今天用requests写了一个简书点赞的小爬虫来玩玩。没有使用多线程，进程等，就是单纯的requests.

"""
----------
version=1.0
------------
"""

import requests
from lxml import etree
from time import time


headers = {
  # 用自己的账号的header  
}


def fetch_url(url, page):
    data = {'page': page}
    r = requests.post(url, headers=headers, data=data)
    return r.content


# 解析出来的文章url,加入到队列中
def parse(url, pages):
    article_urllist = []
    article_xpath = "//li/div[@class='content']/a[@class='title']"
    for page_number in range(1, pages + 1):
        try:
            page = fetch_url(url, page_number)
            html = etree.HTML(page)
            article_list = html.xpath(article_xpath)
            for article in article_list:
                article_urllist.append(f"https://www.jianshu.com{article.get('href')}")
        except:
            print('失败')
    return article_urllist


# 请求网站，点赞
def dianzan(article_url):
    try:
        a = requests.get(article_url, headers=headers)
    except:
        print('请求文章页面失败')
    html = etree.HTML(a.content)
    dianzan_path = "//meta[@property='al:android:url']"
    url_part = html.xpath(dianzan_path)[0].get('content')
    # https://www.jianshu.com/notes/38734391/like
    url = f'https://www.jianshu.com{url_part[9:]}/like'
    # 点赞
    try:
        requests.post(url, headers=headers)
    except:
        print('点赞失败')


def run(url, page):
    n = 0
    article_list = parse(url, page)
    for article_url in article_list:
        dianzan(article_url)
        n = n + 1
    print(f'点赞文章数量{n}')


if __name__ == '__main__':
    url = 'https://www.jianshu.com/trending_notes'
    pages = 1
    start = time()
    run(url, pages)
    end = time()
    print(f'{end - start}')

image.png

速度好慢，哈哈哈哈。