res = R(headers=self.__headers)
24 
25 
26     def run(self):
27 
28         # 因为不知道循环次数，所有采用while循环
29         index = 2 #起始页码设置为1
30         not_in = "5352384,5352410"
31         while True:
32             url  = self.__start.format(index,not_in)
33             print("开始操作:{}".format(url))
34             index += 1
35 
36             content = self.__res.get_content(url,charset="gbk")
37 
38             if content is None:
39                 print("数据可能已经没有了====")
40                 continue
41 
42             time.sleep(3)  # 睡眠3秒
43             json_content = json.loads(content)
44 
45             if json_content["status"] == 1:
46                 for item in json_content["data"]:
47                     title = item["title"]
48                     child_url =  item["url"]   # 获取到链接之后
49 
50                     img_content = self.__res.get_content(child_url,charset="gbk")
51 
52                     pattern = re.compile(‘"pic_url_1920_b":"(.*?)"‘)
53                     imgs_json = pattern.findall(img_content)
54                     if len(imgs_json) > 0:
55 
56                         if imgs_lock.acquire():
57                             img_list.append({"title":title,"urls":imgs_json})   # 这个地方，我用的是字典+列表的方式，主要是想后面生成文件夹用，你可以进行改造
58                             imgs_lock.release()
59 
60 #小编整理一套Python资料和PDF，有需要Python学习资料可以加学习群：1004391443，反正闲着也是闲着呢，不如学点东西啦~~

# 消费者
class Consumer(threading.Thread):
    def __init__(self):
        threading.Thread.__init__(self)
        self.__res = R()

    def run(self):

        while True:
            if len(img_list) <= 0:
                continue  # 进入下一次循环

            if imgs_lock.acquire():

                data = img_list[0]
                del img_list[0]  # 删除第一项

                imgs_lock.release()

            urls =[url.replace("\\","") for url in data["urls"]]

            # 创建文件目录
            for item_url in urls:
               try:
                   file =  self.__res.get_file(item_url)
                   # 记得在项目根目录先把fengniaos文件夹创建完毕
                   with open("./fengniaos/{}".format(str(time.time())+".jpg"), "wb+") as f:
                       f.write(file)
               except Exception as e:
                   print(e)