Python爬虫必备技巧详细总结

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)
# 批量调用函数
companies = ['腾讯', '阿里巴巴', '百度集团']
for i in companies:
    baidu(i)

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')
# 批量调用函数
companies = ['腾讯', '阿里巴巴', '百度集团']
for i in companies:
    baidu(i)

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

for i in companies:
    try:
        baidu(i)
        print('运行成功')
    except:
        print('运行失败')

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

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=腾讯&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)