import requests
from bs4 import BeautifulSoup
headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:93.0) Gecko/20100101 Firefox/93.0'}
def baidu(company):
    url = 'https://www.baidu.com/s?rtt=4&tn=news&word=' + company
    print(url)
    html = requests.get(url, headers=headers).text
    s = BeautifulSoup(html, 'html.parser')
    title=s.select('.news-title_1YtI1 a')
    for i in title:
        print(i.text)
# 批量調(diào)用函數(shù)
companies = ['騰訊', '阿里巴巴', '百度集團(tuán)']
for i in companies:
    baidu(i)

批量輸出多個(gè)搜索結(jié)果的標(biāo)題

結(jié)果保存為文本文件

import requests
from bs4 import BeautifulSoup
headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:93.0) Gecko/20100101 Firefox/93.0'}
def baidu(company):
    url = 'https://www.baidu.com/s?rtt=4&tn=news&word=' + company
    print(url)
    html = requests.get(url, headers=headers).text
    s = BeautifulSoup(html, 'html.parser')
    title=s.select('.news-title_1YtI1 a')
    fl=open('test.text','a', encoding='utf-8')
    for i in title:
        fl.write(i.text + '\n')
# 批量調(diào)用函數(shù)
companies = ['騰訊', '阿里巴巴', '百度集團(tuán)']
for i in companies:
    baidu(i)

寫入代碼

fl=open('test.text','a', encoding='utf-8')
for i in title:
	fl.write(i.text + '\n')

異常處理

for i in companies:
    try:
        baidu(i)
        print('運(yùn)行成功')
    except:
        print('運(yùn)行失敗')

寫在循環(huán)中不會(huì)讓程序停止運(yùn)行而會(huì)輸出運(yùn)行失敗

休眠時(shí)間

import time
for i in companies:
    try:
        baidu(i)
        print('運(yùn)行成功')
    except:
        print('運(yùn)行失敗')
time.sleep(5)

time.sleep(5)

括號(hào)里的單位是秒

放在什么位置則在什么位置休眠（暫停）

爬取多頁(yè)內(nèi)容

百度搜索騰訊

切換到第二頁(yè)

去掉多多余的

https://www.baidu.com/s?wd=騰訊&pn=10

分析出

https://www.baidu.com/s?wd=騰訊&pn=0 為第一頁(yè)
https://www.baidu.com/s?wd=騰訊&pn=10 為第二頁(yè)
https://www.baidu.com/s?wd=騰訊&pn=20 為第三頁(yè)
https://www.baidu.com/s?wd=騰訊&pn=30 為第四頁(yè)
..........

代碼

from bs4 import BeautifulSoup
import time
headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:93.0) Gecko/20100101 Firefox/93.0'}
def baidu(c):
    url = 'https://www.baidu.com/s?wd=騰訊&pn=' + str(c)+'0'
    print(url)
    html = requests.get(url, headers=headers).text
    s = BeautifulSoup(html, 'html.parser')
    title=s.select('.t a')
    for i in title:
        print(i.text)

for i in range(10):
    baidu(i)
    time.sleep(2)