更新了爬虫第1天代码

452b6f14 · 骆昊的技术专栏 · 402e0564 · 452b6f14 · 452b6f14 · 452b6f14
隐藏空白更改
内联并排

Showing with 137 addition and 0 deletion

Day66-75/code/example01.py Day66-75/code/example01.py +60 -0

Day66-75/code/example02.py Day66-75/code/example02.py +50 -0

Day66-75/code/example03.py Day66-75/code/example03.py +27 -0

未找到文件。
--- a/Day66-75/code/example01.py
+++ b/Day66-75/code/example01.py
+from urllib.error import URLError
+from urllib.request import urlopen
+
+import re
+import pymysql
+
+
+def get_page_code(start_url, *, retry_times=3, charsets=('utf-8', )):
+    try:
+        for charset in charsets:
+            try:
+                html = urlopen(start_url).read().decode(charset)
+                break
+            except UnicodeDecodeError:
+                html = None
+    except URLError as ex:
+        print('Error:', ex)
+        return get_page_code(start_url, retry_times=retry_times - 1, charsets=charsets) if \
+            retry_times > 0 else None
+    return html
+
+
+def main():
+    url_list = ['http://sports.sohu.com/nba_a.shtml']
+    visited_list = set({})
+    while len(url_list) > 0:
+        current_url = url_list.pop(0)
+        visited_list.add(current_url)
+        print(current_url)
+        html = get_page_code(current_url, charsets=('utf-8', 'gbk', 'gb2312'))
+        if html:
+            link_regex = re.compile(r'<a[^>]+href=["\'](.*?)["\']', re.IGNORECASE)
+            link_list = re.findall(link_regex, html)
+            url_list += link_list
+            conn = pymysql.connect(host='localhost', port=3306,
+                                   db='crawler', user='root',
+                                   passwd='123456', charset='utf8')
+            try:
+                for link in link_list:
+                    if link not in visited_list:
+                        visited_list.add(link)
+                        print(link)
+                        html = get_page_code(link, charsets=('utf-8', 'gbk', 'gb2312'))
+                        if html:
+                            title_regex = re.compile(r'<h1>(.*)<span', re.IGNORECASE)
+                            match_list = title_regex.findall(html)
+                            if len(match_list) > 0:
+                                title = match_list[0]
+                                with conn.cursor() as cursor:
+                                    cursor.execute('insert into tb_result (rtitle, rurl) values (%s, %s)',
+                                               (title, link))
+                                conn.commit()
+            finally:
+                conn.close()
+    print('执行完成!')
+
+
+if __name__ == '__main__':
+    main()
+
--- a/Day66-75/code/example02.py
+++ b/Day66-75/code/example02.py
+from bs4 import BeautifulSoup
+
+import re
+
+
+def main():
+    html = """
+    <!DOCTYPE html>
+    <html lang="en">
+    <head>
+        <meta charset="UTF-8">
+        <title>首页</title>
+    </head>
+    <body>
+        <h1>Hello, world!</h1>
+        <p>Good!!!</p>
+        <hr>
+        <div>
+            <h2>这是一个例子程序</h2>
+            <p>静夜思</p>
+            <p class="foo">床前明月光</p>
+            <p id="bar">疑似地上霜</p>
+            <p class="foo">举头望明月</p>
+            <div><a href="http://www.baidu.com"><p>低头思故乡</p></a></div>
+        </div>
+        <a class="foo" href="http://www.qq.com">腾讯网</a>
+        <img src="./img/pretty-girl.png" alt="美女">
+        <img src="./img/hellokitty.png" alt="凯蒂猫">
+        <img src="./static/img/pretty-girl.png" alt="美女">
+        <goup>Hello, Goup!</goup>
+    </body>
+    </html>
+    """
+    # resp = requests.get('http://sports.sohu.com/nba_a.shtml')
+    # html = resp.content.decode('gbk')
+    soup = BeautifulSoup(html, 'lxml')
+    print(soup.title)
+    # JavaScript: document.body.h1
+    # JavaScript: document.forms[0]
+    print(soup.body.h1)
+    print(soup.find_all(re.compile(r'p$')))
+    print(soup.find_all('img', {'src': re.compile(r'\./img/\w+.png')}))
+    print(soup.find_all(lambda x: len(x.attrs) == 2))
+    print(soup.find_all('p', {'class': 'foo'}))
+    for elem in soup.select('a[href]'):
+        print(elem.attrs['href'])
+
+
+if __name__ == '__main__':
+    main()
--- a/Day66-75/code/example03.py
+++ b/Day66-75/code/example03.py
+from bs4 import BeautifulSoup
+
+import requests
+
+import re
+
+
+def main():
+    # 通过requests第三方库的get方法获取页面
+    resp = requests.get('http://sports.sohu.com/nba_a.shtml')
+    # 对响应的字节串(bytes)进行解码操作(搜狐的部分页面使用了GBK编码)
+    html = resp.content.decode('gbk')
+    # 创建BeautifulSoup对象来解析页面(相当于JavaScript的DOM)
+    bs = BeautifulSoup(html, 'lxml')
+    # 通过CSS选择器语法查找元素并通过循环进行处理
+    # for elem in bs.find_all(lambda x: 'test' in x.attrs):
+    for elem in bs.select('a[test]'):
+        # 通过attrs属性(字典)获取元素的属性值
+        link_url = elem.attrs['href']
+        resp = requests.get(link_url)
+        bs_sub = BeautifulSoup(resp.text, 'lxml')
+        # 使用正则表达式对获取的数据做进一步的处理
+        print(re.sub(r'[\r\n]', '', bs_sub.find('h1').text))
+
+
+if __name__ == '__main__':
+    main()