新浪爬虫

xinglang_pachong.py

@@ -0,0 +1,26 @@
+import requests
+import chardet
+from lxml import etree
+
+# 定义url
+url = 'https://sailboatdata.com/sailboat/'
+# 伪装浏览器 user——Agent为登陆地址，cookie为密钥
+headvalues = {
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36 Edg/111.0.1661.62',
+        'Cookie': '_ga=GA1.2.463000159.1680249637; _gid=GA1.2.206316371.1680249637; __qca=P0-2064736007-1680249637796; laravel_cookie_consent=1; XSRF-TOKEN=eyJpdiI6IkVSZk1kWlBBV2psRmp5bHRKQnFaRVE9PSIsInZhbHVlIjoiV0VwTWxOOWt0aVwvdGdFMk5sRWlqcHpzTk1ZWUNJVEtwMU1oSXAyMkFZVTB1MmVzQWhLRkpTb0piZUlmZkkwZEQiLCJtYWMiOiI4NTk1OTUwYmMxMWIyOWVkN2IwN2IxYWZiYzlhYmI5NGYyMTkwMmEwZTEyZmM3ZjY2OTEwYTg2YmJiOTg3ODAxIn0%3D; sailboatdatacom_session=eyJpdiI6Im95UXI2ZjJZOUYzMzNRWWMyTFcxMnc9PSIsInZhbHVlIjoiRjhrM3Q0TlZsMk1BNzQ0ZTdJUXlob3dOdG0rRndZbDFZZWZNSGFLeHJtXC83RHlDR2xSN1d6bVRTMmVxcjAwRGciLCJtYWMiOiI0NDA3YTQzMTcyYjE1YjBhODNlMDAyYmMyMjhjMDkzMDEyNDg5YzA0ZDk3OTY3NDgyMTg1MDI4ZDc2MzQxNjBiIn0%3D'
+}
+
+variety = 'J122'
+url = url + variety
+r = requests.get(url, headers=headvalues)
+print(r.text)
+
+# # 获取编码类型并修改
+# code_type = r.apparent_encoding
+# if code_type == 'GB2312':
+#     code_type = 'GBK'
+# html = etree.HTML(r.text)
+# # 主体
+# contents = html.xpath('//text()')
+# print(contents)
+