第一个爬虫

# This is a sample Python script.

# Press Shift+F10 to execute it or replace it with your code.
# Press Double Shift to search everywhere for classes, files, tool windows, actions, and settings.
import requests
import random
from bs4 import BeautifulSoup


# Press the green button in the gutter to run the script.
if __name__ == '__main__':
    headers = {
        "User-Agent": "Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.83 Safari/535.11"}

    r = requests.get('https://book.douban.com/subject/30218241/comments/', headers=headers)  # 不加头会检测到爬虫返回418
    print(r.status_code)

    soup = BeautifulSoup(r.text, "lxml")
    pattern = soup.find_all('span', 'short')  # 找到评论所在行(标签:span,属性内容:short)

    for item in pattern:
        print(item.string)