爬虫之多线程、异步

1.使用传统方式爬取“斗图啦”网站的图片

#-*-coding = utf-8 -*-
import requests
from lxml import etree
import re
import os.path
from urllib import request

def parse_page(url):
    headers = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36'}
    response = requests.get(url=url,headers=headers)
    text = response.text
    parse = etree.HTMLParser(encoding='utf-8')
    html = etree.fromstring(text,parser=parse)
    images = html.xpath('//div[@class="page-content text-center"]//a//img[@class!="gif"]')
    for img in images:
        img_url = img.get("data-original")
        img_name = img.get("alt")
        img_name = re.sub(r'[?？！!./,，。]','',img_name)
        img_postfix = os.path.splitext(img_url)[1]
        img_save_path = os.path.join('E:\study',img_name+img_postfix)
        request.urlretrieve(img_url,img_save_path)

def main():
    for page in range(1,101):
        url = 'https://www.doutula.com/photo/list/?page=%d' %page
        parse_page(url)
       

if __name__=='__main__':
    main()

 2.使用生产者与消费者模式多线程下载表情包

#-*-coding = utf-8 -*-
import requests
from lxml import etree
import re
import os.path
from urllib import request
import threading
from queue import Queue

class Producer(threading.Thread):
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36'}

    def __init__(self,page_queue,image_queue,*args,**kwargs):
        super(Producer,self).__init__(*args,**kwargs)
        self.page_queue = page_queue
        self.image_queue = image_queue
    def run(self):
        while True:
            if self.page_queue.empty():
                break
            url = self.page_queue.get()
            self.parse_page(url)

    def parse_page(self,url):
        response = requests.get(url=url,headers=self.headers)
        text = response.text
        parse = etree.HTMLParser(encoding='utf-8')
        html = etree.fromstring(text,parser=parse)
        images = html.xpath('//div[@class="page-content text-center"]//a//img[@class!="gif"]')
        for img in images:
            img_url = img.get("data-original")
            img_name = img.get("alt")
            img_name = re.sub(r'[，。？！*,\\.?/]','',img_name)
            img_postfix = os.path.splitext(img_url)[1]
            img_save_path = os.path.join('E:\study',img_name+img_postfix)
            self.image_queue.put((img_url,img_save_path))
class Consumer(threading.Thread):
    def __init__(self,page_queue,image_queue,*args,**kwargs):
        super(Consumer,self).__init__(*args,**kwargs)
        self.page_queue = page_queue
        self.image_queue = image_queue
    def run(self):
        while True:
            if self.image_queue.empty() and self.page_queue.empty():
                return
            img = self.image_queue.get(block=True)
            url,path = img
            request.urlretrieve(url,path)
            print(path + "下载完成！")


def main():
    page_queue = Queue(100)
    img_queue = Queue(1000)
    for page in range(1,101):
        url = 'https://www.doutula.com/photo/list/?page=%d' %page
        page_queue.put(url)
    for x in range(5):
        producer = Producer(page_queue,img_queue)
        producer.start()
    for x in range(5):
        consumer = Consumer(page_queue,img_queue)
        consumer.start()

if __name__=='__main__':
    main()

 使用生产者消费者模式下载内涵段子并保存在csv文件

#-*-coding = utf-8 -*-
import requests
from lxml import etree
import threading
from queue import Queue
import csv

class Producer(threading.Thread):
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36'}

    def __init__(self,page_queue,joke_queue,*args,**kwargs):
        super(Producer,self).__init__(*args,**kwargs)
        self.page_queue = page_queue
        self.joke_queue = joke_queue

    def run(self):
        while True:
            if self.page_queue.empty():
                break
            url = self.page_queue.get()
            self.parse_page(url)

    def parse_page(self,url):
        response = requests.get(url=url,headers=self.headers)
        text = response.text
        parse = etree.HTMLParser(encoding='utf-8')
        html = etree.fromstring(text,parser=parse)
        descs = html.xpath("//div[@class='j-r-list-c-desc']//a")
        for a in descs:
            joke = a.xpath("text()")
            joke_content = "\n".join(joke).strip()
            link = 'http://www.budejie.com'+ a.xpath("@href")[0]
            self.joke_queue.put((joke_content,link))
        print('=' * 30 + "第%s页下载完成！" % url.split('/')[-1] + "=" * 30)

class Consumer(threading.Thread):
    def __init__(self,page_queue,joke_queue,csvfilepath,*args,**kwargs):
        super(Consumer,self).__init__(*args,**kwargs)
        self.page_queue = page_queue
        self.joke_queue = joke_queue
        self.lock = threading.Lock()#创建锁
        self.csvfilepath = csvfilepath

    def run(self):
        while True:
            if self.joke_queue.empty() and self.page_queue.empty():
                return
            joke ,link= self.joke_queue.get()
            self.lock.acquire()
            self.writecsv((joke,link))
            self.lock.release()

    def writecsv(self,row):
        with open(self.csvfilepath, "a+", newline='', encoding='utf-8')as csvfile:
            writer = csv.writer(csvfile,dialect='excel')
            writer.writerow(row)

def main():
    page_queue = Queue(10)
    joke_queue = Queue(1000)
    csvfilepath = r'E:\study\joke.csv'

    for page in range(1,11):
        url = 'http://www.budejie.com/text/%d' %page
        page_queue.put(url)
    for x in range(5):
        producer = Producer(page_queue,joke_queue)
        producer.start()
    for x in range(5):
        consumer = Consumer(page_queue,joke_queue,csvfilepath)
        consumer.start()

if __name__=='__main__':
    main()

 

 

 

>>>>>>>>>>待续