使用reques爬取同学的博客

import urllib.request
import sys
import gzip
from lxml import etree
print(sys.getdefaultencoding())

with open('student2.txt', 'r', encoding='utf-8') as f1:
    stuUrls = eval(f1.read())
f1.close

headers = {
    'Host': 'www.cnblogs.com',
    'Connection': 'keep-alive',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
    'Accept-Encoding': 'gzip, deflate',
    'Accept-Language': 'zh-CN,zh;q=0.9'
}

# 判断是否还有下一页
isNextPage = r'下一页'


# 根据url和伪装的header获取网页源代码


def getHtml(url, headers):
    request = urllib.request.Request(url=url, headers=headers)
    page = urllib.request.urlopen(request)
    html = page.read()
    return html

# 解压


def ungzip(data):
    data = gzip.decompress(data)
    return data


# print(data)
# 解析网页
def download(url):
    page = 1
    articleInfoRe = set()
    while True:
        url0 = url + f'/default.html?page={page}'
        html = getHtml(url0, headers)
        data = ungzip(html).decode('utf-8')
        dom = etree.HTML(data)
        # 获取第一页的数据
        # nextPage = dom.xpath('.//div[@class="pager"] ')
        postTitle2href = dom.xpath('.//a[@class="postTitle2"]/@href')
        postTitle2 = dom.xpath('.//a[@class="postTitle2"]/text()')
        for i in range(len(postTitle2)):
            article = postTitle2[i]
            article = str(article).rstrip('
')
            href = str(postTitle2href[i])
            articleInfoRe.add((article, href))
        page = page + 1
        if page == 5:
            break
    for article, href in articleInfoRe:
        print(article + '	' + href)


def main():
    for key, value in stuUrls.items():
        print('
' + key + '		' + key + '		' + key +
              '		' + key + '		' + key + '		' + '
')
        url = value
        download(url)


if __name__ == '__main__':
    main()

View Code

同学的博客列表：

 

 爬取结果:

学习总结:

　　1.利用了set去重

　　2.xpath:[.//节点名[属性=属性值]/]+text()获取文本值 （或者+@属性 获取属性值）

　　3.遍历每一行:

with open('student.txt', 'r', encoding='utf-8') as f:

    strList = f.readlines()

    for stu in strList:

        print(stu)

　　4.添加header

headers = {
'Host': 'www.cnblogs.com',
'Connection': 'keep-alive',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate',
'Accept-Language': 'zh-CN,zh;q=0.9'
}

　　5.打印默认编码:sys.getdefaultencoding()