简单爬取知乎网的问答

                                         简单爬取知乎网的问答模块

    利用requests以及pyquery,以及存储基础技术爬取知乎的问答模块。

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/70.0.3538.67 Safari/537.36",
}
html = requests.get(url, headers=headers).text
doc = pq(html)
# print(doc("html"))
items = doc(".explore-tab .feed-item").items()
for item in items:
    question = item.find("h2").text()
    author = item.find("author-link-line").text()
    answer = pq(item.find(".content").html()).text()
#     print(question)
    file = open("explore.txt","a",encoding="utf-8")
    file.write("\n".join([question,author,answer]))
    file.write("\n" + "=" * 80 + "\n")
    file.close()

猜你喜欢

转载自blog.csdn.net/u014297588/article/details/85137447