python基础（六）——爬虫

内容来源：雨敲窗python教程

爬取糗事百科的段子

#_*_ coding: utf-8 _*_
import re
import requests
import html
import time

def crawl_joke_list(page = 1):
    url = "https://www.qiushibaike.com/8hr/page/" + str(page)
    res = requests.get(url)
    #获取每个段子的正则
    pattern = re.compile("<div class=\"article block untagged mb15.*?<div class=\"content\">.*?</div>", re.S)
    body = html.unescape(res.text).replace("<br/>", "\n")
    m = pattern.findall(body)
    #抽取用户名的正则
    user_pattern = re.compile("<div class=\"author clearfix\">.*?<h2>(.*?)</h2>", re.S)
    #抽取段子内容的正则
    content_pattern = re.compile("<div class=\"content\">.*?<span>(.*?)</span>.*?</div>", re.S)
    f = open("c:/Users/47864/Desktop/1.txt", "a", encoding='utf-8')
    for joke in m:
        user = user_pattern.findall(joke)
        output = []
        if len(user) > 0:
            output.append(user[0])
        content = content_pattern.findall(joke)
        if len(content) > 0:
            output.append(content[0].replace("\n", ""))
        print("\t".join(output))
        f.writelines("\t".join(output))
    time.sleep(2)
    f.close()

if __name__ == '__main__':
    for i in range(1, 10):
        crawl_joke_list(i)

爬取糗事百科图片

#_*_coding: utf-8_*_
import requests
import re

def crawl_img(img_url, img_local_path):
    r = requests.get(img_url, stream=True)
    with open(img_local_path, "wb") as f:
        f.write(r.content)

def crawl(page):
    img_path = "c:/Users/47864/Desktop/img/"
    url = "http://www.qiushibaike.com/imgrank/page/" + str(page)
    res = requests.get(url)
    content_list = re.findall("<div class=\"thumb\">(.*?)</div>", res.content.decode('utf-8'), re.S)
    for content in content_list:
        img_list = re.findall("<img src=\"(.*?)\"", content)
        for img_url in img_list:
            crawl_img("https:" + img_url, img_path + img_url.strip().split('/')[-1])

if __name__ == '__main__':
    crawl(1)

需要注意的是爬取图片的时候糗事百科网页源代码中图片的url是没有协议的，需要我们自己补上去，不然会报错requests.exceptions.MissingSchema: Invalid URL