寻医问药 爬虫

import requests
import re
import pandas as pd

def get_all_date_url():
    all_url=[]
    for i in range(61):
        url = ‘http://club.xywy.com/keshi/{}.html‘.format(str(i+1))
        res = requests.get(url)
        urls=re.findall(r"http://club.xywy.com/keshi/\d{4}-\d{2}-\d+/\d+\.html",res.text)
        all_url.extend(urls)
    return list(set(all_url))

def get_QA_url(url):
    all_QA_url=[]
    res = requests.get(url)
    res.encoding = ‘gb2312‘
    all_page = re.findall(r‘共 (\d+) 页‘,res.text)[0]
    for i in range(int(all_page)):
        url1 = ‘http://club.xywy.com/keshi/‘+ url.split(‘/‘)[-2] + ‘/‘ + str(i+1) +‘.html‘
        all_QA_url.append(url1)
    return list(set(all_QA_url))

def main():
    all_url_data = []
    for i in get_all_date_url():
        all_url_data.extend(get_QA_url(i))

    info_list = []
    for detail_url in all_url_data:
        final_dic_data = {}
        final_dic_data[‘url‘]=detail_url
        final_dic_data[‘患者标题‘]=xx
        final_dic_data[‘患者姓名‘]=xx
        final_dic_data[‘患者性别‘]=xx
        final_dic_data[‘提问日期‘]=xx
        final_dic_data[‘患者描述‘]=xx
        final_dic_data[‘医生姓名‘]=xx
        final_dic_data[‘医生职称‘]=xx
        final_dic_data[‘医生科室‘]=xx
        final_dic_data[‘问题分析‘]=xx
        final_dic_data[‘回答时间‘]=xx
        info_list.append(final_dic_data)

    df =pd.DataFrame(info_list)
    df.to_excel(‘xunyiwenyao.xlsx‘,index=False)

if __name__ == ‘__main__‘:
    mian()

原文地址：https://www.cnblogs.com/Erick-L/p/8311825.html