爬取【医疗问答】数据

最新推荐文章于 2024-07-03 20:47:12 发布

Robin C

最新推荐文章于 2024-07-03 20:47:12 发布

阅读量1.5k

点赞数 4

分类专栏：爬虫

本文链接：https://blog.csdn.net/qq_38423499/article/details/105013076

版权

爬虫专栏收录该内容

2 篇文章 0 订阅

订阅专栏

本文章以丁香医生为例
主要以科目分类来进行爬取，每个科目爬取的内容会存储到一个文本文档中，内容是问答式。

代码如下：

from bs4 import BeautifulSoup
import pandas as pd
import json
import requests
import time
import random
def get_static_url_content(url):
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36'}
    req = requests.get(url, headers=headers)
    print(req.status_code)
    content = req.text
    bsObj = BeautifulSoup(content, 'lxml')
    return bsObj

def start_cralwer(subject):
    url = 'https://ask.dxy.com/questions/%s/'%subject
    res = get_static_url_content(url)
    title = res.find('title').text
    print(title)
    bs = res.find_all('div', {'class': 'question-matching-questions-item'})
    with open('%s.txt'%subject, 'w', encoding='utf-8') as f:
        # first_page
        dialogue = {}
        for i in bs:
            question = i.find('div', {'class':'question-dialog dialog-of-patient'})
            answer = i.find('div', {'class':'question-dialog dialog-of-doctor'})
            f.write('patient:' + str(question.text)+'   doctor:' + str(answer.text) +'\n')
            # print('patient:', str(question.text), '   doctor:', str(answer.text))
        for i in range(2, 40):
            ask_url = 'https://ask.dxy.com/view/i/question/list/section?section_group_name=%s&page_index=%s'%(subject, str(i))  # url need a number
            time.sleep(random.randint(3, 10))
            res = get_static_url_content(ask_url)
            downloads_questions = res.find('body').text
            # print(downloads_questions)

            # print(json_str)
            try:
                json_str = json.loads(downloads_questions)
                items_list = json_str['data']['items']
                for item in items_list:
                    dialogs = item['dialogs']
                    # print(len(dialogs))
                    all_answer = []
                    questions = []
                    for j in dialogs:
                        # print(j)
                        if j['user_id'] == 0:
                            questions.extend([j['content']])
                        else:
                            answer = j['content']
                            all_answer.extend([answer])
                    dialogue[str(questions)] = all_answer
                for key, value in dialogue.items():
                    f.write('patient:' + str(key) + '   doctor:' + str(value) + '\n')
                    # print('patient:', str(key), '   doctor:', str(key))
            except:
                print('page:',i)
                print('page error:', ask_url)
    f.close()

if __name__ == '__main__':
    # subject
    # 'xiaohuaneike',
    subjects = [
               'huxineike',
               'erbiyanhoutoujing',
               'erke',
               'fengshimianyi',
               'neike',
               'xinxueguannei',
               'ganranchuanran',
               'putongwaike',
               'guke',
               'yanke',
               'neifenmi',
               'kouqiangke',
               'shenjingneike',
               'fuchanshengzhi',
               'xinxiongwaike',
               'gandanyiwaike',
               'naoliuke',
               'jiazhuangxianruxian',
               'miniaowaike',
               'xingbing',
               'jingshenxinli',
               'xueyeke',
               'shenzangnei',
               'shenjingwaike',
               'zhengxingmeirong',
               'tengtongmazui']
    # title
    for subject in subjects:
        start_cralwer(subject)
        print(subject, 'is done!')

可能因为【网速问题】报错！
自行调整！