Python3：小爬虫成长记（三）---爬取数据并写入到文件

#!/usr/bin/env python
# -*- coding=utf-8 -*-
# coding: utf-8

from pyquery import PyQuery
import requests, json, csv
import urllib3  # 为了忽略InsecureRequestWarning

urllib3.disable_warnings()
url = 'https://www.zhihu.com/explore'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 '
                  '(KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.4098.3 '
                  'Safari/537.36'
}
html = requests.get(url, headers=headers, verify=False).text
doc = PyQuery(html)
items = doc('.explore-feed').items()  # 返回generator object PyQuery.items


def wr_txt(data_txt):
    with open('explore.txt', 'a', encoding='utf-8') as fp:
        fp.write('\n'.join(data_txt))


def wr_json(data_json):
    with open('explore.json', 'a', encoding='utf-8') as fp:
        json.dump(obj=data_json, fp=fp)


def wr_csv(data_csv):
    with open('explore.csv', 'a', encoding='utf-8') as fp:
        writer = csv.writer(fp)
        writer.writerow(data_csv)


for item in items:
    question = item.find('h2').text()
    author = item.find('.author-link').text()
    answer = PyQuery(item.find('.content').html()).text()
    data = [question, author, answer]
    # 写入到TXT文件
    wr_txt(data_txt=data)
    # 写入到JSON文件
    wr_json(data_json=data)
    # 写入到csv文件
    wr_csv(data_csv=data)