欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页  >  IT编程

python3爬虫-使用requests爬取起点小说

程序员文章站 2022-04-28 15:17:30
import requests from lxml import etree from urllib import parse import os, time def get_page_html(url): '''向url发送请求''' resoponse = session.get(url, he... ......
import requests
from lxml import etree
from urllib import parse
import os, time


def get_page_html(url):
    '''向url发送请求'''
    resoponse = session.get(url, headers=headers, timeout=timeout)
    try:
        if resoponse.status_code == 200:
            return resoponse
    except exception:
        return none


def get_next_url(resoponse):
    '''获取下一页的url链接'''
    if resoponse:
        try:
            selector = etree.html(resoponse.text)
            url = selector.xpath("//a[@id='j_chapternext']/@href")[0]
            next_url = parse.urljoin(resoponse.url, url)
            return next_url
        except indexerror:
            return none


def xs_content(resoponse):
    '''获取小说的章节名,内容'''
    if resoponse:
        selector = etree.html(resoponse.text)
        title = selector.xpath("//h3[@class='j_chaptername']/text()")[0]
        content_xpath = selector.xpath(
            "//div[contains(@class,'read-content') and contains(@class,'j_readcontent')]//p/text()")
        return title, content_xpath


def write_to_txt(info_tuple: tuple):
    if not info_tuple: return
    path = os.path.join(base_path, info_tuple[0])
    if not os.path.exists(path):
        with open(path + ".txt", "wt", encoding="utf-8") as f:
            for line in info_tuple[1]:
                f.write(line + "\n")
            f.flush()


def run(url):
    '''启动'''
    html = get_page_html(url)
    next_url = get_next_url(html)
    info_tupe = xs_content(html)
    if next_url and info_tupe:
        print("正在写入")
        write_to_txt(info_tupe)
        time.sleep(sleep_time)  # 延迟发送请求的时间,减少对服务器的压力。
        print("正在爬取%s" % info_tupe[0])
        print("正在爬取%s" % next_url)
        run(next_url)


if __name__ == '__main__':
    session = requests.session()
    sleep_time = 5
    timeout = 5
    base_path = r"d:\图片\lszj"  # 存放文件的目录
    url = "https://read.qidian.com/chapter/8iw8dkb_ztxrzk4x-cujuw2/fwjwroiobhn4p8iew--ppw2"  # 这是斗破苍穹第一章的url    需要爬取的小说的第一章的链接(url)
    headers = {
        "referer": "read.qidian.com",
        "user-agent": "mozilla/5.0 (windows nt 10.0; wow64) applewebkit/537.36 (khtml, like gecko) chrome/72.0.3626.121 safari/537.36"
    }
    print('开始运行爬虫')
    run(url)