Python 爬虫，peca 网站作品信息采集爬虫源码

“我看见一个男人，前几年他无忧无虑，逍遥自在，现在他，一身酒味，两眼无光，满脸憔悴，我很想心疼他一下，于是我伸手摸了一下镜子”

一个比较简单的爬虫源码，爬取 peca 网站作品信息，包括图片及文字内容信息，几乎没有限制，适合新人学习练手使用，文末附上源码供参考学习。

这里简单分享一下批量下载图片的方式，使用了三种方式，前两种是多线程的方式，后面应用了队列的方式，最后是采用了线程池批量下载图片。

第一种，以图片数量来确定线程数批量下载图片！

import threading

def down_imgs(path,imgs):
    threadings = []
    for img in imgs:
        t = threading.Thread(target=get_img, args=(path,img))
        threadings.append(t)
        t.start()

    for x in threadings:
        x.join()

    print(f"恭喜，多线程下载图片完成!")

第二种，使用了队列控制，开启四个线程下载图片。

#使用了队列
import threading
from queue import Queue

def down_four_imgs(path,imgs):
    imgQ=Queue()
    for img in imgs:
        imgQ.put(img)
    while not imgQ.empty():
        threadings = []
        for i in range(5):
            imgurl=imgQ.get()
            t = threading.Thread(target=get_img, args=(path,imgurl))
            threadings.append(t)
            t.start()

        for x in threadings:
            x.join()

        print(f"恭喜，四线程下载图片完成!")

    print(f"恭喜，多线程下载图片完成!")

第三种，应用了线程池批量下载图片。

#线程池
def downs_imgs(path,imgs):
    datas=[]
    for img in imgs:
        data=path,img
        datas.append(data)

    try:
        # 开4个 worker，没有参数时默认是 cpu 的核心数
        pool = ThreadPool(4)
        results = pool.map(gets_img, datas)
        pool.close()
        pool.join()
        print("采集所有图片完成！")
    except:
        print("Error: unable to start thread")

附完整源码：

# -*- coding: UTF-8 -*-
# Author@公众号：eryeji
# https://www.peca.com.mx/

import requests
from lxml import etree
import time
import random
import re
import threading
import os
from queue import Queue
from multiprocessing.dummy import Pool as ThreadPool



def get_ua():
    ua_list = [
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1',
        'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36Chrome 17.0',
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
        'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0Firefox 4.0.1',
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
        'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
        'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
        'Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11',
    ]
    ua=random.choice(ua_list)
    return ua


def get_hrefs():
    url='https://www.peca.com.mx/'
    headers={
        "User-Agent":get_ua()
    }
    response=requests.get(url=url,headers=headers,timeout=6)
    print(response.status_code)
    html=response.content.decode('utf-8')
    #print(html)
    tree=etree.HTML(html)
    hrefs=tree.xpath('//a[@class="grid-item"]/@href')
    print(len(hrefs))
    print(hrefs)
    for href in hrefs:
        href=f'https://www.peca.com.mx{href}'
        try:
            get_detail(href)
        except Exception as e:
            print(f"采集错误：错误代码：{e}")
        time.sleep(3)




def get_detail(href):
    headers = {
        "User-Agent": get_ua()
    }
    response = requests.get(url=href, headers=headers, timeout=6)
    print(response.status_code)
    html = response.content.decode('utf-8')
    #print(html)
    tree = etree.HTML(html)
    h1=tree.xpath('//h1/text()')[0]
    pattern = r"[\/\\\:\*\?\"\<\>\|]"
    h1=re.sub(pattern, "_", h1)  # 替换为下划线
    print(h1)
    path = f'{h1}/'
    os.makedirs(path, exist_ok=True)
    print(f">> 生成保存目录 {h1} 文件夹成功！")
    ptexts=tree.xpath('//div[@class="accordion-item__dropdown"]//p/text()')
    ptext='\n'.join(ptexts)
    print(ptext)
    with open(f'{path}{h1}.txt','w',encoding='utf-8') as f:
        f.write(f'{h1}\n{ptext}')
    print(f">> 保存 {h1}.txt 文件成功！")
    imgs=tree.xpath('//div[@class="gallery-masonry-item-wrapper"]//img/@data-src')
    print(len(imgs))
    print(imgs)
    down_imgs(path, imgs)
    #down_four_imgs(path, imgs)
    #downs_imgs(path, imgs)



# 3次重试
def get_resp(url):
    i = 0
    while i < 4:
        try:
            headers = {
                "User-Agent":get_ua()
            }
            response = requests.get(url, headers=headers, timeout=10)
            print(response.status_code)
            return response
        except requests.exceptions.RequestException:
            i += 1
            print(f">> 获取网页出错，6S后将重试获取第：{i} 次")
            time.sleep(i * 2)


def down_four_imgs(path,imgs):
    imgQ=Queue()
    for img in imgs:
        imgQ.put(img)
    while not imgQ.empty():
        threadings = []
        for i in range(5):
            imgurl=imgQ.get()
            t = threading.Thread(target=get_img, args=(path,imgurl))
            threadings.append(t)
            t.start()

        for x in threadings:
            x.join()

        print(f"恭喜，四线程下载图片完成!")

    print(f"恭喜，多线程下载图片完成!")


def down_imgs(path,imgs):
    threadings = []
    for img in imgs:
        t = threading.Thread(target=get_img, args=(path,img))
        threadings.append(t)
        t.start()

    for x in threadings:
        x.join()

    print(f"恭喜，多线程下载图片完成!")


def downs_imgs(path,imgs):
    datas=[]
    for img in imgs:
        data=path,img
        datas.append(data)

    try:
        # 开4个 worker，没有参数时默认是 cpu 的核心数
        pool = ThreadPool(4)
        results = pool.map(gets_img, datas)
        pool.close()
        pool.join()
        print("采集所有图片完成！")
    except:
        print("Error: unable to start thread")


#下载图片
def gets_img(data):
    path=data[0]
    img_url=data[1]
    img_name = img_url.split('/')[-1]
    r = get_resp(img_url)
    time.sleep(1)
    with open(f'{path}{img_name}', 'wb')as f:
        f.write(r.content)
    print(f">> {img_name}下载图片成功")

#下载图片
def get_img(path,img_url):
    img_name = img_url.split('/')[-1]
    r = get_resp(img_url)
    time.sleep(1)
    with open(f'{path}{img_name}', 'wb')as f:
        f.write(r.content)
    print(f">> {img_name}下载图片成功")


def main():
    get_hrefs()



if __name__=='__main__':
    main()

Python爬虫，B站视频下载源码脚本工具助手附exe

·················END·················

你好，我是二大爷，

革命老区外出进城务工人员，

互联网非早期非专业站长，

喜好python，写作，阅读，英语

关注我的都变秃了

说错了，都变强了！

不信你试试

扫码关注最新动态

公众号ID：eryeji