1. 爬虫基础

python爬虫

1. 爬取网页内容

a. 使用urllib库

# 导入模块
import urllib.request

headers = {
    "User-Agent": "User-Agent:Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11"
}
def use_urllib(url=None, headers=None):
    """
    对于一些有反爬措施的网站，需要利用headers模仿浏览器访问
    :param url:网页地址
    :param headers:用户代理
    :return:返回网页html内容
    """
    req = urllib.request.Request(url=url, headers=headers)
    response = urllib.request.urlopen(req)
    data = response.read().decode()  # 对网页内容进行解码
    print(data)
    return data

b. 使用requests库

import requests

def use_requests(url, headers=None):
    """
    :param url: 网页地址
    :param headers:用户代理，一般可不用
    :return:返回网页html内容
    """
    response = requests.get(url=url, headers=headers)
    print(response)
    data = response.text
    return data
    # print(data)

c. 使用 selenium库调用浏览器

可以用Chrome浏览器和Firefox浏览器，需要下载各自的webdriver, 谷歌浏览器见chromedriver,需要下载对应的版本;火狐浏览器见Firefoxdriver。下载完成后需要解压到编译环境所在的python目录下。

使用如下：

import selenium.webdriver as sw

def use_Chrome():
    # 选择浏览器为Chrome浏览器
    driver = sw.Chrome()
    # 传入需要访问的网址
    driver.get(url)
    # 将网页的内容赋值给data
    data = driver.page_source

    # 将data的内容保存到本地
    with open(FILE_PATH, 'w', encoding='utf-8') as f:
        f.write(data)
    # 关闭浏览器
    driver.close()

def use_Firefox():
    driver = sw.Firefox()
    driver.get(url)
    data = driver.page_source

    # 将网页内容保存到本地
    with open(FILE_PATH, 'w', encoding='utf-8') as f:
        f.write(data)
    driver.close()

2. 爬取某读书网站的小说分类的前十页书

import requests
import selenium.webdriver as sw
from bs4 import BeautifulSoup
import csv

# 书名
book_name_list = []
# 作者
author_name_list = []
# 简介
abstract_list = []

for i in range(0, 10):
    	# 通过翻页获取网址的规律，写入外层循环
        url = "https://www.dushu.com/book/1078_" + str(i + 1) + ".html"
        response = requests.get(url)
        data = response.text
		# BeautifulSoup方法解析网页内容
        soup = BeautifulSoup(data, "html.parser")
        for i in range(40):
            # 找到每页书名对应选择器的样式
            book_name = soup.select("body > div:nth-child(6) > div > "
                                    "div.span19.padding-left > div.bookslist "
                                    "> ul > li:nth-child(" + str(
                i + 1) + ") > div "
                         "> h3 > a")
            author_name = soup.select("body > div:nth-child(6) > div > "
                                      "div.span19.padding-left > "
                                      "div.bookslist > ul > li:nth-child("
                                      "" + str(
                i + 1) + ") > div > p:nth-child(3)")
            abstract = soup.select("body > div:nth-child(6) > div > "
                                   "div.span19.padding-left > div.bookslist >"
                                   " ul > li:nth-child(" + str(
                i + 1) + ") > div > "
                         "p.disc.eps")
            # 将解析得到的书名、作者、简介存到列表中	
            for book_name in book_name:
                book_name_list.append(
                    book_name.get_text().replace("\n", "").replace(" ", ""))
                # print(book_name.get_text().replace("\n", "").replace(" ", ""))
            for author_name in author_name:
                # print(author_name)
                author_name_list.append(
                    author_name.get_text().replace("\n", "").replace(" ", ""))
            for abstract in abstract:
                abstract_list.append(
                    abstract.get_text().replace("\n", "").replace(" ", ""))

找相应样式，在网页右键检查元素->操作框左上角->选择一个元素检测->选择书名->右键复制selector

3. 将爬取的内容写入csv文件

def save_csv(path):
    with open(path, 'w', newline='',encoding='utf_8_sig') as f:
        # 定义表头名
        fieldnames = ["书名", "作者", "简介"]
        # 以字典形式写入
        f_csv = csv.DictWriter(f, fieldnames)
        # 写入表头
        f_csv.writeheader()
        for i in range(len(book_name_list)):
        # 循环写入行，key值需要和表头值对应
            f_csv.writerow({
                "书名": book_name_list[i],
                "作者": author_name_list[i],
                "简介": abstract_list[i],
            })

结果如下：