Created
April 26, 2016 06:33
-
-
Save t0mst0ne/37ea38c0fbd0be681e9d0f5dc964ec8b to your computer and use it in GitHub Desktop.
Parse the Taiwan earthquake data and plot
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
import pandas as pd | |
from bs4 import BeautifulSoup | |
from bokeh.io import output_file, show | |
from bokeh.models import ( | |
GMapPlot, GMapOptions, ColumnDataSource, Circle, DataRange1d, PanTool, WheelZoomTool, BoxSelectTool | |
) | |
# Fetch the data | |
URL = 'http://scweb.cwb.gov.tw/Page.aspx?ItemId=20&loc=tw&adv=0' | |
r = requests.get(URL) | |
# parse the header and data | |
soup = BeautifulSoup(r.text, "lxml") | |
viewstate = soup.find('input', {'id' : '__VIEWSTATE'})['value'] | |
eventval = soup.find('input', {'id' : '__EVENTVALIDATION'})['value'] | |
viewgen = soup.find('input', {'id' : '__VIEWSTATEGENERATOR'})['value'] | |
cookies = r.cookies | |
headers = r.headers | |
data = {"__VIEWSTATE":viewstate,"__EVENTVALIDATION":eventval, "__VIEWSTATEGENERATOR":viewgen} | |
data['ctl03$btnSearch'] = '%E9%80%81%E5%87%BA' | |
DF = pd.DataFrame() | |
for Y in range (1995,2003): | |
data['ctl03$ddlYear'] = str(Y) | |
for M in range(1,13): | |
data['ctl03$ddlMonth'] = str(M).zfill(2) | |
r1 = requests.post(URL, data=data) | |
try: | |
df = pd.read_html(r1.text,header =0)[1] | |
df['year'] = Y | |
DF = pd.concat([DF,df]) | |
print Y,M, r1.status_code | |
except IndexError: print Y,M,'fail' | |
for Y in range (2017,2017): | |
data['ctl03$ddlYear'] = str(Y) | |
for M in range(1,13): | |
data['ctl03$ddlMonth'] = str(M).zfill(2) | |
r1 = requests.post(URL, data=data) | |
try: | |
df = pd.read_html(r1.text,header =0)[2] | |
df['year'] = Y | |
DF = pd.concat([DF,df]) | |
print Y,M, r1.status_code | |
except IndexError: print Y,M,'fail' | |
except ValueError: pass | |
map_options = GMapOptions(lat=23.8, lng=120.8, map_type="roadmap", zoom=8) #‘satellite’, ‘roadmap’, ‘terrain’, ‘hybrid’ | |
plot = GMapPlot( | |
x_range=DataRange1d(), y_range=DataRange1d() , map_options=map_options, title="台灣", plot_height = 1000, | |
plot_width = 1000, | |
) | |
source = ColumnDataSource( | |
data=dict( | |
lat=DF['緯度'].tolist(), | |
lon=DF['經度'].tolist(), | |
) | |
) | |
circle = Circle(x="lon", y="lat", size=2, fill_color="red", fill_alpha=0.5, line_color=None) | |
plot.add_glyph(source, circle) | |
plot.add_tools(PanTool(), WheelZoomTool(), BoxSelectTool()) | |
output_file("gmap_plot.html") | |
show(plot) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
wow