Python爬虫——xpath().[0]的用法

①

1.1   name,无[0],无循环——打印出列表

import requests
from lxml import etree

url="https://movie.douban.com/top250"
header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"}
html = requests.get(url, headers=header).text
selector=etree.HTML(html)
name=selector.xpath('//ol[@class="grid_view"]/li/div/div[2]/div[1]/a/span[1]/text()')
print(name)
#  ['肖申克的救赎', '霸王别姬'..(省去21条记录)..'怦然心动','触不可及']

1.2   name,有[0],无循环———返回列表中第一个元素

import requests
from lxml import etree

url="https://movie.douban.com/top250"
header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"}
html = requests.get(url, headers=header).text
selector=etree.HTML(html)
name=selector.xpath('//ol[@class="grid_view"]/li/div/div[2]/div[1]/a/span[1]/text()')[0]
print(name)
#  肖申克的救赎

1.3   name,有.extract()或者.extract()[0],无循环——均报错

import requests
from lxml import etree

url="https://movie.douban.com/top250"
header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"}
html = requests.get(url, headers=header).text
selector=etree.HTML(html)
name=selector.xpath('//ol[@class="grid_view"]/li/div/div[2]/div[1]/a/span[1]/text()').extract()[0]
print(name)
#  .extract()      .extract()[0] 均报错

②

2.1    name，score，无[0],无循环——打印出两个列表

import requests
from lxml import etree

url="https://movie.douban.com/top250"
header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"}
html = requests.get(url, headers=header).text
selector=etree.HTML(html)
name=selector.xpath('//ol[@class="grid_view"]/li/div/div[2]/div[1]/a/span[1]/text()')
score=selector.xpath('//ol[@class="grid_view"]/li/div/div[2]/div[2]/div/span[2]/text()')
print(name,score)
#  ['肖申克的救赎', '霸王别姬'..(省去21条记录)..'怦然心动','触不可及']['9.7','9.6'..(省去21条记录).. '9.1','9.2']

2.2.1    name，score，有[0],无循环——分别返回两个列表中的第一个元素

import requests
from lxml import etree

url="https://movie.douban.com/top250"
header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"}
html = requests.get(url, headers=header).text
selector=etree.HTML(html)
name=selector.xpath('//ol[@class="grid_view"]/li/div/div[2]/div[1]/a/span[1]/text()')[0]
score=selector.xpath('//ol[@class="grid_view"]/li/div/div[2]/div[2]/div/span[2]/text()')[0]
print(name,score)
#  肖申克的救赎 9.7

2.2.2    name，score，有[1],无循环——分别返回两个列表中的第二个元素

import requests
from lxml import etree

url="https://movie.douban.com/top250"
header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"}
html = requests.get(url, headers=header).text
selector=etree.HTML(html)
name=selector.xpath('//ol[@class="grid_view"]/li/div/div[2]/div[1]/a/span[1]/text()')[1]
score=selector.xpath('//ol[@class="grid_view"]/li/div/div[2]/div[2]/div/span[2]/text()')[1]
print(name,score)
#  霸王别姬 9.6

③有循环

3.1.1    name，score，无[0],有循环——打印出每次循环的结果

import requests
from lxml import etree

url="https://movie.douban.com/top250"
header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"}
html = requests.get(url, headers=header).text
selector=etree.HTML(html)
lis=selector.xpath('//ol[@class="grid_view"]/li')
for oneSelector in lis:
    name=oneSelector.xpath("div/div[2]/div[1]/a/span[1]/text()")
    score=oneSelector.xpath("div/div[2]/div[2]/div/span[2]/text()")
    print(name,score)
    # ['肖申克的救赎'] ['9.7']  ----第一次循环后的结果
    # ['霸王别姬'] ['9.6']  ----第二次循环后的结果
    #  .....中间省去21条记录
    # ['怦然心动'] ['9.1']
    # ['触不可及'] ['9.2']

3.1.2    name，score，有[0],有循环——打印出每次循环的结果

import requests
from lxml import etree

url="https://movie.douban.com/top250"
header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"}
html = requests.get(url, headers=header).text
selector=etree.HTML(html)
lis=selector.xpath('//ol[@class="grid_view"]/li')
for oneSelector in lis:
    name=oneSelector.xpath("div/div[2]/div[1]/a/span[1]/text()")[0]
    score=oneSelector.xpath("div/div[2]/div[2]/div/span[2]/text()")[0]
    print(name,score)
    # 肖申克的救赎 9.7  ----第一次循环后的结果
    # 霸王别姬 9.6  ----第二次循环后的结果
    #  .....中间省去21条记录
    # 怦然心动 9.1
    # 触不可及 9.2

3.1.3    name，score，有[0],有循环——打印出最终结果

import requests
from lxml import etree

url="https://movie.douban.com/top250"
header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"}
html = requests.get(url, headers=header).text
selector=etree.HTML(html)
lis=selector.xpath('//ol[@class="grid_view"]/li')
for oneSelector in lis:
    name=oneSelector.xpath("div/div[2]/div[1]/a/span[1]/text()")[0]
    score=oneSelector.xpath("div/div[2]/div[2]/div/span[2]/text()")[0]
print(name,score)
# 触不可及 9.2

④

4.1.1    name，score，people无[0],有循环,存入一个元组中——打印出每次循环的结果

import requests
from lxml import etree

url="https://movie.douban.com/top250"
header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"}
html = requests.get(url, headers=header).text
selector=etree.HTML(html)
lis=selector.xpath('//ol[@class="grid_view"]/li')
allMovieList=[]
for oneSelector in lis:
        name=oneSelector.xpath("div/div[2]/div[1]/a/span[1]/text()")
        score=oneSelector.xpath("div/div[2]/div[2]/div/span[2]/text()")
        people=oneSelector.xpath("div/div[2]/div[2]/div/span[4]/text()")
        oneMovieList=[name,score,people]
        print(oneMovieList)
# [['肖申克的救赎'], ['9.7'], ['1918400人评价']] ----第一次循环后的结果
# [['霸王别姬'], ['9.6'], ['1411167人评价']] ----第二次循环后的结果
#          ..(省去20条记录)..
# [['怦然心动'], ['9.1'], ['1193590人评价']]
# [['触不可及'], ['9.2'], ['677191人评价']]

4.1.2    name，score，people有[0],有循环,存入一个元组中——打印出每次循环的结果

import requests
from lxml import etree

url="https://movie.douban.com/top250"
header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"}
html = requests.get(url, headers=header).text
selector=etree.HTML(html)
lis=selector.xpath('//ol[@class="grid_view"]/li')
allMovieList=[]
for oneSelector in lis:
        name=oneSelector.xpath("div/div[2]/div[1]/a/span[1]/text()")[0]
        score=oneSelector.xpath("div/div[2]/div[2]/div/span[2]/text()")[0]
        people=oneSelector.xpath("div/div[2]/div[2]/div/span[4]/text()")[0]
        oneMovieList=[name,score,people]
        print(oneMovieList)
# ['肖申克的救赎', '9.7', '1918400人评价']
# ['霸王别姬', '9.6', '1411167人评价']
#          ..(省去20条记录)..
# ['怦然心动', '9.1', '1193590人评价']
# ['触不可及', '9.2', '677191人评价']

4.2.2    name，score，people无[0],有循环,存入一个元组中后逐一添加到一个大的元组中——打印每次循环的结果

import requests
from lxml import etree

url="https://movie.douban.com/top250"
header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"}
html = requests.get(url, headers=header).text
selector=etree.HTML(html)
lis=selector.xpath('//ol[@class="grid_view"]/li')
allMovieList=[]
for oneSelector in lis:
        name=oneSelector.xpath("div/div[2]/div[1]/a/span[1]/text()")
        score=oneSelector.xpath("div/div[2]/div[2]/div/span[2]/text()")
        people=oneSelector.xpath("div/div[2]/div[2]/div/span[4]/text()")
        oneMovieList=[name,score,people]
        allMovieList.append(oneMovieList)
        print(allMovieList)
# [[['肖申克的救赎'], ['9.7'], ['1918400人评价']]]
# [[['肖申克的救赎'], ['9.7'], ['1918400人评价']], [['霸王别姬'], ['9.6'], ['1411167人评价']]]
# [[['肖申克的救赎'], ['9.7'], ['1918400人评价']], [['霸王别姬'], ['9.6'], ['1411167人评价']], [['阿甘正传'], ['9.5'], ['1458464人评价']]]

4.2.3    name，score，people有[0],有循环,存入一个元组中后逐一添加到一个大的元组中——打印每次循环的结果

import requests
from lxml import etree

url="https://movie.douban.com/top250"
header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"}
html = requests.get(url, headers=header).text
selector=etree.HTML(html)
lis=selector.xpath('//ol[@class="grid_view"]/li')
allMovieList=[]
for oneSelector in lis:
        name=oneSelector.xpath("div/div[2]/div[1]/a/span[1]/text()")[0]
        score=oneSelector.xpath("div/div[2]/div[2]/div/span[2]/text()")[0]
        people=oneSelector.xpath("div/div[2]/div[2]/div/span[4]/text()")[0]
        oneMovieList=[name,score,people]
        allMovieList.append(oneMovieList)
        print(allMovieList)
# [['肖申克的救赎', '9.7', '1918400人评价']]
# [['肖申克的救赎', '9.7', '1918400人评价'], ['霸王别姬', '9.6', '1411167人评价']]
# [['肖申克的救赎', '9.7', '1918400人评价'], ['霸王别姬', '9.6', '1411167人评价'], ['阿甘正传', '9.5', '1458464人评价']]

4.3.1    name，score，people无[0],有循环,存入一个元组中后逐一添加到一个大的元组中——打印最终结果

import requests
from lxml import etree

url="https://movie.douban.com/top250"
header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"}
html = requests.get(url, headers=header).text
selector=etree.HTML(html)
lis=selector.xpath('//ol[@class="grid_view"]/li')
allMovieList=[]
for oneSelector in lis:
        name=oneSelector.xpath("div/div[2]/div[1]/a/span[1]/text()")
        score=oneSelector.xpath("div/div[2]/div[2]/div/span[2]/text()")
        people=oneSelector.xpath("div/div[2]/div[2]/div/span[4]/text()")
        oneMovieList=[name,score,people]
        allMovieList.append(oneMovieList)
print(allMovieList)
# [[['肖申克的救赎'], ['9.7'], ['1918400人评价']], [['霸王别姬'], ['9.6'],...... ['1411167人评价']], [['阿甘正传'], ['9.5'], ['1458464人评价']]]

4.3.2    name，score，people有[0],有循环,存入一个元组中后逐一添加到一个大的元组中——打印最终结果

import requests
from lxml import etree

url="https://movie.douban.com/top250"
header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"}
html = requests.get(url, headers=header).text
selector=etree.HTML(html)
lis=selector.xpath('//ol[@class="grid_view"]/li')
allMovieList=[]
for oneSelector in lis:
        name=oneSelector.xpath("div/div[2]/div[1]/a/span[1]/text()")[0]
        score=oneSelector.xpath("div/div[2]/div[2]/div/span[2]/text()")[0]
        people=oneSelector.xpath("div/div[2]/div[2]/div/span[4]/text()")[0]
        oneMovieList=[name,score,people]
        allMovieList.append(oneMovieList)
print(allMovieList)
# [['肖申克的救赎', '9.7', '1918400人评价'], ['霸王别姬', '9.6', '1411167人评价'],...... ['触不可及', '9.2', '677191人评价']]

进入Debug调试：
第一次循环：

第二次循环：

第三次循环：

依次类推得出最总结果。

总结：

      无[0]时返回的是一个列表，有[0]时返回的是列表中的第一个元素，熟练运用Debug模式进行调试。