增加医学辞典构建

src/zhiwang_dict.py

@@ -0,0 +1,59 @@
+import json
+import re
+import requests
+from bs4 import BeautifulSoup
+
+
+def zhiwang(id):
+    """
+    基于词语知网数据查询
+    :param id: 页面id
+    :return: 查询返回json包
+    """
+    headers = {
+        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
+        "Accept-Encoding": "gzip, deflate", "Accept-Language": "zh-CN,zh;q=0.9",
+        "Cache-Control": "max-age=0",
+        "Connection": "keep-alive", "Host": "wiki.cnki.com.cn",
+        "Upgrade-Insecure-Requests": "1",
+        "Cookie": "UM_distinctid=173c16e519d73a-058630ec26edf5-3323765-144000-173c16e519e6d0; SID_wiki=018060; CNZZDATA3412177=cnzz_eid%3D2011079095-1596676096-null%26ntime%3D1597380140",
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36"}
+    url = "http://wiki.cnki.com.cn/HotWord/"+str(id)+".htm"
+    response = requests.get(url, headers=headers)
+    soup = BeautifulSoup(response.text, 'html.parser')
+    content = {}
+    for element in soup.find_all(class_='explain'):
+        for element_one in element.find_all('p'):
+            content['概述'] = re.sub(('[\n \r \t  ：\xa0\u3000]'), '', element_one.get_text())
+    list_content = []
+    list_content_key = ['相似词', '相关词']
+    for element in soup.find_all(class_='sidepan2'):
+        for element_one in element.find_all(class_='thesis'):
+            word_value = []
+            for element_three in element_one.find_all("ul"):
+                for element_four in element_three.find_all('li'):
+                    for element_five in element_four.find_all('a'):
+                        word_value.append(element_five['title'])
+            list_content.append(word_value)
+    dict_content_list = dict(zip(list_content_key, list_content))
+    content.update(dict_content_list)
+    qikan_list = []
+    words = []
+    for element in soup.find_all(class_='essay_list'):
+        for element_one in element.find_all('dl'):
+            for element_two in element_one.find_all('dt'):
+                for element_three in element_two.find_all('strong'):
+                    for element_four in element_three.find_all('a'):
+                        qikan_list.append('http:' + element_four['href'])
+            temp_word = []
+            for element_five in element_one.find_all(class_='infor'):
+                for element_six in element_five.find_all('a'):
+                    temp_word.append(element_six.get_text())
+            words.append(temp_word)
+    content['期刊url'] = qikan_list
+    content['期刊word'] = words
+    return content
+
+
+if __name__ == '__main__':
+    print(json.dumps(zhiwang('3718950'), ensure_ascii=False, indent=2))