bs4爬虫入门

# -*- coding: utf-8 -*-
"""
Created on Fri Nov 16 13:35:33 2018

@author: zhen
"""
import urllib
import urllib.request
from bs4 import BeautifulSoup

# 设置目标rootUrl，使用urllib.request.Request创建请求
rootUrl = "https://www.cnblogs.com/"
request = urllib.request.Request(rootUrl)

header = "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36"
# 使用add_header设置请求头，将代码伪装成浏览器
request.add_header("User-Agent", header)

# 使用urllib.request.urlopen打开页面，使用read方法保存html代码
htmlUrl = urllib.request.urlopen(request).read()

# 使用BeautifulSoup创建html代码的BeautifulSoup实例，存为beautifulSoup
beautifulSoup = BeautifulSoup(htmlUrl)

# 获取尾页（对照前一小节获取尾页的内容看你就明白了）
total_page = int(beautifulSoup.find("div",class_= "pager").findAll("a")[-2].get_text())

list_item = beautifulSoup.findAll("a",class_="titlelnk")
for i in list_item: # 遍历所有的内容
    href = i["href"] # 获取对应的href
    req = urllib.request.Request(href)
    req.add_header("User-Agent", header)
    html = urllib.request.urlopen(req).read()
    soup = BeautifulSoup(html)
    # 获取标题
    titleContent = soup.find("a", id="cb_post_title_url")
    if titleContent is not None: # 判读是否为空
        title = titleContent.get_text()   
        # 获取内容
        content = soup.find("div").get_text().strip()
        print(title, "\n=====================================\n", content[1:100])

爬虫结果：