Python爬虫（六）

源码：

import requests
import re
from my_mysql import MysqlConnect


# 获取问答信息
def get_contents(page,headers):
    url = 'https://www.zhihu.com/api/v4/members/chen-lu-ya-26/answers?include=data%5B*%5D.is_normal%2Cadmin_closed_comment%2Creward_info%2Cis_collapsed%2Cannotation_action%2Cannotation_detail%2Ccollapse_reason%2Ccollapsed_by%2Csuggest_edit%2Ccomment_count%2Ccan_comment%2Ccontent%2Cvoteup_count%2Creshipment_settings%2Ccomment_permission%2Cmark_infos%2Ccreated_time%2Cupdated_time%2Creview_info%2Cquestion%2Cexcerpt%2Crelationship.is_authorized%2Cvoting%2Cis_author%2Cis_thanked%2Cis_nothelp%3Bdata%5B*%5D.author.badge%5B%3F(type%3Dbest_answerer)%5D.topics&offset={}&limit=20&sort_by=created'.format(page)
    req = requests.get(url,headers=headers)
    html_json_dict = req.json()
    # print(html_json_dict)
    data_list = html_json_dict['data']
    contents = []
    for item in data_list:
        question = item['question']['title']
        excerpt = item['excerpt']
        if '<' in excerpt:
            pat = r'(.*?)<.*>(.*)'
            res = re.search(pat, excerpt)
            front = res.group(1)
            back = res.group(2)
            pat = r'<.*?>(.*?)<.*?>'
            res = re.findall(pat, excerpt)
            middle = ' '.join(res)
            excerpt = front + middle + back
        contents.append((question,excerpt))
    return contents

if __name__ == '__main__':
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
    }
    mc = MysqlConnect('127.0.0.1','root','123456','homework')
    for page in range(0,20*8,20):
        contents = get_contents(page, headers)
        # print(contents)
        for content in contents:
            sql = 'insert into zhihu values(null,%s,%s)'
            mc.exec_data(sql,content)
            print(content)