-
大小: 4KB文件類型: .py金幣: 2下載: 1 次發(fā)布日期: 2021-06-05
- 語言: Python
- 標(biāo)簽: 網(wǎng)絡(luò)爬蟲??
資源簡(jiǎn)介
爬取百度遷徙數(shù)據(jù),使用python語言,使用時(shí)需要輸入日期,然后自動(dòng)生成表格
代碼片段和文件信息
from?urllib?import?request
from?urllib?import?error
import?re
import?xlrd
import?xlwt
import?threading
def?set_style(name?height?bold=False):
????style?=?xlwt.XFstyle()??#?初始化樣式
????font?=?xlwt.Font()??#?為樣式創(chuàng)建字體
????font.name?=?name??#?‘Times?New?Roman‘
????font.bold?=?bold
????font.color_index?=?4
????font.height?=?height
????#?borders=?xlwt.Borders()
????#?borders.left=?6
????#?borders.right=?6
????#?borders.top=?6
????#?borders.bottom=?6
????style.font?=?font
????#?style.borders?=?borders
????return?style
f?=?xlwt.Workbook()
sheet2?=?f.add_sheet(u‘sheet2‘?cell_overwrite_ok=True)??#?創(chuàng)建sheet2
row0?=?[u‘遷入城市‘u‘所在城市‘u‘lyd‘u‘遷出城市‘u‘所在城市‘u‘lyd‘]
?#?生成第一行
for?i?in?range(0?len(row0)):
????sheet2.write(0?i?row0[i]?set_style(‘Times?New?Roman‘?200?True))
headers?=?{“User-agent“:“Mozilla/5.0?(Windows?NT?10.0;?WOW64)?AppleWebKit/537.36?(KHTML?like?Gecko)?Chrome/49.0.2623.221?Safari/537.36?SE?2.X?metaSr?1.0“}
opener?=?request.build_opener()
opener.add_headers?=?[headers]
request.install_opener(opener)
riqi?=?input(“日期是:“)
#ID?=?[5354315317316348224161346163365]
#name?=?[“長(zhǎng)春““延邊““南京““無錫““徐州““常州““蘇州““南通““揚(yáng)州““南昌““贛州“]
ID?=?[48218125121150265148151266307149191208158268153267152154308309]
name?=?[“哈爾濱““武漢““海口““三亞““石家莊““唐山““秦皇島““邯鄲““邢臺(tái)““保定““滄州““廊坊““衡水““長(zhǎng)沙““鄭州““洛陽““安陽““新鄉(xiāng)““商丘““周口““南陽“]
for?i?in?range(0len(ID)):
????firsturl?=?“http://huiyan.baidu.com/migration/api/cityrank?dt=city&id=“+str(ID[i])+“&type=move_in&date=“+str(riqi)+“&callback=jsonp“
????data?=?request.urlopen(firsturl).read().decode(“utf-8“)
????data?=?data.encode(“utf-8“).decode(“unicode_escape“)
????#對(duì)Unicode編碼進(jìn)行改造
????pat?=?‘{“city_name“:“(.*?)““province_name“:“.*?““valu
評(píng)論
共有 條評(píng)論