爬虫集合

爬虫集合/README.MD

@@ -0,0 +1,2 @@
+# 代码详细说明请看文章
+

爬虫集合/meizitu.py

@@ -0,0 +1,77 @@
+import requests
+import os
+import time
+import threading
+from bs4 import BeautifulSoup
+
+
+def download_page(url):
+    '''
+    用于下载页面
+    '''
+    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:61.0) Gecko/20100101 Firefox/61.0"}
+    r = requests.get(url, headers=headers)
+    r.encoding = 'gb2312'
+    return r.text
+
+
+def get_pic_list(html):
+    '''
+    获取每个页面的套图列表,之后循环调用get_pic函数获取图片
+    '''
+    soup = BeautifulSoup(html, 'html.parser')
+    pic_list = soup.find_all('li', class_='wp-item')
+    for i in pic_list:
+        a_tag = i.find('h3', class_='tit').find('a')
+        link = a_tag.get('href')
+        text = a_tag.get_text()
+        get_pic(link, text)
+
+
+def get_pic(link, text):
+    '''
+    获取当前页面的图片,并保存
+    '''
+    html = download_page(link)  # 下载界面
+    soup = BeautifulSoup(html, 'html.parser')
+    pic_list = soup.find('div', id="picture").find_all('img')  # 找到界面所有图片
+    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:61.0) Gecko/20100101 Firefox/61.0"}
+    create_dir('pic/{}'.format(text))
+    for i in pic_list:
+        pic_link = i.get('src')  # 拿到图片的具体 url
+        r = requests.get(pic_link, headers=headers)  # 下载图片，之后保存到文件
+        with open('pic/{}/{}'.format(text, link.split('/')[-1]), 'wb') as f:
+            f.write(r.content)
+            time.sleep(1)   # 休息一下，不要给网站太大压力，避免被封
+
+
+def create_dir(name):
+    if not os.path.exists(name):
+        os.makedirs(name)
+
+
+def execute(url):
+    page_html = download_page(url)
+    get_pic_list(page_html)
+
+
+def main():
+    create_dir('pic')
+    queue = [i for i in range(1, 72)]   # 构造 url 链接 页码。
+    threads = []
+    while len(queue) > 0:
+        for thread in threads:
+            if not thread.is_alive():
+                threads.remove(thread)
+        while len(threads) < 5 and len(queue) > 0:   # 最大线程数设置为 5
+            cur_page = queue.pop(0)
+            url = 'http://meizitu.com/a/more_{}.html'.format(cur_page)
+            thread = threading.Thread(target=execute, args=(url,))
+            thread.setDaemon(True)
+            thread.start()
+            print('{}正在下载{}页'.format(threading.current_thread().name, cur_page))
+            threads.append(thread)
+
+
+if __name__ == '__main__':
+    main()

爬虫集合/qiubai_crawer.py

@@ -0,0 +1,54 @@
+import requests
+from bs4 import BeautifulSoup
+
+
+def download_page(url):
+    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:61.0) Gecko/20100101 Firefox/61.0"}
+    r = requests.get(url, headers=headers)
+    return r.text
+
+
+def get_content(html, page):
+    output = """第{}页 作者：{} 性别：{} 年龄：{} 点赞：{} 评论：{}\n{}\n------------\n"""
+    soup = BeautifulSoup(html, 'html.parser')
+    con = soup.find(id='content-left')
+    con_list = con.find_all('div', class_="article")
+    for i in con_list:
+        author = i.find('h2').string  # 获取作者名字
+        content = i.find('div', class_='content').find('span').get_text()  # 获取内容
+        stats = i.find('div', class_='stats')
+        vote = stats.find('span', class_='stats-vote').find('i', class_='number').string
+        comment = stats.find('span', class_='stats-comments').find('i', class_='number').string
+        author_info = i.find('div', class_='articleGender')  # 获取作者 年龄，性别
+        if author_info is not None:  # 非匿名用户
+            class_list = author_info['class']
+            if "womenIcon" in class_list:
+                gender = '女'
+            elif "manIcon" in class_list:
+                gender = '男'
+            else:
+                gender = ''
+            age = author_info.string   # 获取年龄
+        else:  # 匿名用户
+            gender = ''
+            age = ''
+
+        save_txt(output.format(page, author, gender, age, vote, comment, content))
+
+
+def save_txt(*args):
+    for i in args:
+        with open('qiubai.txt', 'a', encoding='utf-8') as f:
+            f.write(i)
+
+
+def main():
+    # 我们点击下面链接，在页面下方可以看到共有13页，可以构造如下 url，
+    # 当然我们最好是用 Beautiful Soup找到页面底部有多少页。
+    for i in range(1, 14):
+        url = 'https://qiushibaike.com/text/page/{}'.format(i)
+        html = download_page(url)
+        get_content(html, i)
+
+if __name__ == '__main__':
+    main()