爬虫学习-第十二篇

"""
Version: 0.1
Author: freshbin
Date: 2019年8月28日
"""

print("=================================txt文本存储 start================================================")

import requests
from pyquery import PyQuery as pq

url = 'https://www.zhihu.com/explore'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36'
}
html = requests.get(url, headers=headers).text
print(html)
doc = pq(html)
items = doc('.ExploreCollectionCard-contentList').items()

print(items)
for item in items:
    question = item.find('.ExploreCollectionCard-contentTitle').text()
    answer = pq(item.find('.ExploreCollectionCard-contentExcerpt').html()).text()
    file = open('explore.txt', 'a', encoding='utf-8')
    file.write('\n'.join([question, answer]))
    file.write('\n' + '=' * 50 + '\n')
    file.close()
print("=================================txt文本存储 end================================================")